@juspay/neurolink 12.41.10 → 12.42.0

package/docs-site/static/search-index.json

@@ -5318,6 +5318,17 @@
 {"objectID":"a829c7ea7d755ed69e4f2fd66b9b4181706ea927fafe747aff052ff1694e3208","title":"Verification status","url":"/docs/getting-started/providers/api-route#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog records for API Route:\n\n| Probe                 | Result                                                                                                                                                                                                                                    |\n| --------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                | authenticated GET /v1/models, HTTP 200, 2026-09-17                                                                                                                                                                                        |\n| Auth rejection        | HTTP 401, 2026-09-17                                                                                                                                                                                                                      |\n| Live capability sweep | 2026-09-17 — Verified live against https://global.api-route.com/v1: GET /v1/models returned 70 models. Chat completions, streaming, function calling, streamed function calling, and structured JSON output (jsonobject and jsonschema) |","hierarchy":{"lvl0":"Getting Started","lvl1":"API Route Provider Guide","lvl2":"Verification status","lvl3":""}},
 {"objectID":"bc92ecfff94022bb7ac65c46d0f0420c49b1d1aa6ad44d3ddbd10aca4cb2808f","title":"Troubleshooting","url":"/docs/getting-started/providers/api-route#troubleshooting","content":"| Symptom                     | Cause                               | Fix                                                               |\n| --------------------------- | ----------------------------------- | ----------------------------------------------------------------- |\n| Invalid API Route API key | API_ROUTE_API_KEY unset or wrong  | Check the key at https://api-route.com                            |\n| Model not found             | The roster changed since 2026-09-17 | Pick a current id; catalog providers retire models without notice |","hierarchy":{"lvl0":"Getting Started","lvl1":"API Route Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
 {"objectID":"7bc9dfff71486ee8ef56b766b5763a939281319919c770f077801f72de82566e","title":"See also","url":"/docs/getting-started/providers/api-route#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"API Route Provider Guide","lvl2":"See also","lvl3":""}},
+{"objectID":"ff86b3e34afb9ba8b89efbf7279850f8df16470b0bab216f27b1ae2775bba21b","title":"Arcee Provider Guide","url":"/docs/getting-started/providers/arcee","content":"Arcee Provider Guide\n\nArcee is a Tier-2 catalog provider: OpenAI-wire-compatible, so its entire\nintegration is one JSON file (src/lib/providers/catalog/arcee.json) rather\nthan hand-written code. That file is the source of truth for everything on this\npage.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's GET https://api.arcee.ai/api/v1/models needs a\nkey (it answers HTTP 401 without one), so the model ids come from Arcee's\npublic docs and the roster has not been checked. No account was created and no\nAPI key was used to build this entry. evidence.liveMatrix is null until\nsomeone runs the live capability matrix with a real key (see\nVerification status below).\n\nKey Facts\nProvider id: arcee\nProtocol: OpenAI-compatible (/chat/completions). The\n  Your First API Call page\n  says \"The Arcee Platform API is OpenAI compatible.\"\nBase URL: https://api.arcee.ai/api/v1 — the base_url value in the\n  Quick Start Python example\n  and the baseURL value in its JavaScript example. The\n  Your First API Call page\n  table lists base_url as https://api.arcee.ai/api/v1/chat/completions;\n  wire.baseURL is the value the SDK examples set\nDefault model: trinity-large-thinking — the API Model Name the\n  Arcee Model Overview\n  lists for Trinity-Large-Thinking (400B), which the page says is \"the only Arcee\n  model available via api.\"\nModels in catalog: 10 — the ten rows of the \"Text Models\" table on the\n  pricing page\nStreaming: supported — the\n  Streaming Messages page\n  says \"To enable streaming, set stream=True.\"\nTool calling: model-dependent — the\n  Function Calling page\n  documents the tools parameter and the tool_calls output with a\n  MODEL_NAME placeholder, and the\n  Trinity-Large-Thinking page\n  lists \"Purpose-built for tool calling, multi-step planning, and agent\n  workflows\" under Key Features\nTools while streaming: false — not exercised, since no POST request was\n  sent\nStructured output: true — the\n  Structured Outputs page\n  documents the response_format value {'type': 'json_object'}. Under \"To\n  enable JSON Output, users should:\" the page lists \"Include the word \"json\" in\n  the system or user prompt, and provide an example of the desired JSON format\n  to guide the model in outputting valid JSON.\" and \"Set the max_tokens\n  parameter reasonably to prevent the JSON string from being truncated\n  midway.\"\n  quirks.responseFormatDowngrade is set so a generate({ schema }) request\n  sends json_object; NeuroLink still validates the response against your\n  schema on the client. No request with json_schema was sent\nStructured output + tools together: false — no combined probe was run\n  without credentials\nEmbeddings: false\nThinking: false — the entry sets no thinking-level request parameter.\n  The Reasoning Traces page\n  documents the reasoning_content response field for Trinity-Large-Thinking\nReasoning replay (quirks.replayReasoningContent: true): the\n  Trinity-Large-Thinking page says \"thinking tokens must be kept in context for\n  multi-turn conversations and agentic loops to function correctly\", and the\n  Reasoning Traces page says \"use reasoning_content when constructing\n  assistant messages for input\". NeuroLink sends each assistant turn's\n  reasoning_content back on later requests. No multi-turn request was sent\nBilling: schema value no-free-tier, see Billing below\nKey format: none declared. The\n  Chat Completion reference\n  gives the key format as \"Arcee API key (prefixed with rcai-)\"; NeuroLink does\n  not validate it because no key was available to test it\n\nQuick Start\nGet an API key\nVisit: https://platform.arcee.ai/api/api-keys — the Quick Start says to access the Arcee Platform (https://platform.arcee.ai/), \"Register or Login.\", then to \"Create an API Key in the API Keys management page.\" and \"Copy your API Key for use and store in a secure location.\"\nAuthentication is HTTP Bearer: the Quick Start's curl example sends the header Authorization: Bearer YOURAPIKEY, and the Chat Completion reference (https://docs.arcee.ai/api-reference/chat-completion.md) gives the key format as \"Arcee API key (prefixed with rcai-)\"\nBilling as the vendor states it: the Quick Start says to open the Wallet (https://platform.arcee.ai/api/wallet) \"to top up if needed\"; the Chat Completion reference lists HTTP 402 as \"Insufficient Balance\"\nSet ARCEE_API_KEY in your .env file\nConfigure\nUse it\n\nPer-request credentials use the same shape as the other catalog providers:\n\nBilling\n\nThe Quick Start says to open\nthe Wallet (https://platform.arcee.ai/api/wallet) \"to top up if needed\". The\nChat Completion reference\nlists HTTP 402 as \"Insufficient Balance\". The\npricing page says \"All prices are\nin USD.\" and lists prices per 1M tokens.\n\nThe catalog schema has no unknown billing value, so billingPolicy holds\nno-free-tier. It is a schema value, not a vendor statement of signup terms.\n\nModels\n\n| Model                               | Context | Vision | $/M in · out (cached)  | Notes                                          ","hierarchy":{"lvl0":"Getting Started","lvl1":"Arcee Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"2ae7f55564fe4ef4d1f94b2412de0f00a713d532c0af12c8d42e9fd543672cc4","title":"Arcee Provider Guide","url":"/docs/getting-started/providers/arcee#arcee-provider-guide","content":"Arcee is a Tier-2 catalog provider: OpenAI-wire-compatible, so its entire\nintegration is one JSON file (src/lib/providers/catalog/arcee.json) rather\nthan hand-written code. That file is the source of truth for everything on this\npage.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's GET https://api.arcee.ai/api/v1/models needs a\nkey (it answers HTTP 401 without one), so the model ids come from Arcee's\npublic docs and the roster has not been checked. No account was created and no\nAPI key was used to build this entry. evidence.liveMatrix is null until\nsomeone runs the live capability matrix with a real key (see\nVerification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"Arcee Provider Guide","lvl2":"Arcee Provider Guide","lvl3":""}},
+{"objectID":"071a8e4a5fe3f512c4b32bd583c1f067925f09a824cfede9b1cc4f0af2c46069","title":"Key Facts","url":"/docs/getting-started/providers/arcee#key-facts","content":"Provider id: arcee\nProtocol: OpenAI-compatible (/chat/completions). The\n  Your First API Call page\n  says \"The Arcee Platform API is OpenAI compatible.\"\nBase URL: https://api.arcee.ai/api/v1 — the base_url value in the\n  Quick Start Python example\n  and the baseURL value in its JavaScript example. The\n  Your First API Call page\n  table lists base_url as https://api.arcee.ai/api/v1/chat/completions;\n  wire.baseURL is the value the SDK examples set\nDefault model: trinity-large-thinking — the API Model Name the\n  Arcee Model Overview\n  lists for Trinity-Large-Thinking (400B), which the page says is \"the only Arcee\n  model available via api.\"\nModels in catalog: 10 — the ten rows of the \"Text Models\" table on the\n  pricing page\nStreaming: supported — the\n  Streaming Messages page\n  says \"To enable streaming, set stream=True.\"\nTool calling: model-dependent — the\n  Function Calling page\n  documents the tools parameter and the tool_calls output with a\n  MODEL_NAME placeholder, and the\n  Trinity-Large-Thinking page\n  lists \"Purpose-built for tool calling, multi-step planning, and agent\n  workflows\" under Key Features\nTools while streaming: false — not exercised, since no POST request was\n  sent\nStructured output: true — the\n  Structured Outputs page\n  documents the response_format value {'type': 'json_object'}. Under \"To\n  enable JSON Output, users should:\" the page lists \"Include the word \"json\" in\n  the system or user prompt, and provide an example of the desired JSON format\n  to guide the model in outputting valid JSON.\" and \"Set the max_tokens\n  parameter reasonably to prevent the JSON string from being truncated\n  midway.\"\n  quirks.responseFormatDowngrade is set so a generate({ schema }) request\n  sends json_object; NeuroLink still validates the response against your\n  schema on the client. No request with json_schema was sent\nStructured output + tools together: false — no combined probe was run\n  without credentials\nEmbeddings: false\nThinking: false — the entry sets no","hierarchy":{"lvl0":"Getting Started","lvl1":"Arcee Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"92b86e47a9502515df434cddd600ea4bc68f7dfa2582d4a733f364ceaed77e39","title":"1. Get an API key","url":"/docs/getting-started/providers/arcee#1-get-an-api-key","content":"Visit: https://platform.arcee.ai/api/api-keys — the Quick Start says to access the Arcee Platform (https://platform.arcee.ai/), \"Register or Login.\", then to \"Create an API Key in the API Keys management page.\" and \"Copy your API Key for use and store in a secure location.\"\nAuthentication is HTTP Bearer: the Quick Start's curl example sends the header Authorization: Bearer YOURAPIKEY, and the Chat Completion reference (https://docs.arcee.ai/api-reference/chat-completion.md) gives the key format as \"Arcee API key (prefixed with rcai-)\"\nBilling as the vendor states it: the Quick Start says to open the Wallet (https://platform.arcee.ai/api/wallet) \"to top up if needed\"; the Chat Completion reference lists HTTP 402 as \"Insufficient Balance\"\nSet ARCEE_API_KEY in your .env file","hierarchy":{"lvl0":"Getting Started","lvl1":"Arcee Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"caf52d468e76358475deffb490ae4de2d4425025b97bb7f682623a7da0da7d3e","title":"3. Use it","url":"/docs/getting-started/providers/arcee#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Arcee Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"f1a15ae0efe1adf5579e561842ee01ec3f214c216f98323882cba19135da601c","title":"CLI","url":"/docs/getting-started/providers/arcee#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider arcee\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"arcee\",\n  credentials: { arcee: { apiKey: process.env.ARCEEAPIKEY } },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"Arcee Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"d4862d73f0e93772d48382c16d8e705fc9f314d58d191b1f65874d45b61cfd66","title":"Billing","url":"/docs/getting-started/providers/arcee#billing","content":"The Quick Start says to open\nthe Wallet (https://platform.arcee.ai/api/wallet) \"to top up if needed\". The\nChat Completion reference\nlists HTTP 402 as \"Insufficient Balance\". The\npricing page says \"All prices are\nin USD.\" and lists prices per 1M tokens.\n\nThe catalog schema has no unknown billing value, so billingPolicy holds\nno-free-tier. It is a schema value, not a vendor statement of signup terms.","hierarchy":{"lvl0":"Getting Started","lvl1":"Arcee Provider Guide","lvl2":"Billing","lvl3":""}},
+{"objectID":"c6c6db44f3da778b5abdbfd9c1bbd6f05501d92f9cd958db15c57d55e94ab04e","title":"Models","url":"/docs/getting-started/providers/arcee#models","content":"| Model                               | Context | Vision | $/M in · out (cached)  | Notes                                                                                                                                                                                        |\n| ----------------------------------- | ------- | ------ | ---------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| trinity-large-thinking ⭐         | 128,000 | no     | $0.25 / $0.80 ($0.06)  | NeuroLink default. Strength \"Robust generalist model with strong performance across reasoning, coding, math, and complex task decomposition.\" Context Window \"512k tokens (hosted at 128k)\". |\n| deepseek/deepseek-v4-flash-latest | —       | no     | $0.14 / $0.28 ($0.028) | NeuroLink fallback; listed under \"Text Models\".                                                                                                                                              |\n| zai-org/glm-5.3-flash             | —       | no     | $0.15 / $0.50 ($0.03)  | NeuroLink fallback; listed under \"Text Models\".                                                                                                                                              |\n| thinkingmachines/inkling-small    | —       | no     | $0.50 / $1.20 ($0.10)  | NeuroLink fallback; listed under \"Text Models\".                                                                                                                                              |\n| deepseek/deepseek-v4-pro-0813     | —       | no     | $1.32 / $3.96 ($0.044) | NeuroLink fallback; listed under \"Text Models\".                                                                                                                                              |\n| deepseek/deepseek-v4-pro          | —       | no     | $1.74 / $3.48 ($0.20)  | Neur","hierarchy":{"lvl0":"Getting Started","lvl1":"Arcee Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"eb0296d1c968da1acf98e871118bbd82a5e0a71429c4663229fddac04925a4b7","title":"Verification status","url":"/docs/getting-started/providers/arcee#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the catalog\ncurrently records for Arcee — docs-verified only, not live-verified:\n\n| Probe                     | Result                                                                                                                                                                                                                                                                                                                                                                                   |\n| ------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                    | unauthenticated GET /api/v1/models answers HTTP 401 without a key (2026-09-29), so model ids are taken from the pricing page; roster not verified. The Models reference documents this endpoint with a 401 response described as \"Authentication Fails\"                                                                               |\n| Auth-failure shape        | unauthenticated GET /models answered HTTP 401 with header www-authenticate: Bearer and body {\"detail\":\"Missing or invalid Authorization header. Expected: Bearer <api_key>\"} (2026-09-29); the Chat Completion reference Error schema has one property, detail. errorRules carry the 401, 402, 403, 429 and 503 rows |\n| /chat/completions GET   | unauthenticated GET /chat/completions answered HTTP 405 with header allow: POST and body {\"error\":{\"message\":\"Method Not Allowed\",\"type\":\"invalid_request_error\",\"param\":null,\"code\":\"request.rejected\"}} (2026-09-29). No POST request was s","hierarchy":{"lvl0":"Getting Started","lvl1":"Arcee Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"640b1c4a424b242e66a782e95642f99e2e225ef16671bc16eeb29b4bfc84ab0b","title":"Troubleshooting","url":"/docs/getting-started/providers/arcee#troubleshooting","content":"The rows below are the statuses the vendor's\nChat Completion reference\nlists; NeuroLink's errorRules map 401, 402, 403, 429 and 503 to error classes.\n\n| Symptom  | What the Chat Completion reference says |\n| -------- | --------------------------------------- |\n| HTTP 400 | \"Invalid Format\"                        |\n| HTTP 401 | \"Authentication Fails\"                  |\n| HTTP 402 | \"Insufficient Balance\"                  |\n| HTTP 403 | \"Permission Denied\"                     |\n| HTTP 404 | \"Not Found\"                             |\n| HTTP 422 | \"Invalid Parameters\"                    |\n| HTTP 429 | \"Rate Limit Reached\"                    |\n| HTTP 500 | \"Server Error\"                          |\n| HTTP 503 | \"Server Overloaded\"                     |","hierarchy":{"lvl0":"Getting Started","lvl1":"Arcee Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
+{"objectID":"f6f2b1871f3f93d8548b8436375e503a0a399d0fd60115810a1618877b40bb32","title":"See also","url":"/docs/getting-started/providers/arcee#see-also","content":"Provider setup overview\nProviders index\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Arcee Provider Guide","lvl2":"See also","lvl3":""}},
 {"objectID":"2b53ae5d3ad0ee42ef2f6b71b622281914c1d1248ca4cb70e4abb74f3d154426","title":"Atlas Cloud Provider Guide","url":"/docs/getting-started/providers/atlas-cloud","content":"Atlas Cloud Provider Guide\n\nAtlas Cloud is a Tier-2 catalog provider: OpenAI-wire-compatible with no\nbehavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/atlas-cloud.json) rather than hand-written code.\nThat file is the source of truth for everything on this page.\n\nVerification status: this entry is docs- and roster-verified, not yet\nlive-verified. Every field below comes from Atlas Cloud's own public\ndocumentation and an unauthenticated GET /v1/models call — no account was\ncreated and no API key was used to build it. evidence.liveMatrix is null\nuntil someone runs the live capability matrix with a real key (see\nVerification status below).\n\nKey Facts\nProvider id: atlas-cloud\nProtocol: OpenAI-compatible (POST /v1/chat/completions, Bearer auth) —\n  Atlas Cloud's LLM API Protocols page\n  (docs/llm-protocols) also\n  lists Anthropic Messages, Responses and Gemini formats on the same base URL;\n  NeuroLink uses only the chat-completions one\nBase URL: https://api.atlascloud.ai/v1 (the /v1 suffix is required —\n  docs/models/llm)\nDefault model: deepseek-ai/deepseek-v3.2 — Atlas Cloud is an\n  aggregator with no single house model; this is the model its own\n  chat-completions, Anthropic-Messages and Responses examples all use\nModels in catalog: 10 (curated from a 120-model live roster)\nStreaming: supported — the LLM / Chat page states the API \"supports both\n  streaming and non-streaming modes\"\nTool calling: model-dependent — the docs say tools, tool_choice and\n  parallel_tool_calls are passed through on models that advertise tools\nStructured output: supported — response_format accepts json_object\n  and json_schema on models that advertise json_mode or\n  structured_outputs; every model in this catalog advertises one of them\nStructured output + tools together: not declared (false) — no combined\n  probe was run without credentials\nTool calls under streaming: not declared (false) — no page describes\n  streamed tool-call deltas\nThinking: declared (true) — the default model carries the roster's\n  reasoning feature and the protocols page documents normalised reasoning\n  flags (enable_thinking, thinking.type, reasoning_effort: \"none\"); not\n  exercised live\nEmbeddings: false — the protocols page lists /v1/embeddings under\n  \"Not available\"\nBilling: no-free-tier is the conservative schema value, not a\n  verified fact — see Billing below\nKey format: starts with apikey- (docs/llm-protocols)\n\nQuick Start\nGet an API key\nVisit: https://www.atlascloud.ai/login and sign up or sign in (Google, GitHub, or email and password — one page handles both, see https://www.atlascloud.ai/docs/account/sign-in)\nOpen https://www.atlascloud.ai/console/api-keys, choose Create API Key and copy it immediately — it is shown only once (https://www.atlascloud.ai/docs/api-keys), and Atlas Cloud API keys begin with apikey- (https://www.atlascloud.ai/docs/llm-protocols)\nBilling is pay-as-you-go from a prepaid balance: the quick start's Step 3 is Add Funds with a $25 minimum top-up (https://www.atlascloud.ai/docs/get-started), and requests are rejected with 402 while the balance is insufficient (https://www.atlascloud.ai/docs/errors). The homepage FAQ also says 'No credit card required to start', but no free-tier terms are documented, so check your balance at https://www.atlascloud.ai/console/billing before relying on it\nSet ATLAS_CLOUD_API_KEY in your .env file (ATLASCLOUD_API_KEY, the name used in Atlas Cloud's own docs, is also read)\nConfigure\nUse it\n\nPer-request credentials work as they do for every provider:\n\nModels\n\n| Model                                | Context | Vision | $/M in · out                  | Notes                                                                                                                                                                                                                                                          |\n| ------------------------------------ | ------- | ------ | ----------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| deepseek-ai/deepseek-v3.2 ⭐       | 164K    | no     | $0.26 / $0.38 (cached $0.13)  | Default here because the chat-completions, Anthropic Messages and Responses examples on the LLM API Protocols page use it (the vendor does not recommend it); roster tags tools, structured_outputs, reasoning; model page says 128K context, see below. |\n| deepseek-ai/deepseek-v4-flash      | 1M      | no     | $0.14 / $0.28 (cached $0.028) | First fallback; 393K output ceiling on the roster.                                                                                                                                                                                                             |\n| zai-org/glm-5.3                    | 1M     ","hierarchy":{"lvl0":"Getting Started","lvl1":"Atlas Cloud Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"2e3964893f5fac4fdf23a40a8f78ed2d178bfe8d1132363a45cfe5a801e0c3f3","title":"Atlas Cloud Provider Guide","url":"/docs/getting-started/providers/atlas-cloud#atlas-cloud-provider-guide","content":"Atlas Cloud is a Tier-2 catalog provider: OpenAI-wire-compatible with no\nbehavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/atlas-cloud.json) rather than hand-written code.\nThat file is the source of truth for everything on this page.\n\nVerification status: this entry is docs- and roster-verified, not yet\nlive-verified. Every field below comes from Atlas Cloud's own public\ndocumentation and an unauthenticated GET /v1/models call — no account was\ncreated and no API key was used to build it. evidence.liveMatrix is null\nuntil someone runs the live capability matrix with a real key (see\nVerification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"Atlas Cloud Provider Guide","lvl2":"Atlas Cloud Provider Guide","lvl3":""}},
 {"objectID":"928f739f548a3cde6c6876f9d9a29d5c784fd6d8ace60cae744204f140852573","title":"Key Facts","url":"/docs/getting-started/providers/atlas-cloud#key-facts","content":"Provider id: atlas-cloud\nProtocol: OpenAI-compatible (POST /v1/chat/completions, Bearer auth) —\n  Atlas Cloud's LLM API Protocols page\n  (docs/llm-protocols) also\n  lists Anthropic Messages, Responses and Gemini formats on the same base URL;\n  NeuroLink uses only the chat-completions one\nBase URL: https://api.atlascloud.ai/v1 (the /v1 suffix is required —\n  docs/models/llm)\nDefault model: deepseek-ai/deepseek-v3.2 — Atlas Cloud is an\n  aggregator with no single house model; this is the model its own\n  chat-completions, Anthropic-Messages and Responses examples all use\nModels in catalog: 10 (curated from a 120-model live roster)\nStreaming: supported — the LLM / Chat page states the API \"supports both\n  streaming and non-streaming modes\"\nTool calling: model-dependent — the docs say tools, tool_choice and\n  parallel_tool_calls are passed through on models that advertise tools\nStructured output: supported — response_format accepts json_object\n  and json_schema on models that advertise json_mode or\n  structured_outputs; every model in this catalog advertises one of them\nStructured output + tools together: not declared (false) — no combined\n  probe was run without credentials\nTool calls under streaming: not declared (false) — no page describes\n  streamed tool-call deltas\nThinking: declared (true) — the default model carries the roster's\n  reasoning feature and the protocols page documents normalised reasoning\n  flags (enable_thinking, thinking.type, reasoning_effort: \"none\"); not\n  exercised live\nEmbeddings: false — the protocols page lists /v1/embeddings under\n  \"Not available\"\nBilling: no-free-tier is the conservative schema value, not a\n  verified fact — see Billing below\nKey format: starts with apikey- (docs/llm-protocols)","hierarchy":{"lvl0":"Getting Started","lvl1":"Atlas Cloud Provider Guide","lvl2":"Key Facts","lvl3":""}},
@@ -5457,6 +5468,17 @@
 {"objectID":"ec6300f21745b39bc6ee317430d479d7c88ccf7c58d241764dff42a7e70293dd","title":"Supported Voices","url":"/docs/getting-started/providers/azure-speech#supported-voices","content":"Azure Speech supports 400+ neural voices across 140+ languages. Common voices:\n\n| Voice                | Language     | Style   |\n| -------------------- | ------------ | ------- |\n| en-US-JennyNeural  | English (US) | General |\n| en-US-GuyNeural    | English (US) | General |\n| en-GB-SoniaNeural  | English (UK) | General |\n| de-DE-KatjaNeural  | German       | General |\n| fr-FR-DeniseNeural | French       | General |\n| ja-JP-NanamiNeural | Japanese     | General |","hierarchy":{"lvl0":"Getting Started","lvl1":"Azure Speech Services","lvl2":"Supported Voices","lvl3":""}},
 {"objectID":"43d94a26d7cd992572edaf4c441dcf2112c7ee11aa44e8107e706a07af92b67f","title":"Supported Audio Formats","url":"/docs/getting-started/providers/azure-speech#supported-audio-formats","content":"TTS output: mp3, wav, ogg\nSTT input: wav (16kHz PCM mono recommended), ogg, opus\nAzure's short-audio REST endpoint does not decode MP3 — convert to WAV first or use a different STT provider for MP3 input.","hierarchy":{"lvl0":"Getting Started","lvl1":"Azure Speech Services","lvl2":"Supported Audio Formats","lvl3":""}},
 {"objectID":"da9b065ce67be33eeb3ba05aa627928f7de5427599917c3969f368a829452d86","title":"Limits","url":"/docs/getting-started/providers/azure-speech#limits","content":"TTS: 10,000 characters per request\nSTT: Batch mode (streaming not yet supported)","hierarchy":{"lvl0":"Getting Started","lvl1":"Azure Speech Services","lvl2":"Limits","lvl3":""}},
+{"objectID":"32755ff724ca5a57803a91e09392878685ad08441e3d09b3555b787fd830db1c","title":"Baidu Qianfan Provider Guide","url":"/docs/getting-started/providers/baidu-qianfan","content":"Baidu Qianfan Provider Guide\n\nBaidu Qianfan is a Tier-2 catalog provider: its integration is one JSON\nfile (src/lib/providers/catalog/baidu-qianfan.json) rather than hand-written\ncode. That file is the source of truth for everything on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. An unauthenticated GET https://qianfan.baidubce.com/v2/models\non 2026-09-29 answered HTTP 403, so the model ids come from Baidu's public\ndocs and the roster has not been checked. No account was created and no API\nkey was used to build this entry.\nevidence.liveMatrix is null until someone runs the live capability matrix\nwith a real key (see Verification status below).\n\nKey Facts\nProvider id: baidu-qianfan (aliases qianfan, baidu)\nProtocol: OpenAI-compatible (/chat/completions). The\n  quickstart says\n  \"千帆ModelBuilder提供了与OpenAI兼容的使用方式，用户只需调整apikey、baseurl、model等参数，就可以通过OpenAI SDK调用千帆ModelBuilder推理服务。\"\n  and the Inference API V2 page\n  says the V2 model-service API is \"完全兼容OpenAI标准（包含身份认证、接口协议）\"\nBase URL: https://qianfan.baidubce.com/v2\nDefault model: ernie-5.1\nModels in catalog: 12, taken from the vendor's\n  model-list page\n  (updated 2026-09-16, retrieved 2026-09-29)\nStreaming: supported — the\n  structured-outputs page\n  shows an OpenAI SDK example with stream=True that iterates over the chunks\nTool calling: model-dependent — the\n  function-calling page\n  (updated 2026-07-09) documents an OpenAI-style tools parameter and lists\n  ernie-5.1 and ernie-5.0 in its 支持模型范围 (supported models) section\nTools while streaming: not declared (false) — the function-calling\n  page's request examples send \"stream\": false\nStructured output: true on this entry — the\n  structured-outputs page\n  (updated 2026-05-27) documents the response_format field with text,\n  json_object and json_schema, has a json_schema object description\n  containing \"只有部分模型支持\" (translation: only some models support it), and\n  lists DeepSeek-V4-Pro and GLM-5.1, among others, in its 支持模型范围\n  (supported models) section\nStructured output + tools together: not declared (false) — no combined\n  probe was possible without credentials\nEmbeddings: not declared on this catalog entry (embeddings is false).\n  The model-list page has a 文本向量 (text embedding) section; this flag\n  describes the NeuroLink entry, not the vendor's own API surface\nThinking: not declared (false) — the\n  deep-thinking page\n  documents thinking and enable_thinking request parameters for the models\n  it lists and a reasoning_content output field; this entry declares no\n  thinking capability\nBilling: free-tier — see Billing below\nKey format: none declared (apiKeyFormat is null), so NeuroLink does\n  not validate the key\nScheduled retirements: the\n  model-retirement page\n  (updated 2026-09-24, retrieved 2026-09-29) has rows with 模型退役日期\n  \"2026-10-29\" for ERNIE-5.0, ERNIE-4.5-Turbo-128K, ERNIE-4.5-Turbo-32K,\n  ERNIE-4.5-Turbo-VL-128K and ERNIE-4.5-Turbo-VL-32K\n\nQuick Start\nGet an API key\nVisit: https://console.bce.baidu.com/qianfan/ (an unauthenticated GET on 2026-09-29 answered HTTP 200 with the page title 百度智能云千帆大模型平台; sign-in was not attempted while building this entry)\nCreate an API key: the API KEY page (https://cloud.baidu.com/doc/qianfan/s/wmh8l6tnf, updated 2026-04-14) says to log in to the 百度千帆 platform, click 系统管理 in the left navigation, open API Key, then click 创建 API Key and enter a name; the quickstart (https://cloud.baidu.com/doc/qianfan/s/rmh4stn9m) links 控制台-安全认证-API Key to https://console.bce.baidu.com/iam/#/iam/apikey/list\nAuthentication is HTTP Bearer: the quickstart (https://cloud.baidu.com/doc/qianfan/s/rmh4stn9m) says the Authorization request header must carry the API key with Bearer in front of it; NeuroLink does not validate the key format\nBilling as the vendor states it: the new-user free-quota page (https://cloud.baidu.com/doc/qianfan/s/Imi2rpirg, updated 2025-11-17) says that after you visit the platform and agree to the user agreement the system activates it automatically and issues a new-user free token quota; its table has 17 rows under 服务名称, 赠送Tokens量 and 有效期, and the page says the quota applies to online inference calls of preset model services, not batch inference. The billing page (https://cloud.baidu.com/doc/qianfan/s/wmh4sv6ya, updated 2026-09-24) lists text-generation prices under \"按量后付费\" in 元/千tokens, for example \"ERNIE 5.1\" (版本名称 \"ERNIE-5.1\") with 在线推理 \"0.004\" for 子项 输入（输入<=32k） and \"0.018\" for 子项 输出（输入<=32k）\nSet BAIDU_QIANFAN_API_KEY in your .env file\nConfigure\nUse it\n\nPer-request credentials work as they do for every provider:\n\nBilling\n\nThe new-user free-quota page\n(updated 2025-11-17) says that from 2025-10-24 00:00, after you visit the\nplatform and agree to the user agreement, the system activates Qianfan\nautomatically and issues a new-user free token quota. Its table has 17 rows,\nand the 服务名称 column reads: ERNIE-4.5-Turbo-128K, ERNIE-4.5-Turbo-32K,\nERNIE-4.5-Turbo-VL, ERNIE-X1-Turbo-32K, DeepSeek-R1, DeepSeek-R1-250528,\nDeepSeek-V3-25","hierarchy":{"lvl0":"Getting Started","lvl1":"Baidu Qianfan Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"3e898f39b0a8d2eb2432f857ff4359f6ced3cd7a6ebb7f8274d0d672dd83e6f9","title":"Baidu Qianfan Provider Guide","url":"/docs/getting-started/providers/baidu-qianfan#baidu-qianfan-provider-guide","content":"Baidu Qianfan is a Tier-2 catalog provider: its integration is one JSON\nfile (src/lib/providers/catalog/baidu-qianfan.json) rather than hand-written\ncode. That file is the source of truth for everything on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. An unauthenticated GET https://qianfan.baidubce.com/v2/models\non 2026-09-29 answered HTTP 403, so the model ids come from Baidu's public\ndocs and the roster has not been checked. No account was created and no API\nkey was used to build this entry.\nevidence.liveMatrix is null until someone runs the live capability matrix\nwith a real key (see Verification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"Baidu Qianfan Provider Guide","lvl2":"Baidu Qianfan Provider Guide","lvl3":""}},
+{"objectID":"ce434581d2a842a3d82f9916ee421eb35916112ad29c3c6e9035f2f7c55ca261","title":"Key Facts","url":"/docs/getting-started/providers/baidu-qianfan#key-facts","content":"Provider id: baidu-qianfan (aliases qianfan, baidu)\nProtocol: OpenAI-compatible (/chat/completions). The\n  quickstart says\n  \"千帆ModelBuilder提供了与OpenAI兼容的使用方式，用户只需调整apikey、baseurl、model等参数，就可以通过OpenAI SDK调用千帆ModelBuilder推理服务。\"\n  and the Inference API V2 page\n  says the V2 model-service API is \"完全兼容OpenAI标准（包含身份认证、接口协议）\"\nBase URL: https://qianfan.baidubce.com/v2\nDefault model: ernie-5.1\nModels in catalog: 12, taken from the vendor's\n  model-list page\n  (updated 2026-09-16, retrieved 2026-09-29)\nStreaming: supported — the\n  structured-outputs page\n  shows an OpenAI SDK example with stream=True that iterates over the chunks\nTool calling: model-dependent — the\n  function-calling page\n  (updated 2026-07-09) documents an OpenAI-style tools parameter and lists\n  ernie-5.1 and ernie-5.0 in its 支持模型范围 (supported models) section\nTools while streaming: not declared (false) — the function-calling\n  page's request examples send \"stream\": false\nStructured output: true on this entry — the\n  structured-outputs page\n  (updated 2026-05-27) documents the response_format field with text,\n  json_object and json_schema, has a json_schema object description\n  containing \"只有部分模型支持\" (translation: only some models support it), and\n  lists DeepSeek-V4-Pro and GLM-5.1, among others, in its 支持模型范围\n  (supported models) section\nStructured output + tools together: not declared (false) — no combined\n  probe was possible without credentials\nEmbeddings: not declared on this catalog entry (embeddings is false).\n  The model-list page has a 文本向量 (text embedding) section; this flag\n  describes the NeuroLink entry, not the vendor's own API surface\nThinking: not declared (false) — the\n  deep-thinking page\n  documents thinking and enable_thinking request parameters for the models\n  it lists and a reasoning_content output field; this entry declares no\n  thinking capability\nBilling: free-tier — see Billing below\nKey format: none declared (apiKeyFormat is null), so NeuroLink does\n  not validate the key\nSchedule","hierarchy":{"lvl0":"Getting Started","lvl1":"Baidu Qianfan Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"517850866c80db1ab276996a57fc710b3847b1fdad87d74299649ee5299d1bf8","title":"1. Get an API key","url":"/docs/getting-started/providers/baidu-qianfan#1-get-an-api-key","content":"Visit: https://console.bce.baidu.com/qianfan/ (an unauthenticated GET on 2026-09-29 answered HTTP 200 with the page title 百度智能云千帆大模型平台; sign-in was not attempted while building this entry)\nCreate an API key: the API KEY page (https://cloud.baidu.com/doc/qianfan/s/wmh8l6tnf, updated 2026-04-14) says to log in to the 百度千帆 platform, click 系统管理 in the left navigation, open API Key, then click 创建 API Key and enter a name; the quickstart (https://cloud.baidu.com/doc/qianfan/s/rmh4stn9m) links 控制台-安全认证-API Key to https://console.bce.baidu.com/iam/#/iam/apikey/list\nAuthentication is HTTP Bearer: the quickstart (https://cloud.baidu.com/doc/qianfan/s/rmh4stn9m) says the Authorization request header must carry the API key with Bearer in front of it; NeuroLink does not validate the key format\nBilling as the vendor states it: the new-user free-quota page (https://cloud.baidu.com/doc/qianfan/s/Imi2rpirg, updated 2025-11-17) says that after you visit the platform and agree to the user agreement the system activates it automatically and issues a new-user free token quota; its table has 17 rows under 服务名称, 赠送Tokens量 and 有效期, and the page says the quota applies to online inference calls of preset model services, not batch inference. The billing page (https://cloud.baidu.com/doc/qianfan/s/wmh4sv6ya, updated 2026-09-24) lists text-generation prices under \"按量后付费\" in 元/千tokens, for example \"ERNIE 5.1\" (版本名称 \"ERNIE-5.1\") with 在线推理 \"0.004\" for 子项 输入（输入<=32k） and \"0.018\" for 子项 输出（输入<=32k）\nSet BAIDU_QIANFAN_API_KEY in your .env file","hierarchy":{"lvl0":"Getting Started","lvl1":"Baidu Qianfan Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"811d34461e004acc7b4e3f0b94fe68385527cf908e80a91e632115d78fd149bf","title":"3. Use it","url":"/docs/getting-started/providers/baidu-qianfan#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Baidu Qianfan Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"57f3631c97f446ddfc812d4cd8fe0f8b383aed6bf1cd5475e654238f930b3363","title":"CLI","url":"/docs/getting-started/providers/baidu-qianfan#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider baidu-qianfan\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"baidu-qianfan\",\n  credentials: { baiduQianfan: { apiKey: process.env.BAIDUQIANFANAPI_KEY } },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"Baidu Qianfan Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"34403636b2be7d95e2e955a5cc647f3f8b8b27e51d40be5328683930359ec024","title":"Billing","url":"/docs/getting-started/providers/baidu-qianfan#billing","content":"The new-user free-quota page\n(updated 2025-11-17) says that from 2025-10-24 00:00, after you visit the\nplatform and agree to the user agreement, the system activates Qianfan\nautomatically and issues a new-user free token quota. Its table has 17 rows,\nand the 服务名称 column reads: ERNIE-4.5-Turbo-128K, ERNIE-4.5-Turbo-32K,\nERNIE-4.5-Turbo-VL, ERNIE-X1-Turbo-32K, DeepSeek-R1, DeepSeek-R1-250528,\nDeepSeek-V3-250324, DeepSeek-V3.1-250821, DeepSeek-V3.1-Think-250821,\nKimi-K2-Instruct, Qwen3-235B-A22B-Instruct-2507,\nQwen3-30B-A3B-Instruct-2507, Qwen3-Coder-30B-A3B-Instruct,\nQwen3-Coder-480B-A35B-Instruct, bge-large-en, bge-large-zh and\nqianfan-sug-8k. In rows 1 to 17 the 赠送Tokens量 cell reads \"100万\" and the\n有效期 cell reads \"3个月\". The page says the quota applies to online inference\ncalls of preset model services, not batch inference. The entry records\nfree-tier from that page.\n\nThe model-retirement page\n(updated 2026-09-24, retrieved 2026-09-29) has rows with 退役模型版本\n\"DeepSeek-V3.1-250821\" (模型退役日期 \"2026-06-30\"), \"Kimi-K2-Instruct\"\n(模型退役日期 \"2026-03-26\") and \"ERNIE-4.5-Turbo-128K\" (模型退役日期\n\"2026-10-29\").\n\nThe billing page (updated\n2026-09-24) lists text-generation prices under \"按量后付费\" in 元/千tokens\n(yuan per thousand tokens). For example, its row with 模型名称 \"ERNIE 5.1\" and\n版本名称 \"ERNIE-5.1\" has 在线推理 \"0.004\" for 子项 输入（输入<=32k）, \"0.018\"\nfor 输出（输入<=32k）, \"0.006\" for 输入（32k<输入<=128k） and \"0.022\" for\n输出（32k<输入<=128k）. The catalog entry carries no pricingPerMTok; the\nbilling page states prices in 元/千tokens.","hierarchy":{"lvl0":"Getting Started","lvl1":"Baidu Qianfan Provider Guide","lvl2":"Billing","lvl3":""}},
+{"objectID":"3723ee1692c59419af321583f3907cbbaa45b2fe9dfc1d8a71f0e2f465969ebf","title":"Models","url":"/docs/getting-started/providers/baidu-qianfan#models","content":"| Model                    | Context | Vision | Max output | Notes                                                                                                                                                                                                                                                                                              |\n| ------------------------ | ------- | ------ | ---------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| ernie-5.1 ⭐           | 128k    | no     | 65,536     | NeuroLink default. Listed under the \"ERNIE系列-旗舰模型\" heading; the \"推荐模型\" table cell begins \"ERNIE 5.1是文心系列最新模型\". Listed on the function-calling page.                                                                                                                             |\n| ernie-5.0              | 128k    | yes    | 65,536     | Listed in the vendor's 视觉理解 (vision understanding) ERNIE table and on the function-calling page; described as \"文心5.0是原生全模态大模型\". The model-retirement page has a row with 退役模型版本 \"ERNIE-5.0\" and 模型退役日期 \"2026-10-29\".                                                    |\n| ernie-4.5-turbo-128k   | 128k    | no     | not set    | Listed under the \"ERNIE系列-旗舰模型\" heading and in the \"推荐模型\" table; the page states max output as \"16k\" in one table and \"[2，12288]\" in another, so the entry leaves it unset. The model-retirement page has a row with 退役模型版本 \"ERNIE-4.5-Turbo-128K\" and 模型退役日期 \"2026-10-29\". |\n| ernie-4.5-turbo-32k    | 32k     | no     | 12,288     | Listed under the \"ERNIE系列-旗舰模型\" heading. The model-retirement page has a row with 退役模型版本 \"ERNIE-4.5-Turbo-32K\" and 模型退役日期 \"2026-10-29\".                                                                                                                ","hierarchy":{"lvl0":"Getting Started","lvl1":"Baidu Qianfan Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"73c5535c842de474a975503055f53f725cbd491e6909fd33d6c6e572621634b8","title":"Verification status","url":"/docs/getting-started/providers/baidu-qianfan#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog currently records for Baidu Qianfan — docs-verified only, not\nlive-verified:\n\n| Probe                     | Result                                                                                                                                                                                                                                                                                                                                                                              |\n| ------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                    | unauthenticated GET https://qianfan.baidubce.com/v2/models, HTTP 403, JSON body with code \"AccessDenied\" and message \"Access denied.\", 2026-09-29 — no key used, so the 12 model ids come from the model-list page and the roster has not been checked                                                                                                                            |\n| Auth-failure shape        | unauthenticated GET https://qianfan.baidubce.com/v2/chat/completions, HTTP 401, JSON body with error.code \"invalidiamtoken\", 2026-09-29. The error-code page (updated 2026-04-22) lists 错误码 \"invalidiamtoken\" as HTTP 401 with 错误信息 \"IAM Certification failed\" and rows of 类型 \"ratelimitexceeded\" as HTTP 429 |\n| Model retirements         | public model-retirement page (updated 2026-09-24), read 2026-09-29 — rows with 模型退役日期 \"2026-10-29\" for ERNIE-5.0, ERNIE-4.5-Turbo-128K, ERNIE-4.5-Turbo-32K, ERNIE-4.5-Turbo-VL-128K and ERNIE-4.5-Turbo","hierarchy":{"lvl0":"Getting Started","lvl1":"Baidu Qianfan Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"3d29151dfe00cdf36635c380767d0f0e9ba915ea66f5f71b8c742dbe64712516","title":"Troubleshooting","url":"/docs/getting-started/providers/baidu-qianfan#troubleshooting","content":"| Symptom                                  | Cause                                                                                                                                                           | Fix                                                                                                                            |\n| ---------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ |\n| HTTP 401 with code invalid_iam_token   | The error-code page says the bearer token is invalid or expired, or the request's Authorization header did not add Bearer                                       | The quickstart says to put Bearer in front of the API key in the Authorization header; NeuroLink reads BAIDU_QIANFAN_API_KEY |\n| HTTP 429 with 类型 rate_limit_exceeded | The error-code page lists 错误码 rpm_rate_limit_exceeded (错误信息 \"Rate limit reached for RPM\") and tpm_rate_limit_exceeded (\"Rate limit reached for TPM\") | The same page's 说明 for those rows includes \"适当控制请求频率\" (translation: control the request frequency appropriately)     |","hierarchy":{"lvl0":"Getting Started","lvl1":"Baidu Qianfan Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
+{"objectID":"b73c8158fc0fec24943e26c79d211092c64cc829b5187ff5a0cd63f3c08bc98f","title":"See also","url":"/docs/getting-started/providers/baidu-qianfan#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Baidu Qianfan Provider Guide","lvl2":"See also","lvl3":""}},
 {"objectID":"2635222e23856e968a4b8684e741c55f18fc3655d0bca7b4ffe1034b90cbc7ec","title":"Baseten Provider Guide","url":"/docs/getting-started/providers/baseten","content":"Baseten Provider Guide\n\nBaseten is a Tier-2 catalog provider: OpenAI-wire-compatible with no\nbehavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/baseten.json) rather than hand-written code. That\nfile is the source of truth for everything on this page.\n\nKey Facts\nProvider id: baseten\nProtocol: OpenAI-compatible (/chat/completions)\nBase URL: https://inference.baseten.co/v1\nDefault model: zai-org/GLM-5.3-Flash\nModels in catalog: 16\nStreaming: supported\nTool calling: supported (native)\nStructured output: supported\nEmbeddings: not supported\nBilling: free-tier\n\nQuick Start\nGet an API key\nVisit: https://app.baseten.co/ and sign in or create a workspace\nReview the current Baseten billing and credit terms in the console before making requests\nCreate a personal API key in the Baseten console\nSet BASETEN_API_KEY in your .env file\nConfigure\nUse it\n\nPer-request credentials work as they do for every provider:\n\nModels\n\n| Model                                      | Context | Vision | $/M in · out  | Notes                                                                                              |\n| ------------------------------------------ | ------- | ------ | ------------- | -------------------------------------------------------------------------------------------------- |\n| openai/gpt-oss-120b                      | 125K    | no     | $0.1 / $0.5   | OpenAI GPT-OSS 120B; general-purpose model with controllable reasoning                             |\n| zai-org/GLM-4.7                          | 195K    | no     | $0.6 / $2.2   | GLM 4.7; fast general-purpose model with 200K context and enhanced tool use                        |\n| moonshotai/Kimi-K2.6                     | 256K    | no     | $0.95 / $4    | Kimi K2.6; agentic and coding model for multi-step reasoning and tool use                          |\n| deepseek-ai/DeepSeek-V4-Pro              | 1M      | no     | $1.74 / $3.48 | DeepSeek V4 Pro; 1M-context mixture-of-experts model for agentic workflows and coding              |\n| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | 198K    | no     | $0.6 / $2.4   | NVIDIA Nemotron 3 Ultra; flagship reasoning and non-reasoning model for code and agentic execution |\n| zai-org/GLM-5.2                          | 1M      | no     | $1.4 / $4.4   | GLM 5.2; 1M-context reasoning model                                                                |\n| moonshotai/Kimi-K2.7-Code                | 256K    | no     | $0.95 / $4    | Kimi K2.7 Code; model for complex coding, code reasoning and long-horizon development              |\n| deepseek-ai/DeepSeek-V4-Flash-0731       | 1M      | no     | $0.13 / $0.26 | DeepSeek V4 Flash 0731; fast, low-cost 1M-context mixture-of-experts model                         |\n| thinkingmachines/inkling                 | 1M      | no     | $1 / $4.05    | Thinking Machines Inkling; 1M-context reasoning model                                              |\n| zai-org/GLM-5.2-Fast                     | 1M      | no     | $2.1 / $6.6   | GLM 5.2 Fast; 1M-context model                                                                     |\n| moonshotai/Kimi-K3                       | 1M      | no     | $3 / $15      | Kimi K3; 1M-context model                                                                          |\n| thinkingmachines/inkling-small           | 1M      | no     | $0.5 / $1.2   | Thinking Machines Inkling Small; 1M-context reasoning model                                        |\n| deepseek-ai/DeepSeek-V4-Pro-0813         | 1M      | no     | $1.32 / $3.96 | DeepSeek V4 Pro 0813; dated 1M-context mixture-of-experts model for agentic workflows and coding   |\n| zai-org/GLM-5.3-Flash ⭐                 | 1M      | yes    | $0.15 / $0.5  | GLM 5.3 Flash; 1M-context reasoning model with live-verified image input                           |\n| zai-org/GLM-5.3                          | 1M      | no     | $1.4 / $4.4   | GLM 5.3; 1M-context reasoning model                                                                |\n| zai-org/GLM-5.3-Fast                     | 1M      | yes    | $2.1 / $6.6   | GLM 5.3 Fast; 1M-context reasoning model with image input                                          |\n\nFallback order when the default is unavailable: zai-org/GLM-5.3-Flash → zai-org/GLM-5.3 → zai-org/GLM-5.2.\n\nVerification status\n\nTier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog records for Baseten:\n\n| Probe                 | Result                                             |\n| --------------------- | -------------------------------------------------- |\n| Roster                | authenticated GET /v1/models, HTTP 200, 2026-09-03 |\n| Auth rejection        | HTTP 403, 2026-09-03                               |\n| Live capability sweep | not run                                        |\n\n⚠️ No live capability sweep is recorded for Baseten. The roster and auth\nbehaviour were ver","hierarchy":{"lvl0":"Getting Started","lvl1":"Baseten Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"eb9c3f4209e5426278de1c7deb54c4eb68ae80402a3cb16754e5c220be026366","title":"Baseten Provider Guide","url":"/docs/getting-started/providers/baseten#baseten-provider-guide","content":"Baseten is a Tier-2 catalog provider: OpenAI-wire-compatible with no\nbehavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/baseten.json) rather than hand-written code. That\nfile is the source of truth for everything on this page.","hierarchy":{"lvl0":"Getting Started","lvl1":"Baseten Provider Guide","lvl2":"Baseten Provider Guide","lvl3":""}},
 {"objectID":"d2f16ce28b384cc6e0c5fbda396362387d2b3d22b967b71b869c5fa75f17a59e","title":"Key Facts","url":"/docs/getting-started/providers/baseten#key-facts","content":"Provider id: baseten\nProtocol: OpenAI-compatible (/chat/completions)\nBase URL: https://inference.baseten.co/v1\nDefault model: zai-org/GLM-5.3-Flash\nModels in catalog: 16\nStreaming: supported\nTool calling: supported (native)\nStructured output: supported\nEmbeddings: not supported\nBilling: free-tier","hierarchy":{"lvl0":"Getting Started","lvl1":"Baseten Provider Guide","lvl2":"Key Facts","lvl3":""}},
@@ -5484,6 +5506,27 @@
 {"objectID":"ac2c330a03d89fe314b405926dfc3b54711891d2ed749d13436d24b514f0ec59","title":"Verification status","url":"/docs/getting-started/providers/bee-heossi#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog records for Bee by HEOSSI today — docs- and roster-verified only,\nnot live-verified:\n\n| Probe                 | Result                                                                                                                                                                                                                                                                                                                                                                  |\n| --------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                | unauthenticated GET https://api.bee.heossi.com/bee/models, HTTP 200, 13 models, 2026-09-28. The endpoint's own OpenAPI entry declares security: [] (public).                                                                                                                                                                                                        |\n| Docs cross-check      | Base URL, request/response shapes and reasoning_effort field confirmed against the public OpenAPI 3.1 contract at https://api.bee.heossi.com/openapi.json (retrieved 2026-09-28). Pricing/context per tier confirmed against https://bee.heossi.com/pricing. Tool-calling/JSON-mode/context-mode facts confirmed against https://bee.heossi.com/docs/changelog. |\n| Auth rejection        | Not probed — no authenticated or POST request was made (credential-free onboarding). The OpenAPI contract documents a 401 response (\"Missing or invalid API credential\") with no literal error-body text","hierarchy":{"lvl0":"Getting Started","lvl1":"Bee by HEOSSI Provider Guide","lvl2":"Verification status","lvl3":""}},
 {"objectID":"e9b16c3ebd164557d7f565549295e1636e7273dc26950d6e89db0804d0562362","title":"Troubleshooting","url":"/docs/getting-started/providers/bee-heossi#troubleshooting","content":"| Symptom                                            | Cause                                                                                        | Fix                                                                                             |\n| -------------------------------------------------- | -------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- |\n| Invalid Bee API key                              | BEE_HEOSSI_API_KEY unset or wrong                                                          | Check the key at https://workspace.bee.heossi.com/account/api-keys                              |\n| \"insufficient funded usage credit\" (HTTP 402)      | Prepaid wallet is empty (paid tiers only)                                                    | Top up at https://bee.heossi.com/pricing                                                        |\n| \"model or capability not included\" (HTTP 403)      | The requested tier/feature isn't in your plan                                                | Upgrade at https://bee.heossi.com/pricing, or switch to a tier your plan includes               |\n| Frequent 429s                                      | Allowance or rate limit reached                                                              | Wait and retry; review your plan's usage caps at https://bee.heossi.com/pricing                 |\n| Tool calls / response_format ignored or rejected | bee-cell (the default) is not among the tiers Bee documents tool calling and JSON mode for | Switch to bee-comb, bee-buzz or bee-hive, which the 2026-07-11 changelog names explicitly |","hierarchy":{"lvl0":"Getting Started","lvl1":"Bee by HEOSSI Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
 {"objectID":"7d9904a1f2b283fa9c737a4fffbff9aca22048ae27b9a7d8cd992367f3e0d2fb","title":"See also","url":"/docs/getting-started/providers/bee-heossi#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Bee by HEOSSI Provider Guide","lvl2":"See also","lvl3":""}},
+{"objectID":"8beb03f249df417dc587349be4a775732dc7d6d7c8a320c68f79c9a708f4a3c2","title":"BytePlus ModelArk Provider Guide","url":"/docs/getting-started/providers/byteplus-modelark","content":"BytePlus ModelArk Provider Guide\n\nBytePlus ModelArk is a Tier-2 catalog provider: OpenAI-wire-compatible with no\nbehavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/byteplus-modelark.json) rather than hand-written code.\nThat file is the source of truth for the data on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's GET /models needs a key (an unauthenticated\nGET answers HTTP 401), so the model ids come from the vendor's public\nModel list page and\nthe roster has not been checked. No account was created and no API key was\nused to build this entry. evidence.liveMatrix is null until someone runs\nthe live capability matrix with a real key (see\nVerification status below).\n\nKey Facts\nProvider id: byteplus-modelark (aliases byteplus, modelark)\nProtocol: OpenAI-compatible (/chat/completions) — the vendor's\n  Compatible with OpenAI API\n  page says \"ModelArk model APIs are largely compatible with the OpenAI SDK.\"\nBase URL: https://ark.ap-southeast.bytepluses.com/api/v3. The\n  Region availability\n  page lists a second base URL, https://ark.eu-west.bytepluses.com/api/v3;\n  set BYTEPLUS_MODELARK_BASE_URL to use it. On that page, the section\n  \"Models supported in the EU region\" has the sentence \"The EU region currently\n  supports the following models:\" followed by a one-item list, seed-2-0-lite.\n  Separately, a tip on the Model list page says \"The seed-2-0 and\n  seedream-5-0-lite models are also supported in the eu-west-1 region.\" The\n  Region availability page also says \"Platform-level resources, such as API keys\n  and model activation status, are isolated by region.\"\nDefault model: seed-2-0-pro-260328\nModels in catalog: 12, taken from the Text generation table of the Model\n  list page. That table has 22 rows: 8 are marked Retired and are not in the\n  catalog, and 2 of the other 14 (deepseek-v4-pro-260425 and\n  deepseek-v4-flash-260425) are left out to stay within the 12-model cap\nStreaming: supported — the\n  Chat API page documents\n  a stream parameter that returns content \"according to the SSE protocol\" and\n  ends with a data: [DONE] message\nTool calling: model-dependent — the\n  Function call\n  page documents tools and points to the Model list's Tool use table for the\n  models that support it\nTools while streaming: supported — the Function call page has a Streaming\n  output section whose example passes tools with stream=True\nStructured output: structuredOutput is true for the entry, in beta —\n  the\n  Structured output (beta)\n  page documents response_format with json_schema mode, and says \"This\n  capability is still in the beta phase. Proceed with caution when using it in\n  the production environment.\" The Chat API page says of response_format\n  \"For models that support this parameter, see documentation.\" The Model list's\n  Structured output (beta) section lists these non-retired model ids: dola-seed-2-1-turbo-260628, seed-2-0-lite-260428, seed-2-0-mini-260428, seed-2-0-lite-260228, seed-2-0-mini-260215, deepseek-v4-1-flash-260910, deepseek-v4-pro-ga-260813, deepseek-v4-flash-ga-260731.\n  The NeuroLink default seed-2-0-pro-260328 is not in that section.\nStructured output + tools together: not declared (false) — no combined\n  probe was run without credentials\nEmbeddings: not declared — the Model list has a separate \"Multimodal\n  embedding\" section with its own API, and this entry lists chat models\nThinking: not declared — the\n  Deep reasoning\n  page documents a thinking request field, and this entry sets no\n  thinking-level request parameter\nBilling: free-tier — the vendor's\n  Inference free trial\n  page states a free inference trial quota for new users, see\n  Billing below\nKey format: none declared\n\nQuick Start\nGet an API key\nVisit: https://console.byteplus.com/auth/signup and register as a BytePlus user — the Inference free trial page (https://docs.byteplus.com/en/docs/ModelArk/free-inference-quota) says \"Register and authenticate as a BytePlus user.\"\nActivate the models you want to call on the Model activation page (https://ai.byteplus.com/ark/region:ap-southeast-1/openManagement) — the Quick start (https://docs.byteplus.com/en/docs/ModelArk/quick-start) says \"Go to the Model activation page to activate the models you need to use.\"\nCreate an API key at https://ai.byteplus.com/ark/region:ap-southeast-1/apiKey — the Quick start says to \"create or obtain a ModelArk API key\"; the API key page (https://docs.byteplus.com/en/docs/ModelArk/api-key) says \"API Key is isolated by region. Select the appropriate region before creating and using the API Key for authentication.\"\nFree trial, as the vendor states it: \"ModelArk offers new users a free inference trial quota, allowing them to get started at no cost.\" (https://docs.byteplus.com/en/docs/ModelArk/free-inference-quota); the Free Tokens Only mode page (https://docs.byteplus.com/en/docs/ModelArk/free-tokens-only-mode) says \"In this mode, calls to the inference API consume only the 50","hierarchy":{"lvl0":"Getting Started","lvl1":"BytePlus ModelArk Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"7a3aa829e4557f2a088d9ea807bae645778fd546213ee070b14a596162f0d0bc","title":"BytePlus ModelArk Provider Guide","url":"/docs/getting-started/providers/byteplus-modelark#byteplus-modelark-provider-guide","content":"BytePlus ModelArk is a Tier-2 catalog provider: OpenAI-wire-compatible with no\nbehavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/byteplus-modelark.json) rather than hand-written code.\nThat file is the source of truth for the data on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's GET /models needs a key (an unauthenticated\nGET answers HTTP 401), so the model ids come from the vendor's public\nModel list page and\nthe roster has not been checked. No account was created and no API key was\nused to build this entry. evidence.liveMatrix is null until someone runs\nthe live capability matrix with a real key (see\nVerification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"BytePlus ModelArk Provider Guide","lvl2":"BytePlus ModelArk Provider Guide","lvl3":""}},
+{"objectID":"6998480d78e1b4aab8f4c40d438100017968fad94577fc2e63baf9c6f518969f","title":"Key Facts","url":"/docs/getting-started/providers/byteplus-modelark#key-facts","content":"Provider id: byteplus-modelark (aliases byteplus, modelark)\nProtocol: OpenAI-compatible (/chat/completions) — the vendor's\n  Compatible with OpenAI API\n  page says \"ModelArk model APIs are largely compatible with the OpenAI SDK.\"\nBase URL: https://ark.ap-southeast.bytepluses.com/api/v3. The\n  Region availability\n  page lists a second base URL, https://ark.eu-west.bytepluses.com/api/v3;\n  set BYTEPLUS_MODELARK_BASE_URL to use it. On that page, the section\n  \"Models supported in the EU region\" has the sentence \"The EU region currently\n  supports the following models:\" followed by a one-item list, seed-2-0-lite.\n  Separately, a tip on the Model list page says \"The seed-2-0 and\n  seedream-5-0-lite models are also supported in the eu-west-1 region.\" The\n  Region availability page also says \"Platform-level resources, such as API keys\n  and model activation status, are isolated by region.\"\nDefault model: seed-2-0-pro-260328\nModels in catalog: 12, taken from the Text generation table of the Model\n  list page. That table has 22 rows: 8 are marked Retired and are not in the\n  catalog, and 2 of the other 14 (deepseek-v4-pro-260425 and\n  deepseek-v4-flash-260425) are left out to stay within the 12-model cap\nStreaming: supported — the\n  Chat API page documents\n  a stream parameter that returns content \"according to the SSE protocol\" and\n  ends with a data: [DONE] message\nTool calling: model-dependent — the\n  Function call\n  page documents tools and points to the Model list's Tool use table for the\n  models that support it\nTools while streaming: supported — the Function call page has a Streaming\n  output section whose example passes tools with stream=True\nStructured output: structuredOutput is true for the entry, in beta —\n  the\n  Structured output (beta)\n  page documents response_format with json_schema mode, and says \"This\n  capability is still in the beta phase. Proceed with caution when using it in\n  the production environment.\" The Chat API page says of response_format\n  \"Fo","hierarchy":{"lvl0":"Getting Started","lvl1":"BytePlus ModelArk Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"1d984aa813d36f9084c4073f6734d25aeb5ef372c4bf6b8e969d873d529a18d6","title":"1. Get an API key","url":"/docs/getting-started/providers/byteplus-modelark#1-get-an-api-key","content":"Visit: https://console.byteplus.com/auth/signup and register as a BytePlus user — the Inference free trial page (https://docs.byteplus.com/en/docs/ModelArk/free-inference-quota) says \"Register and authenticate as a BytePlus user.\"\nActivate the models you want to call on the Model activation page (https://ai.byteplus.com/ark/region:ap-southeast-1/openManagement) — the Quick start (https://docs.byteplus.com/en/docs/ModelArk/quick-start) says \"Go to the Model activation page to activate the models you need to use.\"\nCreate an API key at https://ai.byteplus.com/ark/region:ap-southeast-1/apiKey — the Quick start says to \"create or obtain a ModelArk API key\"; the API key page (https://docs.byteplus.com/en/docs/ModelArk/api-key) says \"API Key is isolated by region. Select the appropriate region before creating and using the API Key for authentication.\"\nFree trial, as the vendor states it: \"ModelArk offers new users a free inference trial quota, allowing them to get started at no cost.\" (https://docs.byteplus.com/en/docs/ModelArk/free-inference-quota); the Free Tokens Only mode page (https://docs.byteplus.com/en/docs/ModelArk/free-tokens-only-mode) says \"In this mode, calls to the inference API consume only the 500k free tokens granted by the platform.\"\nSet BYTEPLUS_MODELARK_API_KEY in your .env file (the vendor's examples read ARK_API_KEY, which NeuroLink does not)","hierarchy":{"lvl0":"Getting Started","lvl1":"BytePlus ModelArk Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"7111f3fc16ed11bbfb3a1c35efe6ba2d97087e73c32312b338f84be852c61517","title":"3. Use it","url":"/docs/getting-started/providers/byteplus-modelark#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"BytePlus ModelArk Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"9730988414e95043ff3c63c37f64f8ed6873069c27acc4b7f824415b3b9bb9cd","title":"CLI","url":"/docs/getting-started/providers/byteplus-modelark#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider byteplus-modelark\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"byteplus-modelark\",\n  credentials: {\n    byteplusModelark: { apiKey: process.env.BYTEPLUSMODELARKAPI_KEY },\n  },\n});\n\n\nThe Chat API page describes the model` parameter as the \"ID of the called\nmodel\" and says \"For scenarios with multiple applications and fine-grained\nmanagement, we recommend calling by inference endpoint ID.\"","hierarchy":{"lvl0":"Getting Started","lvl1":"BytePlus ModelArk Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"49b14f48c83ea19d084af6fc51d9111223ed1c8a5aeccf291577617b62e8c0b7","title":"Billing","url":"/docs/getting-started/providers/byteplus-modelark#billing","content":"The vendor's pages state:\nFree trial: \"ModelArk offers new users a free inference trial quota, allowing\n  them to get started at no cost.\"\n  (Inference free trial)\nFree Tokens Only mode: \"In this mode, calls to the inference API consume only\n  the 500k free tokens granted by the platform.\"\n  (Free Tokens Only mode)\nWith Free Tokens Only mode disabled: \"When disabled: Online inference calls\n  first consume the free quota. After the free quota is used up, usage is billed\n  based on actual token consumption.\" (same page)\nPricing: the Pricing\n  page says \"Pay-as-you-go by token.\"\n\nThe entry records free-tier, the schema value closest to the stated free\ninference trial quota.","hierarchy":{"lvl0":"Getting Started","lvl1":"BytePlus ModelArk Provider Guide","lvl2":"Billing","lvl3":""}},
+{"objectID":"3f334766f18b6f01306875aac5f7a8d1dc34d3063f3e845eaa29935b6795e946","title":"Models","url":"/docs/getting-started/providers/byteplus-modelark#models","content":"| Model                          | Context | Vision | $/M in · out (cache hit) | Notes                                                                                                                                                                                                                           |\n| ------------------------------ | ------- | ------ | ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| seed-2-0-pro-260328 ⭐       | 256K    | yes    | $0.50 / $3.00 ($0.10)    | NeuroLink default. The Model list card that links to its detail page is captioned \"Flagship general-purpose agentic model\". Tools are listed as \"Tool Calling\". It is not in the Model list's Structured output (beta) section. |\n| dola-seed-2-1-turbo-260628   | 256K    | yes    | $0.5 / $2.5 ($0.1)       | Fallback. Capabilities include Structured output.                                                                                                                                                                               |\n| seed-2-0-lite-260428         | 256K    | yes    | $0.25 / $2.00 ($0.05)    | Fallback. Structured output is listed as \"Structured output (Recommended: json_schema mode)\".                                                                                                                                 |\n| seed-2-0-mini-260428         | 256K    | yes    | $0.10 / $0.40 ($0.02)    | Fallback. Structured output is listed with \"(Recommended: json_schema mode)\".                                                                                                                                                 |\n| seed-2-0-lite-260228         | 256K    | yes    | $0.25 / $2.00 ($0.05)    | Fallback and models.fallbackModelName. The id in the vendor's OpenAI-compatibility quickstar","hierarchy":{"lvl0":"Getting Started","lvl1":"BytePlus ModelArk Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"ea1a787445eabf8c91645f87b7f86fc36685e7823d467a08403c3a393ef6026b","title":"Verification status","url":"/docs/getting-started/providers/byteplus-modelark#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog currently records for BytePlus ModelArk — docs-verified only, not\nlive-verified:\n\n| Probe                     | Result                                                                                                                                                                                                                           |\n| ------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                    | unauthenticated GET https://ark.ap-southeast.bytepluses.com/api/v3/models answered HTTP 401 on 2026-09-29; model ids are taken from the Model list page and the roster has not been checked                                    |\n| Auth-failure shape        | unauthenticated GET of /models and of /chat/completions each answered HTTP 401 on 2026-09-29 with a JSON body whose error.code is AuthenticationError and error.type is Unauthorized; no POST was sent             |\n| Billing                   | public pages state a free inference trial quota for new users and pay-as-you-go pricing by token, 2026-09-29 — see Billing; no signup was performed                                                                  |\n| Tools / structured output | documented on the Function call and Structured output (beta) pages; neither was exercised live, and no combined tools+schema request was sent — structuredOutputWithTools stays false                                        |\n| Live capability sweep     | not run. evidence.liveMatrix is null. Before treating this provider as production-ready, run npx tsx test/continuous-test-suite-provider-matrix.ts --provider=byteplus-modelark with a real key and record the result. |\n\nDo not treat","hierarchy":{"lvl0":"Getting Started","lvl1":"BytePlus ModelArk Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"211b3128b4fd3b439f0be39ed65be5226eff067a546f0c7b745d82b5c07c4227","title":"Troubleshooting","url":"/docs/getting-started/providers/byteplus-modelark#troubleshooting","content":"The first six rows quote the vendor's\nError codes page (rows\n1 to 4 and 6) or\nFree Tokens Only mode\npage (row 5); the last row describes NeuroLink's own behaviour.\n\n| Symptom                                       | Cause                                                                                                              | Fix                                                                                                                              |\n| --------------------------------------------- | ------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------- |\n| HTTP 401 AuthenticationError                | \"The API key or AK/SK in the request is missing or invalid.\"                                                       | \"Please check the authentication credentials or troubleshoot based on the API document.\"                                         |\n| HTTP 404 ModelNotOpen                       | \"Your account %s has not activated the model %s.\"                                                                  | \"Please activate the model service in the Ark Console.\"                                                                          |\n| HTTP 404 InvalidEndpointOrModel.NotFound    | \"The model or inference endpoint %s does not exist or you do not have access to it.\"                               | —                                                                                                                                |\n| HTTP 429 QuotaExceeded                      | \"The account (%s) has exhausted the free trial quota of the model (%s).\"                                           | \"To continue using the service, go to the ModelArk console and activate the corresponding model service on the Activation page.\" |\n| HTTP 429 SetLimitExceeded                   | \"Your a","hierarchy":{"lvl0":"Getting Started","lvl1":"BytePlus ModelArk Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
+{"objectID":"7005eb55a023e2ac186e3a6ed389bb0008a2f5b7616becf6503b0139c7b811c1","title":"See also","url":"/docs/getting-started/providers/byteplus-modelark#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"BytePlus ModelArk Provider Guide","lvl2":"See also","lvl3":""}},
+{"objectID":"8cfa54818a579986e59b637d8ecc961e2791da6c3ca1c8c10e9731ea5cf6813c","title":"Bytez Provider Guide","url":"/docs/getting-started/providers/bytez","content":"Bytez Provider Guide\n\nBytez is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/bytez.json) rather than hand-written code. That\nfile is the source of truth for this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. Bytez's GET /models needs a key, so the model ids come from\nits public docs and the roster has not been checked. The fields below come\nfrom Bytez's own public documentation and unauthenticated GET requests — no\naccount was created and no API key was used to build it.\nevidence.liveMatrix is null until someone runs the live capability matrix\nwith a real key (see Verification status below).\n\nKey Facts\nProvider id: bytez\nProtocol: OpenAI-compatible (/chat/completions) — the docs' OpenAI-client\n  examples create a client with this base URL and call\n  chat.completions.create\n  (Chat Completions page)\nBase URL: https://api.bytez.com/models/v2/openai/v1\nDefault model: Qwen/Qwen3-4B (NeuroLink default)\nModels in catalog: 2 models named in the Bytez docs\nStreaming: supported — the \"Streaming (Open Source)\" example sets\n  stream: true and reads event.choices[0].delta.content\n  (Chat Completions page)\nRequest fields listed in the API reference: model, messages,\n  max_completion_tokens (default 256), temperature (default 0.7), stream,\n  top_p, presence_penalty, frequency_penalty, logprobs and\n  top_logprobs\n  (API reference).\n  The examples on the Chat Completions page send max_tokens\nTool calling: false — declared in this entry and not exercised\nTools while streaming: false\nStructured output: false — declared in this entry and not exercised\nStructured output + tools together: false — not exercised\nEmbeddings: not declared on this catalog entry (false)\nThinking: not declared (false)\nBilling: free-tier — the Billing & Credits page lists a Free plan,\n  \"$0 / month - Get $1 in free credits\"\n  (Billing & Credits)\n\nQuick Start\nGet an API key\nOpen the API Dashboard at https://bytez.com/api; the Get started page (https://docs.bytez.com/model-api/docs/get-started.md) says \"Copy your key from the API Dashboard\"\nFree plan (https://docs.bytez.com/model-api/docs/billing.md): \"$0 / month - Get $1 in free credits\", with \"Run open models up to 7B parameters\" and \"Credits refresh every 4 weeks\"; the Billing Cycle section lists Billing: None for the Free Plan\nThe same page lists a Pay-as-you-go plan with \"Run open models up to 120B parameters\" and \"Add credits anytime\"\nSet BYTEZ_API_KEY in your .env file\nConfigure\nUse it\n\nPer-request credentials:\n\nModels\n\n| Model              | Context | Vision | Pricing                 | Notes                                                                                                                                                                                            |\n| ------------------ | ------- | ------ | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| Qwen/Qwen3-4B ⭐ | not set | no     | per second of inference | NeuroLink default. The model in the \"Basic usage (Open Source)\" and \"Streaming (Open Source)\" examples of the Chat Completions page and in the Basic usage example of the chat Get started page. |\n| Qwen/Qwen3-1.7B  | not set | no     | not set                 | NeuroLink fallback. Named in the API reference's model field description: \"The ID of the model to run (e.g., Qwen/Qwen3-1.7B, openai/gpt-4)\".                                              |\n\nModel ids are copied from these pages, retrieved 2026-09-29:\nChat Completions page\n  — Qwen/Qwen3-4B\nChat Completions API reference\n  — Qwen/Qwen3-1.7B\n\nOpen models are billed per second of inference (the \"How Credits Work\" table on\nthe Billing & Credits page).\nThat page's \"Pricing by Model Size\" table lists 7B at $0.000072 per second, 15B\nat $0.000108, 35B at $0.000144, 70B at $0.000216 and 120B at $0.00036. The\ncatalog stores no per-token price, because pricingPerMTok is a per-token\nfigure.\n\nmodels.defaultContextWindow (8,192) and models.defaultMaxOutputTokens\n(1,024) are placeholders the vendor does not publish. The per-model context and\noutput figures are left unset.\n\nVision: the catalog sets vision: false for both models. The Chat\nCompletions API reference types message content as string.\n\nFallback: fallbacks lists Qwen/Qwen3-1.7B, which is the runtime fallback\nmodel name the loader derives.\n\nNot in the catalog: closed-source provider models (for example\nopenai/gpt-4) are addressed with a provider prefix, and their curl examples on\nthe Chat Completions page add a provider-key header. The catalog schema has no\nfield for an extra request header, so none are listed.\n\nVerification status\n\nTier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog currently records for Bytez — docs-verified onl","hierarchy":{"lvl0":"Getting Started","lvl1":"Bytez Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"24bc7be0281bcfa27b5d96608fc6a6fd0476ab0f91834ea56821e5e9fed8b74a","title":"Bytez Provider Guide","url":"/docs/getting-started/providers/bytez#bytez-provider-guide","content":"Bytez is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/bytez.json) rather than hand-written code. That\nfile is the source of truth for this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. Bytez's GET /models needs a key, so the model ids come from\nits public docs and the roster has not been checked. The fields below come\nfrom Bytez's own public documentation and unauthenticated GET requests — no\naccount was created and no API key was used to build it.\nevidence.liveMatrix is null until someone runs the live capability matrix\nwith a real key (see Verification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"Bytez Provider Guide","lvl2":"Bytez Provider Guide","lvl3":""}},
+{"objectID":"e5f77451659f05d8a20be8175a297a379b8476dc647c621fd1ce4cce49cfb641","title":"Key Facts","url":"/docs/getting-started/providers/bytez#key-facts","content":"Provider id: bytez\nProtocol: OpenAI-compatible (/chat/completions) — the docs' OpenAI-client\n  examples create a client with this base URL and call\n  chat.completions.create\n  (Chat Completions page)\nBase URL: https://api.bytez.com/models/v2/openai/v1\nDefault model: Qwen/Qwen3-4B (NeuroLink default)\nModels in catalog: 2 models named in the Bytez docs\nStreaming: supported — the \"Streaming (Open Source)\" example sets\n  stream: true and reads event.choices[0].delta.content\n  (Chat Completions page)\nRequest fields listed in the API reference: model, messages,\n  max_completion_tokens (default 256), temperature (default 0.7), stream,\n  top_p, presence_penalty, frequency_penalty, logprobs and\n  top_logprobs\n  (API reference).\n  The examples on the Chat Completions page send max_tokens\nTool calling: false — declared in this entry and not exercised\nTools while streaming: false\nStructured output: false — declared in this entry and not exercised\nStructured output + tools together: false — not exercised\nEmbeddings: not declared on this catalog entry (false)\nThinking: not declared (false)\nBilling: free-tier — the Billing & Credits page lists a Free plan,\n  \"$0 / month - Get $1 in free credits\"\n  (Billing & Credits)","hierarchy":{"lvl0":"Getting Started","lvl1":"Bytez Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"8b2ac51c4b822027c3b61fd52533992570d6a4fae13c25f8cc7ae5bd46305ac5","title":"1. Get an API key","url":"/docs/getting-started/providers/bytez#1-get-an-api-key","content":"Open the API Dashboard at https://bytez.com/api; the Get started page (https://docs.bytez.com/model-api/docs/get-started.md) says \"Copy your key from the API Dashboard\"\nFree plan (https://docs.bytez.com/model-api/docs/billing.md): \"$0 / month - Get $1 in free credits\", with \"Run open models up to 7B parameters\" and \"Credits refresh every 4 weeks\"; the Billing Cycle section lists Billing: None for the Free Plan\nThe same page lists a Pay-as-you-go plan with \"Run open models up to 120B parameters\" and \"Add credits anytime\"\nSet BYTEZ_API_KEY in your .env file","hierarchy":{"lvl0":"Getting Started","lvl1":"Bytez Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"96f4ca797e5281cc70f37b39eb54c9c25a3ea4fda110eda689dd5950ef9b35c8","title":"3. Use it","url":"/docs/getting-started/providers/bytez#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Bytez Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"4e2a7c1e198d9fe0272bc30ed4c5cfdd25b60c68f4e952b3f501d76a5fac14f4","title":"CLI","url":"/docs/getting-started/providers/bytez#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider bytez\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"bytez\",\n  credentials: { bytez: { apiKey: process.env.BYTEZAPIKEY } },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"Bytez Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"9c9f82d24b033b6ad0bdfba648556c7f8d06b9ed461ac6f22fab41bbe22cbcf0","title":"Models","url":"/docs/getting-started/providers/bytez#models","content":"| Model              | Context | Vision | Pricing                 | Notes                                                                                                                                                                                            |\n| ------------------ | ------- | ------ | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| Qwen/Qwen3-4B ⭐ | not set | no     | per second of inference | NeuroLink default. The model in the \"Basic usage (Open Source)\" and \"Streaming (Open Source)\" examples of the Chat Completions page and in the Basic usage example of the chat Get started page. |\n| Qwen/Qwen3-1.7B  | not set | no     | not set                 | NeuroLink fallback. Named in the API reference's model field description: \"The ID of the model to run (e.g., Qwen/Qwen3-1.7B, openai/gpt-4)\".                                              |\n\nModel ids are copied from these pages, retrieved 2026-09-29:\nChat Completions page\n  — Qwen/Qwen3-4B\nChat Completions API reference\n  — Qwen/Qwen3-1.7B\n\nOpen models are billed per second of inference (the \"How Credits Work\" table on\nthe Billing & Credits page).\nThat page's \"Pricing by Model Size\" table lists 7B at $0.000072 per second, 15B\nat $0.000108, 35B at $0.000144, 70B at $0.000216 and 120B at $0.00036. The\ncatalog stores no per-token price, because pricingPerMTok is a per-token\nfigure.\n\nmodels.defaultContextWindow (8,192) and models.defaultMaxOutputTokens\n(1,024) are placeholders the vendor does not publish. The per-model context and\noutput figures are left unset.\n\nVision: the catalog sets vision: false for both models. The Chat\nCompletions API reference types message content as string.\n\nFallback: fallbacks lists Qwen/Qwen3-1.7B, which is the runtime fallback\nmodel name the loader derives.\n\nNot in the catalog: closed-source provider mode","hierarchy":{"lvl0":"Getting Started","lvl1":"Bytez Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"4842424852c197445928c41e9f4b904b82f9453277a4f9bcf57214cb7a39475a","title":"Verification status","url":"/docs/getting-started/providers/bytez#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog currently records for Bytez — docs-verified only, not\nlive-verified:\n\n| Probe                     | Result                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |\n| ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| Roster                    | unauthenticated GET https://api.bytez.com/models/v2/openai/v1/models answered HTTP 401 with the body {\"error\":\"Unauthorized\"}, 2026-09-29 — no key used. The model ids come from the docs pages listed under Models; the roster has not been checked                                                                                                                                                                                                                                          |\n| Auth-failure shape        | unauthenticated GET of both .../v1/models and .../v1/chat/completions answered 401 with {\"error\":\"Unauthorized\"}, 2026-09-29. The Models API reference describes 401 as \"Auth error - check your","hierarchy":{"lvl0":"Getting Started","lvl1":"Bytez Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"a567088a657e2aa1217849cf49afa8bce5515c22858f1cbbc1b9dab6c5712e25","title":"Documented error responses","url":"/docs/getting-started/providers/bytez#documented-error-responses","content":"| Status | What the Bytez docs say                                                                                                                                                                                                                           |\n| ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| 401    | The Models API reference describes 401 as \"Auth error - check your api key and how you're sending it.\" (page)                                                                             |\n| 402    | The Billing & Credits page shows the response for an account whose credits ran out with auto-reload disabled, with the message \"Insufficient credits. Please add credits to continue.\" (page) |\n| 429    | The Models API reference documents 429 as \"Too Many Requests – You have hit the rate limit.\"; the Billing & Credits page says requests over the open model rate limits \"are rejected with a rate-limit error\"                                     |","hierarchy":{"lvl0":"Getting Started","lvl1":"Bytez Provider Guide","lvl2":"Documented error responses","lvl3":""}},
+{"objectID":"69ad11770ecf1fbffa4dcca22d5bb4730636695adc2aea28d419a1be08544d0a","title":"See also","url":"/docs/getting-started/providers/bytez#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Bytez Provider Guide","lvl2":"See also","lvl3":""}},
 {"objectID":"697cf287d3dd79fa2966036c5cd82e65b185366b481b980b8e9a5b1cb086bdb0","title":"Cartesia TTS Provider Guide","url":"/docs/getting-started/providers/cartesia","content":"Cartesia TTS Provider Guide\n\nLow-latency text-to-speech — Cartesia's sonic-2 model over the\nsynchronous /tts/bytes REST endpoint\n\nOverview\n\nCartesia ships two TTS interfaces:\nA WebSocket streaming endpoint used by voice-agent pipelines —\n   exposed by NeuroLink's CartesiaStream adapter in\n   src/lib/adapters/tts/cartesiaHandler.ts (driven by the voice server).\nA synchronous REST endpoint (POST /tts/bytes) that returns the\n   complete audio in a single response — wrapped by NeuroLink's\n   CartesiaTTS handler so it slots into the same\n   generate({ tts: { provider: \"cartesia\" } }) flow as OpenAI /\n   ElevenLabs / Azure / Fish Audio / Google AI TTS.\n\nThis page documents the synchronous handler. For the streaming\nWebSocket path, see the voice-agent docs.\n\nKey Facts\nProtocol: Native REST API (POST /tts/bytes)\nDefault base URL: https://api.cartesia.ai\nDefault API version: 2025-04-16 (sent as Cartesia-Version header)\nDefault model: sonic-2\nDefault voice: 694f9389-aac1-45b6-b726-9d9369183238 (\"Bright Female\", English)\nMax text length: 5000 characters\nOutput formats: mp3 (default, 44.1 kHz), wav (PCM s16le, 44.1 kHz), pcm16 (raw, 24 kHz)\nStreaming: Not via this handler — use CartesiaStream for the WebSocket flow\n\nQuick Start\nGet an API Key\n\nSign up at play.cartesia.ai, open\nManage → API Keys, click Create, give the key a description, and\ncopy the sk_car_… value.\nConfigure Environment\nSynthesize Your First Audio\n\nSDK Usage\n\nBasic Synthesis (Default Voice)\n\nCustom Voice\n\nCopy a voice id from the Voice Library at\nplay.cartesia.ai:\n\nTTS-Augmented LLM Response\n\nWhen useAiResponse: true, NeuroLink first calls the LLM, then\nsynthesizes the LLM output through Cartesia:\n\nWAV / PCM16 Output\n\nLanguage Override\n\nThe handler defaults to English. Pass language via the same options\nbag for other supported languages (see Cartesia docs for the current\nlist):\n\nCLI Usage\n\nConfiguration Reference\n\n| Environment Variable   | Required | Default                                | Description                                                |\n| ---------------------- | -------- | -------------------------------------- | ---------------------------------------------------------- |\n| CARTESIA_API_KEY     | Yes      | —                                      | Cartesia API key (sk_car_…)                              |\n| CARTESIA_VOICE_ID    | No       | 694f9389-aac1-45b6-b726-9d9369183238 | Default voice id used when no voice is passed per-call   |\n| CARTESIA_MODEL       | No       | sonic-2                              | Model id sent as model_id                                |\n| CARTESIA_API_VERSION | No       | 2025-04-16                           | Value of the Cartesia-Version request header             |\n| CARTESIA_BASE_URL    | No       | https://api.cartesia.ai              | Base URL (override for self-hosted / EU regional gateways) |\n\nVoice Models\n\n| Model     | Notes                                               |\n| --------- | --------------------------------------------------- |\n| sonic-2 | Default — current best balance of latency + quality |\n| sonic   | Legacy general-purpose voice model                  |\n\nVoices are identified by UUID strings from the Cartesia voice library.\nBrowse and clone voices in your Cartesia dashboard.\n\nFeature Support Matrix\n\n| Feature                            | Cartesia                                         |\n| ---------------------------------- | ------------------------------------------------ |\n| Text-to-speech                     | Yes (synchronous)                                |\n| Voice cloning                      | Yes (via dashboard upload, then voice id)        |\n| Multilingual                       | Yes (English-first; pass language to override) |\n| MP3 output                         | Yes (44.1 kHz)                                   |\n| WAV output                         | Yes (PCM s16le @ 44.1 kHz)                       |\n| PCM16 output                       | Yes (24 kHz, raw, no RIFF)                       |\n| OPUS output                        | Falls back to MP3                                |\n| Synchronous synthesis              | Yes (this handler)                               |\n| WebSocket streaming                | Separate — CartesiaStream adapter              |\n| getVoices() programmatic listing | Not implemented (use dashboard)                  |\n\nTroubleshooting\n\nCARTESIA_API_KEY not configured\n\nGet / rotate at play.cartesia.ai.\n\nCartesia synthesis failed: 401\n\nThe API key is invalid or revoked. Regenerate from the dashboard and\nupdate your .env.\n\nCartesia synthesis failed: 429\n\nThrottled — usually because the account has insufficient credits or the\nplan's per-minute limit is exhausted. Top up credits or implement\nclient-side backoff. The handler maps 408 / 429 / 5xx to retriable\nerrors so framework-level retry will honor them.\n\nAudio sounds wrong / wrong voice\n\nThe voice field must be a valid Cartesia voice UUID. If it's missing\nor invalid, the handler falls back to the ","hierarchy":{"lvl0":"Getting Started","lvl1":"Cartesia TTS Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"bd1687c65b3f61357e983fd05e2894fb86699b98c859da0561b7280d3ee7b437","title":"Cartesia TTS Provider Guide","url":"/docs/getting-started/providers/cartesia#cartesia-tts-provider-guide","content":"Low-latency text-to-speech — Cartesia's sonic-2 model over the\nsynchronous /tts/bytes REST endpoint","hierarchy":{"lvl0":"Getting Started","lvl1":"Cartesia TTS Provider Guide","lvl2":"Cartesia TTS Provider Guide","lvl3":""}},
 {"objectID":"7a7e062c33471dc864b09d0d8618d6817319c905e2c4a6802368223d5c3ed42b","title":"Overview","url":"/docs/getting-started/providers/cartesia#overview","content":"Cartesia ships two TTS interfaces:\nA WebSocket streaming endpoint used by voice-agent pipelines —\n   exposed by NeuroLink's CartesiaStream adapter in\n   src/lib/adapters/tts/cartesiaHandler.ts (driven by the voice server).\nA synchronous REST endpoint (POST /tts/bytes) that returns the\n   complete audio in a single response — wrapped by NeuroLink's\n   CartesiaTTS handler so it slots into the same\n   generate({ tts: { provider: \"cartesia\" } }) flow as OpenAI /\n   ElevenLabs / Azure / Fish Audio / Google AI TTS.\n\nThis page documents the synchronous handler. For the streaming\nWebSocket path, see the voice-agent docs.","hierarchy":{"lvl0":"Getting Started","lvl1":"Cartesia TTS Provider Guide","lvl2":"Overview","lvl3":""}},
@@ -5592,6 +5635,17 @@
 {"objectID":"158c09ab45f60747833f9d4cfbf34e601f0081439517b76987c99d40b11aae7e","title":"1. Get an API Key","url":"/docs/getting-started/providers/d-id#1-get-an-api-key","content":"https://studio.d-id.com/account-settings","hierarchy":{"lvl0":"Getting Started","lvl1":"D-ID Provider Guide (avatar)","lvl2":"1. Get an API Key","lvl3":""}},
 {"objectID":"26cf72c9afd2aced8f7435a3abbb8cb347f98601c20cba3354ec0e49c6d69c01","title":"Configuration Reference","url":"/docs/getting-started/providers/d-id#configuration-reference","content":"| Environment Variable | Required | Description  |\n| -------------------- | -------- | ------------ |\n| DID_API_KEY        | Yes      | D-ID API key |","hierarchy":{"lvl0":"Getting Started","lvl1":"D-ID Provider Guide (avatar)","lvl2":"Configuration Reference","lvl3":""}},
 {"objectID":"1bc0ff8a3d17cdd2627612b6a8535e3f7e88fb12944830409ef05f9e887698b0","title":"See Also","url":"/docs/getting-started/providers/d-id#see-also","content":"HeyGen Provider\nMuseTalk via Replicate","hierarchy":{"lvl0":"Getting Started","lvl1":"D-ID Provider Guide (avatar)","lvl2":"See Also","lvl3":""}},
+{"objectID":"4bf1933de56a7e3924c2cbec0c9bc7c42356f0cfba6bcbea8224792cc3d935f8","title":"Alibaba Cloud Model Studio (DashScope) Provider Guide","url":"/docs/getting-started/providers/dashscope","content":"Alibaba Cloud Model Studio (DashScope) Provider Guide\n\nAlibaba Cloud Model Studio (DashScope) is a Tier-2 catalog provider:\nOpenAI-wire-compatible with no behavioural quirks, so its entire integration is\none JSON file (src/lib/providers/catalog/dashscope.json) rather than\nhand-written code. That file is the source of truth for everything on this\npage.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's /models endpoint needs a key (an\nunauthenticated GET of it returns HTTP 401), so the model ids come from the\nvendor's public documentation pages and the roster has not been checked\nagainst the API. No account was created and no API key was used to build it.\nevidence.liveMatrix is null until someone runs the live capability matrix\nwith a real key (see Verification status below).\n\nKey Facts\nProvider id: dashscope\nProtocol: OpenAI-compatible (/chat/completions) — the vendor's\n  first API call page\n  says \"Alibaba Cloud Model Studio supports API calls to models through\n  OpenAI-compatible interfaces and the DashScope SDK.\"\nBase URL: https://dashscope-intl.aliyuncs.com/compatible-mode/v1 — the\n  Singapore region, International deployment scope (see Base URL)\nDefault model: qwen3.8-max\nModels in catalog: 8, taken from the vendor's\n  Models page,\n  text-generation page\n  and pricing page\n  (retrieved 2026-09-29)\nStreaming: supported — the vendor's\n  Streaming output page\n  describes Server-Sent Events, enabled by setting stream to true\nTool calling: model-dependent — the Function Calling column on the\n  text-generation page reads Supported for qwen3.8-max, qwen3.8-max-0902,\n  qwen3.8-flash, qwen3.7-plus, qwen3.7-flash, deepseek-v4-pro and\n  deepseek-v4-flash in its Recommended models table, and Unsupported for some\n  models under Legacy models (for example qwen2.5-omni-7b). The\n  OpenAI-compatible Chat page\n  documents the tools parameter\nTools while streaming: supported — the\n  function calling page\n  has a Streaming output section that begins \"Using streaming output lets you\n  obtain the tool function name and input parameter information in real time\"\nStructured output: supported — the\n  structured output page\n  documents response_format in JSON Object and JSON Schema modes. Its JSON\n  Object list includes kimi-k3, deepseek-v4-pro and deepseek-v4-flash;\n  its JSON Schema list reads \"Qwen3.7-Plus series, Qwen3.7-Flash series,\n  Qwen3.7-Max series, Qwen3.8-Max series, and Qwen3.8-Flash series models.\"\nStructured output + tools together: not declared (false) — no combined\n  probe was possible without credentials\nEmbeddings: not declared\nThinking: false on this entry, because NeuroLink's thinkingLevel\n  option has not been exercised against it (no credentials were used). The\n  text-generation page lists Thinking mode as Supported for the ids in its\n  Recommended models table, and the OpenAI-compatible Chat page documents the\n  enable_thinking and reasoning_effort parameters\nBilling: free-tier — the vendor's\n  free quota page\n  says \"the platform automatically grants you a free quota for various models\"\n  on first activation of Model Studio (Singapore region)\nKey format: none declared. The vendor's\n  error-code page\n  says \"Alibaba Cloud Model Studio API Keys start with sk-\", and NeuroLink\n  does not validate it\n\nQuick Start\nGet an API key\nVisit: https://account.alibabacloud.com/register/intl_register.htm and create an Alibaba Cloud account (linked from https://www.alibabacloud.com/help/en/model-studio/first-api-call-to-qwen)\nComplete your account information, then open https://modelstudio.console.alibabacloud.com/ap-southeast-1 and agree to the service agreement to activate Model Studio (Singapore region); https://www.alibabacloud.com/help/en/model-studio/new-free-quota says the system then grants a free quota automatically\nCreate an API key at https://modelstudio.console.alibabacloud.com/ap-southeast-1/settings/api-key with the region set to Singapore; https://www.alibabacloud.com/help/en/model-studio/get-api-key states that each region has its own endpoint, API keys, and model list, and that they cannot be used across regions. Copy the key when it is shown\nFree quota, per https://www.alibabacloud.com/help/en/model-studio/new-free-quota: valid for 90 days, typically 1,000,000 tokens for each model, and \"After the free quota is exhausted, you are automatically billed on a pay-as-you-go basis.\"\nSet DASHSCOPE_API_KEY in your .env file (the vendor's examples use the same variable name)\nConfigure\nUse it\n\nPer-request credentials are passed the same way as for the other catalog providers:\n\nBase URL\n\nThe catalog uses https://dashscope-intl.aliyuncs.com/compatible-mode/v1. The\nvendor's regions page\nlists dashscope-intl.aliyuncs.com as the Singapore DashScope domain, labelled\n\"existing domain\", and says the China (Beijing) and Singapore regions each\nsupport one service deployment scope, Chinese mainland and International\nrespectively. The\nOpenAI-compatible Chat page\nsays \"The existing do","hierarchy":{"lvl0":"Getting Started","lvl1":"Alibaba Cloud Model Studio (DashScope) Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"482241d2cb8c92d59a0637380f75d231e63c061269df3577a3d7713899c8ded3","title":"Alibaba Cloud Model Studio (DashScope) Provider Guide","url":"/docs/getting-started/providers/dashscope#alibaba-cloud-model-studio-dashscope-provider-guide","content":"Alibaba Cloud Model Studio (DashScope) is a Tier-2 catalog provider:\nOpenAI-wire-compatible with no behavioural quirks, so its entire integration is\none JSON file (src/lib/providers/catalog/dashscope.json) rather than\nhand-written code. That file is the source of truth for everything on this\npage.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's /models endpoint needs a key (an\nunauthenticated GET of it returns HTTP 401), so the model ids come from the\nvendor's public documentation pages and the roster has not been checked\nagainst the API. No account was created and no API key was used to build it.\nevidence.liveMatrix is null until someone runs the live capability matrix\nwith a real key (see Verification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"Alibaba Cloud Model Studio (DashScope) Provider Guide","lvl2":"Alibaba Cloud Model Studio (DashScope) Provider Guide","lvl3":""}},
+{"objectID":"6bee8f5fd2d007ba90b56fd143d9505f3e5b00c30541ceb644b416cdfbfac176","title":"Key Facts","url":"/docs/getting-started/providers/dashscope#key-facts","content":"Provider id: dashscope\nProtocol: OpenAI-compatible (/chat/completions) — the vendor's\n  first API call page\n  says \"Alibaba Cloud Model Studio supports API calls to models through\n  OpenAI-compatible interfaces and the DashScope SDK.\"\nBase URL: https://dashscope-intl.aliyuncs.com/compatible-mode/v1 — the\n  Singapore region, International deployment scope (see Base URL)\nDefault model: qwen3.8-max\nModels in catalog: 8, taken from the vendor's\n  Models page,\n  text-generation page\n  and pricing page\n  (retrieved 2026-09-29)\nStreaming: supported — the vendor's\n  Streaming output page\n  describes Server-Sent Events, enabled by setting stream to true\nTool calling: model-dependent — the Function Calling column on the\n  text-generation page reads Supported for qwen3.8-max, qwen3.8-max-0902,\n  qwen3.8-flash, qwen3.7-plus, qwen3.7-flash, deepseek-v4-pro and\n  deepseek-v4-flash in its Recommended models table, and Unsupported for some\n  models under Legacy models (for example qwen2.5-omni-7b). The\n  OpenAI-compatible Chat page\n  documents the tools parameter\nTools while streaming: supported — the\n  function calling page\n  has a Streaming output section that begins \"Using streaming output lets you\n  obtain the tool function name and input parameter information in real time\"\nStructured output: supported — the\n  structured output page\n  documents response_format in JSON Object and JSON Schema modes. Its JSON\n  Object list includes kimi-k3, deepseek-v4-pro and deepseek-v4-flash;\n  its JSON Schema list reads \"Qwen3.7-Plus series, Qwen3.7-Flash series,\n  Qwen3.7-Max series, Qwen3.8-Max series, and Qwen3.8-Flash series models.\"\nStructured output + tools together: not declared (false) — no combined\n  probe was possible without credentials\nEmbeddings: not declared\nThinking: false on this entry, because NeuroLink's thinkingLevel\n  option has not been exercised against it (no credentials were used). The\n  text-generation page lists Thinking mode as Supported for the ids in its\n  Recommen","hierarchy":{"lvl0":"Getting Started","lvl1":"Alibaba Cloud Model Studio (DashScope) Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"d39ed1ef1f5c541b14b5a2e4bb573b6535813bf77c60a948bf53c4b48421e96c","title":"1. Get an API key","url":"/docs/getting-started/providers/dashscope#1-get-an-api-key","content":"Visit: https://account.alibabacloud.com/register/intl_register.htm and create an Alibaba Cloud account (linked from https://www.alibabacloud.com/help/en/model-studio/first-api-call-to-qwen)\nComplete your account information, then open https://modelstudio.console.alibabacloud.com/ap-southeast-1 and agree to the service agreement to activate Model Studio (Singapore region); https://www.alibabacloud.com/help/en/model-studio/new-free-quota says the system then grants a free quota automatically\nCreate an API key at https://modelstudio.console.alibabacloud.com/ap-southeast-1/settings/api-key with the region set to Singapore; https://www.alibabacloud.com/help/en/model-studio/get-api-key states that each region has its own endpoint, API keys, and model list, and that they cannot be used across regions. Copy the key when it is shown\nFree quota, per https://www.alibabacloud.com/help/en/model-studio/new-free-quota: valid for 90 days, typically 1,000,000 tokens for each model, and \"After the free quota is exhausted, you are automatically billed on a pay-as-you-go basis.\"\nSet DASHSCOPE_API_KEY in your .env file (the vendor's examples use the same variable name)","hierarchy":{"lvl0":"Getting Started","lvl1":"Alibaba Cloud Model Studio (DashScope) Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"032f3f827eaad4fa602142addaee7336fd906c19bef2d4212eb1d8345f076c15","title":"3. Use it","url":"/docs/getting-started/providers/dashscope#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Alibaba Cloud Model Studio (DashScope) Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"8772f256e59f69594bfa7c3d3f4e24e19b712cbb2646b9d04008868b7a1833f3","title":"CLI","url":"/docs/getting-started/providers/dashscope#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider dashscope\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"dashscope\",\n  credentials: { dashscope: { apiKey: process.env.DASHSCOPEAPIKEY } },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"Alibaba Cloud Model Studio (DashScope) Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"4d3ec8b035c5aab1c8bf8263e769d84773f64dff75cf094fbeea9afefdafc888","title":"Base URL","url":"/docs/getting-started/providers/dashscope#base-url","content":"The catalog uses https://dashscope-intl.aliyuncs.com/compatible-mode/v1. The\nvendor's regions page\nlists dashscope-intl.aliyuncs.com as the Singapore DashScope domain, labelled\n\"existing domain\", and says the China (Beijing) and Singapore regions each\nsupport one service deployment scope, Chinese mainland and International\nrespectively. The\nOpenAI-compatible Chat page\nsays \"The existing domain remains fully functional.\"\n\nThe regions page also documents a workspace-dedicated domain,\nhttps://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1,\nlabelled \"(recommended)\" in its endpoint comparison. To use it, set\nDASHSCOPE_BASE_URL to that URL with your workspace id. The same page states:\n\"The DashScope domain (dashscope.aliyuncs.com) will no longer support new\nfeatures after September 30, 2026.\"","hierarchy":{"lvl0":"Getting Started","lvl1":"Alibaba Cloud Model Studio (DashScope) Provider Guide","lvl2":"Base URL","lvl3":""}},
+{"objectID":"3807695c9f2813a8f67a551bddf289d5980d5dbea2a42fbb6079c24e0b05ee3c","title":"Models","url":"/docs/getting-started/providers/dashscope#models","content":"| Model               | Context | Vision           | $/M in · out  | Notes                                                                                                                                                                                                                                      |\n| ------------------- | ------- | ---------------- | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| qwen3.8-max ⭐    | 1M      | yes              | $2 / $6       | NeuroLink default. The model in the vendor's OpenAI-compatible examples; the text-generation page says \"For the strongest reasoning, choose qwen3.8-max.\" Thinking mode, Function Calling, Built-in tools and Structured output Supported. |\n| qwen3.8-flash     | 1M      | yes              | $0.15 / $0.47 | Fallback. Thinking mode, Function Calling, Built-in tools and Structured output Supported.                                                                                                                                                 |\n| qwen3.7-plus      | 1M      | yes              | —             | Fallback. The text-generation page says \"We recommend qwen3.7-plus for balanced performance and cost, with full tool calling and a 1M-token context window for large codebases.\"                                                           |\n| qwen3.8-max-0902  | 1M      | yes              | $2 / $6       | Fallback. Thinking mode, Function Calling, Built-in tools and Structured output Supported.                                                                                                                                                 |\n| qwen3.7-flash     | 1M      | yes              | —             | Fallback. Thinking mode, Function Calling, Built-in tools and Structured output Supported.                ","hierarchy":{"lvl0":"Getting Started","lvl1":"Alibaba Cloud Model Studio (DashScope) Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"78c324b99cf27436784db89a263aec3110ca7db427f752870d96ecd3c479ae84","title":"Verification status","url":"/docs/getting-started/providers/dashscope#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the catalog\ncurrently records for Alibaba Cloud Model Studio (DashScope) —\ndocs-verified only, not live-verified:\n\n| Probe                     | Result                                                                                                                                                                                                                                                                                                                                                           |\n| ------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                    | unauthenticated GET /compatible-mode/v1/models, HTTP 401 without a key, 2026-09-29. Model ids are taken from the vendor's text-generation and Models pages (retrieved 2026-09-29); the roster is not verified                                                                                                                                                  |\n| Auth-failure shape        | the same GET returned a JSON body with error.message \"You didn't provide an API key. You need to provide your API key in an Authorization header using Bearer auth (i.e. Authorization: Bearer YOURKEY).\", error.type \"invalidrequest_error\", error.param null, error.code null and a top-level request_id; errorRules carries a status 401 rule |\n| Endpoint check            | an unauthenticated GET of /compatible-mode/v1/chat/completions answered HTTP 400 with code \"InvalidParameter\" and message \"Request method 'GET' is not supported.\"; that message is also listed on th","hierarchy":{"lvl0":"Getting Started","lvl1":"Alibaba Cloud Model Studio (DashScope) Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"a2c7aa04c54b187cd6b44bece5430acb5c311feca6195d44bcdf6c0749444354","title":"Troubleshooting","url":"/docs/getting-started/providers/dashscope#troubleshooting","content":"The rows below restate what the vendor's\nerror-code page\ngives for the named error.\n\n| Symptom                                 | Cause the vendor lists                                                                                    | Fix the vendor lists                                                                             |\n| --------------------------------------- | --------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------ |\n| HTTP 401 invalid_api_key              | Among the causes: the API key and the base URL belong to different regions                                | Use an API key from the Singapore region page together with the Singapore base URL               |\n| HTTP 403 AllocationQuota.FreeTierOnly | \"Cause 2\": the free quota exhaustion stop was enabled and requests were made after the free quota ran out | Disable the free quota exhaustion stop switch to continue on a paid basis                        |\n| HTTP 400 Arrearage                    | The Alibaba Cloud account associated with the API key has an overdue payment                              | Check Expenses and Costs on the vendor's billing console and recharge                            |\n| HTTP 404 model_not_found              | The model does not exist, or Model Studio has not been activated                                          | Compare the model value with the Models page; activate model services in the Model Marketplace |\n| HTTP 429 Throttling                   | API calls triggered rate limiting                                                                         | \"Reduce call frequency or retry later.\"                                                          |","hierarchy":{"lvl0":"Getting Started","lvl1":"Alibaba Cloud Model Studio (DashScope) Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
+{"objectID":"7f7161d64efdcc9bf9835b94d1ff319fbeddc6e3868d6df2b5ae50bb9943dd32","title":"See also","url":"/docs/getting-started/providers/dashscope#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Alibaba Cloud Model Studio (DashScope) Provider Guide","lvl2":"See also","lvl3":""}},
 {"objectID":"b2be5208100a44ce994ffae3b90fca7b5cf973105450c48eb805966668653ee4","title":"Deepgram Provider Guide","url":"/docs/getting-started/providers/deepgram","content":"Deepgram Provider Guide\n\nFast, accurate speech-to-text with streaming, speaker diarization, and smart formatting\n\nSTT-only in NeuroLink — Deepgram is registered as the STT provider id\ndeepgram. Deepgram's TTS product is not wired in NeuroLink today; for\nTTS use openai-tts, elevenlabs, azure-tts, or google-ai.\n\nOverview\n\nDeepgram is a speech recognition provider optimised for speed and accuracy in production environments. NeuroLink wraps Deepgram's Listen API, giving you access to the Nova-2 and Nova-3 model families through the standard generate() call. Deepgram's strengths include real-time streaming transcription over WebSocket, speaker diarization for multi-speaker audio, and smart formatting that cleans up dates, currency, and numbers automatically.\n\nKey Facts\n\n| Property               | Value                                         |\n| ---------------------- | --------------------------------------------- |\n| Provider ID        | deepgram                                    |\n| API endpoint       | https://api.deepgram.com/v1/listen          |\n| Streaming endpoint | wss://api.deepgram.com/v1/listen            |\n| Default model      | nova-2                                      |\n| Formats            | mp3, wav, ogg, opus                           |\n| Max audio          | 2 hours (7,200 seconds) per request           |\n| Languages          | 40+ languages and dialects                    |\n| Streaming          | Yes (WebSocket-based real-time transcription) |\n\nQuick Start\nGet an API Key\n\nSign up at https://console.deepgram.com and create an API key under Settings → API Keys.\nConfigure Environment\n\nAdd to your .env file:\nInstall NeuroLink\nTranscribe Your First Audio File\n\nSupported Models\n\n| Model ID           | Description                                        | Best For                                |\n| ------------------ | -------------------------------------------------- | --------------------------------------- |\n| nova-2 (default) | Fastest, lowest Word Error Rate in the Nova family | General transcription, production use   |\n| nova-2-general   | General-purpose variant, same as nova-2          | Broad use cases                         |\n| nova-2-meeting   | Optimised for multi-speaker meeting audio          | Video conferences, recordings           |\n| nova-2-phonecall | Tuned for telephone audio quality                  | Call centre, PSTN audio                 |\n| nova-2-voicemail | Handles background noise and compressed audio      | Voicemail transcription                 |\n| nova-2-finance   | Finance-domain vocabulary boost                    | Earnings calls, financial content       |\n| nova-2-medical   | Medical terminology                                | Clinical notes, consultations           |\n| nova-3           | Next-generation model with improved accuracy       | Demanding accuracy requirements         |\n| nova             | Previous generation Nova                           | Legacy compatibility                    |\n| enhanced         | High accuracy, slower processing                   | Archival, quality-critical paths        |\n| base             | Fastest, lower accuracy                            | Draft transcriptions, cost optimisation |\n\nSDK Usage\n\nBasic Transcription\n\nChoosing a Model\n\nSmart Formatting\n\nSmart formatting cleans up numbers, currency, dates, and other structured data automatically:\n\nSpeaker Diarization\n\nIdentify who spoke when in multi-speaker audio:\n\nUtterance Segmentation\n\nSplit audio into utterance-level segments with speaker and timing information:\n\nWord-Level Timestamps\n\nCustom Vocabulary / Keyword Boosting\n\nImprove recognition of domain-specific terms:\n\nContent Redaction\n\nAutomatically redact sensitive data from transcripts:\n\nReal-Time Streaming Transcription\n\nUse the DeepgramSTT handler directly for WebSocket-based streaming:\n\nPer-Call Credential Override\n\nCLI Usage\n\nBasic Transcription\n\nLanguage Selection\n\nSmart Formatting\n\nSpeaker Diarization\n\nSupported Languages\n\nDeepgram supports 40+ languages and regional dialects. Key languages available with diarization and punctuation:\n\n| Code    | Language     |\n| ------- | ------------ |\n| en    | English      |\n| en-US | English (US) |\n| en-GB | English (UK) |\n| es    | Spanish      |\n| fr    | French       |\n| de    | German       |\n| it    | Italian      |\n| pt    | Portuguese   |\n| nl    | Dutch        |\n| ja    | Japanese     |\n| ko    | Korean       |\n| zh    | Chinese      |\n| hi    | Hindi        |\n| ru    | Russian      |\n\nFor the full language list, see the Deepgram language support docs.\n\nConfiguration Reference\n\n| Environment Variable | Required | Default  | Description                    |\n| -------------------- | -------- | -------- | ------------------------------ |\n| DEEPGRAM_API_KEY   | Yes      | —        | Deepgram API key               |\n| DEEPGRAM_MODEL     | No       | nova-2 | Default transcription model    |\n| DEEPGRAM_LANGUAGE  | No       | en-US  | Default transcription language |\n\n","hierarchy":{"lvl0":"Getting Started","lvl1":"Deepgram Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"9414c09c7bc0f32459b7a04e9bd555547a8afd95d34f1fa34b8137b91811f331","title":"Deepgram Provider Guide","url":"/docs/getting-started/providers/deepgram#deepgram-provider-guide","content":"Fast, accurate speech-to-text with streaming, speaker diarization, and smart formatting\n\nSTT-only in NeuroLink — Deepgram is registered as the STT provider id\ndeepgram. Deepgram's TTS product is not wired in NeuroLink today; for\nTTS use openai-tts, elevenlabs, azure-tts, or google-ai.","hierarchy":{"lvl0":"Getting Started","lvl1":"Deepgram Provider Guide","lvl2":"Deepgram Provider Guide","lvl3":""}},
 {"objectID":"b8bd9feff15fd2afb977777316501e9d4ab8e1b5cf643149f2d5cd997cb82133","title":"Overview","url":"/docs/getting-started/providers/deepgram#overview","content":"Deepgram is a speech recognition provider optimised for speed and accuracy in production environments. NeuroLink wraps Deepgram's Listen API, giving you access to the Nova-2 and Nova-3 model families through the standard generate() call. Deepgram's strengths include real-time streaming transcription over WebSocket, speaker diarization for multi-speaker audio, and smart formatting that cleans up dates, currency, and numbers automatically.","hierarchy":{"lvl0":"Getting Started","lvl1":"Deepgram Provider Guide","lvl2":"Overview","lvl3":""}},
@@ -5910,6 +5964,16 @@
 {"objectID":"b3f87826edf93960447e8c3d676ef35294ba56e2fc43f054dfdcb727c8eb799c","title":"Complex Schema Limitations","url":"/docs/getting-started/providers/google-vertex#complex-schema-limitations","content":"\"Too many states for serving\" Error:\n\nWhen using complex Zod schemas with Gemini, you may encounter:\n\nSolutions:\nSimplify schema (reduce nesting, array sizes)\nUse disableTools: true (reduces state count)\nUse Claude models via Vertex AI (no such limitation)\n\nSee Troubleshooting Guide for details.","hierarchy":{"lvl0":"Getting Started","lvl1":"Google Vertex AI Provider Guide","lvl2":"Complex Schema Limitations","lvl3":""}},
 {"objectID":"cdf86b6578427294fa2254117c7e61f42e79da95d8d6d7a708ca89c547d02c6a","title":"Related Documentation","url":"/docs/getting-started/providers/google-vertex#related-documentation","content":"Provider Setup Guide - General configuration\nMulti-Region Deployment - Geographic distribution\nCost Optimization - Reduce costs\nCompliance Guide - Security","hierarchy":{"lvl0":"Getting Started","lvl1":"Google Vertex AI Provider Guide","lvl2":"Related Documentation","lvl3":""}},
 {"objectID":"04e23b984e4f8365322c89cde63196ae29e5afa6708e60280916d36ac0d6565a","title":"Additional Resources","url":"/docs/getting-started/providers/google-vertex#additional-resources","content":"Vertex AI Documentation - Official docs\nVertex AI Pricing - Pricing calculator\nGCP Console - Manage resources\ngcloud CLI - Command-line tool\n\nNeed Help? Join our GitHub Discussions or open an issue.","hierarchy":{"lvl0":"Getting Started","lvl1":"Google Vertex AI Provider Guide","lvl2":"Additional Resources","lvl3":""}},
+{"objectID":"6a4548b9a4d5646f80e67552719d6c78baae2ba87742fc70303b6b75fa2fcc71","title":"GradientAI Provider Guide","url":"/docs/getting-started/providers/gradientai","content":"GradientAI Provider Guide\n\nGradientAI (DigitalOcean) is a Tier-2 catalog provider: OpenAI-wire-compatible with no\nbehavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/gradientai.json) rather than hand-written code.\nThat file is the source of truth for everything on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's GET /v1/models needs a key (an unauthenticated\nGET answers HTTP 401), so the model ids come from DigitalOcean's public docs and\nthe roster has not been checked. No account was created and no API key was used\nto build it. evidence.liveMatrix is null until someone runs the live\ncapability matrix with a real key (see\nVerification status below).\n\nDigitalOcean's docs now brand the product \"Inference\"; the API reference\ndescribes the serverless API as part of \"DigitalOcean Gradient™ AI Agentic\nCloud\".\n\nKey Facts\nProvider id: gradientai\nProtocol: OpenAI-compatible (/chat/completions)\nBase URL: https://inference.do-ai.run/v1\nDefault model: llama-4-maverick\nModels in catalog: 12, copied from the\n  models page\n  (retrieved 2026-09-29), which states \"DigitalOcean Inference supports more than\n  70 foundation, embeddings, and reranking models\"\nStreaming: supported — the\n  Serverless Inference API reference\n  documents stream: \"If set to true, the model response data will be streamed\n  to the client as it is generated using server-sent events.\"\nTool calling: model-dependent — the API reference documents tools and\n  tool_choice request parameters for chat completions, and the models page\n  carries a \"Tool calling\" usage note on individual models (for example\n  glm-5.2, glm-5.3-flash and mimo-v2.5-pro in this catalog)\nTools while streaming: not declared (false) — the API reference\n  documents stream and tools as separate request parameters\nStructured output: not declared (false) — the models page carries a\n  \"Structured outputs\" usage note on the glm-5.2, glm-5.3-flash and\n  mimo-v2.5-pro rows\nStructured output + tools together: not declared (false) — no combined\n  probe was possible without credentials\nEmbeddings: not declared (false) — the\n  endpoint list\n  documents POST /v1/embeddings; the flag records that NeuroLink's generic\n  catalog provider class does not implement embed() / embedMany(), not what\n  the vendor's API offers\nThinking: not declared (false) — the\n  Use Reasoning page\n  describes a reasoning_effort request parameter for models that support\n  reasoning, and the flag here is provider-wide\nBilling: no-free-tier — the schema's closest member to the vendor's\n  statement \"You must maintain a positive prepaid account balance to send\n  serverless inference requests\" (pricing page)\nKey format: none declared (apiKeyFormat: null)\n\nQuick Start\nGet an API key\nVisit: https://cloud.digitalocean.com/model-studio/manage-keys (the Control Panel page that https://docs.digitalocean.com/products/inference/how-to/manage-model-access-keys/ names for creating and managing model access keys; it shows the DigitalOcean login when signed out) and sign in to a DigitalOcean account\nClick Create model access key, enter a name, and copy the secret key when it is shown: the docs state \"Copy and store it securely before closing the window.\"\nPrepaid balance: the docs state \"Serverless Inference requires a positive prepaid account balance before you can send inference requests.\" (https://docs.digitalocean.com/products/inference/how-to/manage-serverless-inference-prepayment/)\nSet GRADIENTAI_API_KEY in your .env file\nConfigure\nUse it\n\nPer-request credentials use the standard NeuroLink pattern:\n\nModels\n\n| Model                    | Context   | Max output    | Vision | $/M in · out (cache read) | Notes                                                                                                                                                                 |\n| ------------------------ | --------- | ------------- | ------ | ------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| llama-4-maverick ⭐    | 128,000   | 16,384        | —      | $0.25 / $0.87             | NeuroLink default. Models page row \"Llama 4 Maverick 17B 128E Instruct\"; the Chat Completions page uses model=\"llama-4-maverick\" in its Python OpenAI SDK example.  |\n| deepseek-v4.1-flash    | 1,048,576 | 1,048,576     | yes    | $0.30 / $1.20 ($0.006)    | NeuroLink fallback and models.visionModel. Usage notes \"Prompt caching\", \"Native vision (text and images)\".                                                         |\n| deepseek-v4-pro-0813   | 1,048,576 | 1,048,576     | —      | $1.32 / $3.96 ($0.044)    | Usage notes \"Input context window of up to 1M tokens\", \"Prompt caching\".                                                                                              |\n| deepseek-v4-flash-0731 | 1,048,576 | 1,048,576     | —      | $0.","hierarchy":{"lvl0":"Getting Started","lvl1":"GradientAI Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"640b2572f5f8aefad5df64c6d04a664dd60f20b41b0f08f069989480f2267688","title":"GradientAI Provider Guide","url":"/docs/getting-started/providers/gradientai#gradientai-provider-guide","content":"GradientAI (DigitalOcean) is a Tier-2 catalog provider: OpenAI-wire-compatible with no\nbehavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/gradientai.json) rather than hand-written code.\nThat file is the source of truth for everything on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's GET /v1/models needs a key (an unauthenticated\nGET answers HTTP 401), so the model ids come from DigitalOcean's public docs and\nthe roster has not been checked. No account was created and no API key was used\nto build it. evidence.liveMatrix is null until someone runs the live\ncapability matrix with a real key (see\nVerification status below).\n\nDigitalOcean's docs now brand the product \"Inference\"; the API reference\ndescribes the serverless API as part of \"DigitalOcean Gradient™ AI Agentic\nCloud\".","hierarchy":{"lvl0":"Getting Started","lvl1":"GradientAI Provider Guide","lvl2":"GradientAI Provider Guide","lvl3":""}},
+{"objectID":"ce3fc362e9bd33bb3abab59e43516d8f22ff3d6c1d1a26292f5157cddfc40168","title":"Key Facts","url":"/docs/getting-started/providers/gradientai#key-facts","content":"Provider id: gradientai\nProtocol: OpenAI-compatible (/chat/completions)\nBase URL: https://inference.do-ai.run/v1\nDefault model: llama-4-maverick\nModels in catalog: 12, copied from the\n  models page\n  (retrieved 2026-09-29), which states \"DigitalOcean Inference supports more than\n  70 foundation, embeddings, and reranking models\"\nStreaming: supported — the\n  Serverless Inference API reference\n  documents stream: \"If set to true, the model response data will be streamed\n  to the client as it is generated using server-sent events.\"\nTool calling: model-dependent — the API reference documents tools and\n  tool_choice request parameters for chat completions, and the models page\n  carries a \"Tool calling\" usage note on individual models (for example\n  glm-5.2, glm-5.3-flash and mimo-v2.5-pro in this catalog)\nTools while streaming: not declared (false) — the API reference\n  documents stream and tools as separate request parameters\nStructured output: not declared (false) — the models page carries a\n  \"Structured outputs\" usage note on the glm-5.2, glm-5.3-flash and\n  mimo-v2.5-pro rows\nStructured output + tools together: not declared (false) — no combined\n  probe was possible without credentials\nEmbeddings: not declared (false) — the\n  endpoint list\n  documents POST /v1/embeddings; the flag records that NeuroLink's generic\n  catalog provider class does not implement embed() / embedMany(), not what\n  the vendor's API offers\nThinking: not declared (false) — the\n  Use Reasoning page\n  describes a reasoning_effort request parameter for models that support\n  reasoning, and the flag here is provider-wide\nBilling: no-free-tier — the schema's closest member to the vendor's\n  statement \"You must maintain a positive prepaid account balance to send\n  serverless inference requests\" (pricing page)\nKey format: none declared (apiKeyFormat: null)","hierarchy":{"lvl0":"Getting Started","lvl1":"GradientAI Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"848b3a9f53166b88c5790fc75b1524f1ca5c6ea3f9a31e639d692c040ef9fd94","title":"1. Get an API key","url":"/docs/getting-started/providers/gradientai#1-get-an-api-key","content":"Visit: https://cloud.digitalocean.com/model-studio/manage-keys (the Control Panel page that https://docs.digitalocean.com/products/inference/how-to/manage-model-access-keys/ names for creating and managing model access keys; it shows the DigitalOcean login when signed out) and sign in to a DigitalOcean account\nClick Create model access key, enter a name, and copy the secret key when it is shown: the docs state \"Copy and store it securely before closing the window.\"\nPrepaid balance: the docs state \"Serverless Inference requires a positive prepaid account balance before you can send inference requests.\" (https://docs.digitalocean.com/products/inference/how-to/manage-serverless-inference-prepayment/)\nSet GRADIENTAI_API_KEY in your .env file","hierarchy":{"lvl0":"Getting Started","lvl1":"GradientAI Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"08555d830754bbbb26783930d9d1ac0f2021c9c3fa6acc93167e57d70ae76260","title":"3. Use it","url":"/docs/getting-started/providers/gradientai#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"GradientAI Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"a9c3a6802840fd80525c7594bb861c17a9977f3ce90a787ceb608199ae6d0988","title":"CLI","url":"/docs/getting-started/providers/gradientai#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider gradientai\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"gradientai\",\n  credentials: { gradientai: { apiKey: process.env.GRADIENTAIAPIKEY } },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"GradientAI Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"e309d3a40299e7f8bf0867459916f1c7e70c35f83aa8560cca30dd1b6569aa39","title":"Models","url":"/docs/getting-started/providers/gradientai#models","content":"| Model                    | Context   | Max output    | Vision | $/M in · out (cache read) | Notes                                                                                                                                                                 |\n| ------------------------ | --------- | ------------- | ------ | ------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| llama-4-maverick ⭐    | 128,000   | 16,384        | —      | $0.25 / $0.87             | NeuroLink default. Models page row \"Llama 4 Maverick 17B 128E Instruct\"; the Chat Completions page uses model=\"llama-4-maverick\" in its Python OpenAI SDK example.  |\n| deepseek-v4.1-flash    | 1,048,576 | 1,048,576     | yes    | $0.30 / $1.20 ($0.006)    | NeuroLink fallback and models.visionModel. Usage notes \"Prompt caching\", \"Native vision (text and images)\".                                                         |\n| deepseek-v4-pro-0813   | 1,048,576 | 1,048,576     | —      | $1.32 / $3.96 ($0.044)    | Usage notes \"Input context window of up to 1M tokens\", \"Prompt caching\".                                                                                              |\n| deepseek-v4-flash-0731 | 1,048,576 | 1,048,576     | —      | $0.14 / $0.28 ($0.028)    | NeuroLink fallback. Usage notes \"Input context window of up to 1M tokens\", \"Prompt caching\".                                                                          |\n| deepseek-3.2           | 163,840   | 163,840       | —      | $0.50 / $1.60 ($0.15)     | Models page row \"DeepSeek V3.2\". Usage note \"Prompt caching\".                                                                                                         |\n| glm-5.2                | 262,144   | 262,144       | —      | $1.40 / $4.40 ($0.21)     | NeuroLink fallback. Usage notes \"Text only\", \"Tool calling\", \"Structured outputs\", \"Reaso","hierarchy":{"lvl0":"Getting Started","lvl1":"GradientAI Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"c857e7561183e8a020eb8c905101be32a97407b05031ceb5d249a42934a5b4a7","title":"Verification status","url":"/docs/getting-started/providers/gradientai#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog currently records for GradientAI — docs-verified only, not\nlive-verified:\n\n| Probe                     | Result                                                                                                                                                                                                                                                                                          |\n| ------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                    | unauthenticated GET https://inference.do-ai.run/v1/models answered HTTP 401 on 2026-09-29 without a key, so model ids are taken from the models page (retrieved 2026-09-29); roster not verified                                                                                              |\n| Auth-failure shape        | the 401 body was {\"id\": \"Unauthorized\", \"message\": \"Unable to authenticate you\" }; authProbe records status 401, code Unauthorized; errorRules covers 401, 429 (body documented in the API reference) and the 404 \"Model not found\" response described on the Model Support Policy page |\n| Chat route                | unauthenticated GET https://inference.do-ai.run/v1/chat/completions answered HTTP 405 with an empty body on 2026-09-29; the documented verb is POST and no POST was sent                                                                                                                      |\n| Billing                   | prepayment page: \"Serverless Inference requires a positive prepaid account balance before you can send inference requests.\" — 2026-09-29                       ","hierarchy":{"lvl0":"Getting Started","lvl1":"GradientAI Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"70ae4da0348b2feab54e6c8b3fd16025b2775bbbb2cc70cc80e3400706e0ce01","title":"Troubleshooting","url":"/docs/getting-started/providers/gradientai#troubleshooting","content":"Each row restates what a DigitalOcean page says; the source page is named in the\nSymptom column.\n\n| Symptom                                                                                                                               | Cause                                                                                                                        | Fix                                                                                                                                                             |\n| ------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| HTTP 401 Unable to authenticate you (API reference)  | The API reference describes 401 as \"Authentication failed due to invalid credentials.\"                                       | Authenticate with a model access key or a DigitalOcean personal access token (overview) |\n| Key stops working (model access keys page)       | \"Regeneration takes effect immediately, with no grace period during which both the old and new keys are valid.\"              | \"update any application that uses the key as soon as you regenerate it\"                                                                                         |\n| Access suspended (prepayment page) | \"When your balance reaches $0, DigitalOcean suspends your access to Serverless Inference until you replenish it.\"            | \"add a prepayment balance manually or enable auto-reload\"                                                                                                       |\n| HTTP 404 Model not found (Model Support Policy)   | \"The model is no longer accessible. Requests to th","hierarchy":{"lvl0":"Getting Started","lvl1":"GradientAI Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
+{"objectID":"12ffa0f7f1a2247dda95cc723224e90c30a49be3df2235638c6f9527ac91f188","title":"See also","url":"/docs/getting-started/providers/gradientai#see-also","content":"Provider setup overview\nProviders index\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility\nDigitalOcean pages opened for this entry: Use Serverless Inference, Serverless Inference API Endpoints, Chat Completions API, Available models, Pricing, Features","hierarchy":{"lvl0":"Getting Started","lvl1":"GradientAI Provider Guide","lvl2":"See also","lvl3":""}},
 {"objectID":"a8e744d750b5ed5548aec577bd769cf20e01bee8e3c38d2b1798cd51202fac2e","title":"Groq Provider Guide","url":"/docs/getting-started/providers/groq","content":"Groq Provider Guide\n\nSub-100ms inference of open-weight models via Groq's LPU — best for\nlatency-sensitive applications\n\nOverview\n\nGroq operates custom Language Processing Units (LPUs) that achieve far\nlower per-token latency than GPU-based inference. NeuroLink wraps\napi.groq.com/openai/v1 (OpenAI-compatible) so the same generate /\nstream contract works for Llama 3.3 / 3.1, Mixtral, Gemma 2, and the\nLlama 3.2 vision variants.\nllama-3.3-70b-versatile (default) — production-grade, 128K context\nllama-3.1-8b-instant — lowest latency tier\nllama-3.2-90b-vision-preview, llama-3.2-11b-vision-preview — multimodal\ngemma2-9b-it — Google's lightweight instruct model\nmixtral-8x7b-32768 — Mistral MoE\nllama-guard-3-8b — safety classifier\n\nKey Facts\nProtocol: OpenAI-compatible (/v1/chat/completions)\nDefault base URL: https://api.groq.com/openai/v1\nDefault model: llama-3.3-70b-versatile\nLatency: typically \\<100ms TTFT (time to first token)\nContext window: 128K tokens on modern Llamas; 32K on Mixtral; 8K on Gemma 2\nVision: Yes — Llama 3.2 vision variants\nStreaming: Supported (with characteristically low TTFT)\nTool calling: Supported\nReasoning trace: Not exposed (use models that natively reason)\n\nQuick Start\nGet an API Key\n\nSign up at https://console.groq.com/ and\ncreate an API key at\nhttps://console.groq.com/keys.\nConfigure Environment\nGenerate Your First Response\n\nSDK Usage\n\nBasic Generation\n\nLowest-Latency Tier\n\nFor chatbots / autocomplete where TTFT matters most:\n\nVision Input\n\nStreaming\n\nStreaming through Groq is particularly responsive due to the LPU:\n\nTool Calling\n\nFor tool-heavy workflows, consider llama3-groq-70b-8192-tool-use-preview (a tool-tuned variant).\n\nPer-Call Credentials\n\nCLI Usage\n\nProvider Aliases\n\n| Alias  | Example           |\n| ------ | ----------------- |\n| groq | --provider groq |\n\nConfiguration Reference\n\n| Environment Variable | Required | Default                          | Description   |\n| -------------------- | -------- | -------------------------------- | ------------- |\n| GROQ_API_KEY       | Yes      | —                                | Groq API key  |\n| GROQ_MODEL         | No       | llama-3.3-70b-versatile        | Default model |\n| GROQ_BASE_URL      | No       | https://api.groq.com/openai/v1 | Base URL      |\n\nFeature Support Matrix\n\n| Feature           | llama-3.3-70b | llama-3.1-8b-instant | llama-3.2-vision | mixtral-8x7b | gemma2-9b |\n| ----------------- | ------------- | -------------------- | ---------------- | ------------ | --------- |\n| Text generation   | Yes           | Yes                  | Yes              | Yes          | Yes       |\n| Streaming         | Yes           | Yes                  | Yes              | Yes          | Yes       |\n| Tool calling      | Yes           | Yes                  | Limited          | Yes          | Yes       |\n| Structured output | Yes           | Yes                  | Limited          | Yes          | Yes       |\n| Vision            | No            | No                   | Yes              | No           | No        |\n| Embeddings        | No            | No                   | No               | No           | No        |\n| Context window    | 128K          | 128K                 | 128K             | 32K          | 8K        |\n\nTroubleshooting\n\n\"Invalid Groq API key\"\n\nGet / rotate at https://console.groq.com/keys.\n\n\"Groq rate limit exceeded\"\n\nFree-tier limits are tight (RPM and TPM). Implement exponential\nbackoff or upgrade at\nhttps://console.groq.com/settings/billing.\n\n\"Groq model 'X' was decommissioned\"\n\nGroq deprecates older models periodically. Pick a current model from\nhttps://console.groq.com/docs/models.\n\n\"Whisper-large-v3 is in the model list — can I transcribe?\"\n\nThe Whisper models on Groq are STT (speech-to-text), not chat models.\nUse NeuroLink's STT path with provider: \"openai-stt\" or \"deepgram\"\nfor transcription — Groq's Whisper endpoint isn't exposed through the\nLLM provider class today.\n\nLatency feels normal, not sub-100ms\n\nTTFT depends on input prompt length and model size. For sub-100ms,\nkeep the prompt short (\\<200 tokens) and use llama-3.1-8b-instant.\nAlso: ensure your network round-trip to api.groq.com is low — test\nfrom a region close to Groq's PoPs.\n\nSee Also\nxAI Grok Provider — sibling OpenAI-compat with Grok 3\nDeepSeek Provider — sibling with reasoning models\nTogether AI — sibling open-model gateway (no setup doc yet; see src/lib/providers/togetherAi.ts)\nAdding a new LLM provider — internal reference\n\nNeed Help? Open a GitHub Discussion or issue.","hierarchy":{"lvl0":"Getting Started","lvl1":"Groq Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"812046ce5d68272f5199ddddef497d8d7038609f7423ed3be955a764ebe09796","title":"Groq Provider Guide","url":"/docs/getting-started/providers/groq#groq-provider-guide","content":"Sub-100ms inference of open-weight models via Groq's LPU — best for\nlatency-sensitive applications","hierarchy":{"lvl0":"Getting Started","lvl1":"Groq Provider Guide","lvl2":"Groq Provider Guide","lvl3":""}},
 {"objectID":"426c55d664c5ea4dfdded83e31cb195800d8e6f08a8d5b43d6fb2ce3263c0cc0","title":"Overview","url":"/docs/getting-started/providers/groq#overview","content":"Groq operates custom Language Processing Units (LPUs) that achieve far\nlower per-token latency than GPU-based inference. NeuroLink wraps\napi.groq.com/openai/v1 (OpenAI-compatible) so the same generate /\nstream contract works for Llama 3.3 / 3.1, Mixtral, Gemma 2, and the\nLlama 3.2 vision variants.\nllama-3.3-70b-versatile (default) — production-grade, 128K context\nllama-3.1-8b-instant — lowest latency tier\nllama-3.2-90b-vision-preview, llama-3.2-11b-vision-preview — multimodal\ngemma2-9b-it — Google's lightweight instruct model\nmixtral-8x7b-32768 — Mistral MoE\nllama-guard-3-8b — safety classifier","hierarchy":{"lvl0":"Getting Started","lvl1":"Groq Provider Guide","lvl2":"Overview","lvl3":""}},
@@ -5936,6 +6000,18 @@
 {"objectID":"29e9cc4a73464fbd13d4148d299615ba07d1368b941d5316139d1caaec3b525e","title":"\"Whisper-large-v3 is in the model list — can I transcribe?\"","url":"/docs/getting-started/providers/groq#whisper-large-v3-is-in-the-model-list-can-i-transcribe","content":"The Whisper models on Groq are STT (speech-to-text), not chat models.\nUse NeuroLink's STT path with provider: \"openai-stt\" or \"deepgram\"\nfor transcription — Groq's Whisper endpoint isn't exposed through the\nLLM provider class today.","hierarchy":{"lvl0":"Getting Started","lvl1":"Groq Provider Guide","lvl2":"\"Whisper-large-v3 is in the model list — can I transcribe?\"","lvl3":""}},
 {"objectID":"ae151e5e0c4714f9c0d78609432512bf13e6456bdb7aa1852e8687366b72e209","title":"Latency feels normal, not sub-100ms","url":"/docs/getting-started/providers/groq#latency-feels-normal-not-sub-100ms","content":"TTFT depends on input prompt length and model size. For sub-100ms,\nkeep the prompt short (\\<200 tokens) and use llama-3.1-8b-instant.\nAlso: ensure your network round-trip to api.groq.com is low — test\nfrom a region close to Groq's PoPs.","hierarchy":{"lvl0":"Getting Started","lvl1":"Groq Provider Guide","lvl2":"Latency feels normal, not sub-100ms","lvl3":""}},
 {"objectID":"30507397a6c96c1ce422fbef2fcb9b549297b3dff565aa9fd15856051826f821","title":"See Also","url":"/docs/getting-started/providers/groq#see-also","content":"xAI Grok Provider — sibling OpenAI-compat with Grok 3\nDeepSeek Provider — sibling with reasoning models\nTogether AI — sibling open-model gateway (no setup doc yet; see src/lib/providers/togetherAi.ts)\nAdding a new LLM provider — internal reference\n\nNeed Help? Open a GitHub Discussion or issue.","hierarchy":{"lvl0":"Getting Started","lvl1":"Groq Provider Guide","lvl2":"See Also","lvl3":""}},
+{"objectID":"31ce7fe0f43dca7b00a91cbccde4005d0358c5eb58beaeb2cff7d48937f55b55","title":"Hetzner Inference Provider Guide","url":"/docs/getting-started/providers/hetzner-inference","content":"Hetzner Inference Provider Guide\n\nHetzner Inference is a Tier-2 catalog provider: its integration is one JSON\nfile (src/lib/providers/catalog/hetzner-inference.json) rather than\nhand-written code. That file is the source of truth for this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. Hetzner's GET /models needs a key, so the model ids come\nfrom its public docs page and the roster has not been checked. No account was\ncreated and no API key was used to build the entry. evidence.liveMatrix is\nnull (see Verification status below).\n\nKey Facts\nProvider id: hetzner-inference (alias hetzner)\nProtocol: OpenAI-compatible (/chat/completions) — the docs page says\n  \"The Inference API provides access to open-source large language models via\n  an OpenAI-compatible REST API.\"\n  (docs)\nBase URL: https://inference.hetzner.com/api/v1\nDefault model: Qwen/Qwen3.6-35B-A3B-FP8\nModels in catalog: 2 — the two rows of the docs page's Available Models\n  table, with ids copied from the table cells\nVision: true on both catalog rows — the table's Modalities cell reads\n  \"Text, Image\" for each\nStreaming: not declared (false)\nTool calling: not declared (false)\nTools while streaming: not declared (false)\nStructured output: not declared (false)\nStructured output + tools together: not declared (false) — no combined\n  probe was possible without credentials\nEmbeddings: not declared (false)\nThinking: not declared (false)\nService status: the docs page's note reads \"This service is provided for\n  experimental purposes only and is offered \"as is\".\" and \"Performance and\n  availability are not guaranteed, especially during periods of high demand.\"\n  The same note reads \"No backups are created, so you are responsible for\n  backing up your own configurations and should not use the platform for\n  production environments.\"\nBilling: free-tier — the docs FAQ says \"As long as the Inference API\n  remains in experimental status, it is free of charge.\"\nKey format: none declared\n\nQuick Start\nGet an API token\nVisit: https://experiments.hetzner.com/inference — the page is client-rendered; its public JavaScript bundle labels the token area \"Tokens\" and the button \"Create API Token\" (sign-in was not attempted while building this entry)\nCreate an API token and copy it. The docs' curl examples (https://docs.hetzner.com/general/company-and-policy/experiments/inference/) use the header Authorization: Bearer <YOUR_TOKEN>\nBilling as the vendor states it: \"As long as the Inference API remains in experimental status, it is free of charge.\" (FAQ, same docs page)\nSet HETZNER_INFERENCE_API_KEY in your .env file\nConfigure\nUse it\n\nPer-request credentials:\n\nModels\n\n| Model                         | Context | Vision | Notes                                                                                                                                                |\n| ----------------------------- | ------- | ------ | ---------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Qwen/Qwen3.6-35B-A3B-FP8 ⭐ | 262,144 | yes    | NeuroLink default. Type \"Causal LM + Vision (MoE, 35B total / 3B active)\"; named in the docs page's four code examples, including its image example. |\n| Qwen3.8-27B                 | 262,144 | yes    | Fallback. Type \"Dense\"; Modalities \"Text, Image\".                                                                                                    |\n\nThe figures come from the Available Models table of\nhttps://docs.hetzner.com/general/company-and-policy/experiments/inference/\n(retrieved 2026-09-29): Context Length \"262,144 tokens\" and Modalities \"Text,\nImage\" on both rows. The same page says \"Only a selected list of models is\navailable. This selection will change during the experimental phase.\" and \"The\nresponse of the models endpoint is definitive.\"\n\nmodels.defaultContextWindow (32,768) and models.defaultMaxOutputTokens\n(4,096) are placeholders the vendor does not publish. They apply to model ids\noutside the catalog, and the output figure applies to both catalog rows, which\ncarry no maxOutputTokens.\n\nFallback order when the default is unavailable: Qwen3.8-27B.\n\nLicenses, as the page's Open-Source Model Licenses table lists them: rows\n\"Qwen3.6-35B-A3B\" and \"Qwen3.8-27B\", each with Developer \"Alibaba Cloud (Qwen\nTeam)\" and License \"Apache 2.0\". The page also says \"By using this API, you\nacknowledge the applicable license terms of the underlying model(s).\"\n\nRate limits\n\nThe docs FAQ says \"Current limits are applied per API key:\" followed by a table\nwith Timeframe \"60s\", Input Tokens \"4M\" and Output Tokens \"100k\". A second\ntable, introduced by \"Additionally, we enforce request-level rate-limits as\nfollows:\", lists Timeframe \"60s\" and Requests \"10\". The FAQ continues: \"If you\nexceed any of the rate limits, the API will respond with HTTP Status Code 429.\"\n\nerrorRules maps HTTP 429 to NeuroLink's rate-limit error class and HTTP 401\nto","hierarchy":{"lvl0":"Getting Started","lvl1":"Hetzner Inference Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"b0a5c8dcc3441dc54546fdf57e5245846f33e1d203e15e5c6fd5e035dbe493fc","title":"Hetzner Inference Provider Guide","url":"/docs/getting-started/providers/hetzner-inference#hetzner-inference-provider-guide","content":"Hetzner Inference is a Tier-2 catalog provider: its integration is one JSON\nfile (src/lib/providers/catalog/hetzner-inference.json) rather than\nhand-written code. That file is the source of truth for this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. Hetzner's GET /models needs a key, so the model ids come\nfrom its public docs page and the roster has not been checked. No account was\ncreated and no API key was used to build the entry. evidence.liveMatrix is\nnull (see Verification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"Hetzner Inference Provider Guide","lvl2":"Hetzner Inference Provider Guide","lvl3":""}},
+{"objectID":"0b3e608842620ed7fd8166e587b9127badc9d21fed834c6594d82c445fe57b6c","title":"Key Facts","url":"/docs/getting-started/providers/hetzner-inference#key-facts","content":"Provider id: hetzner-inference (alias hetzner)\nProtocol: OpenAI-compatible (/chat/completions) — the docs page says\n  \"The Inference API provides access to open-source large language models via\n  an OpenAI-compatible REST API.\"\n  (docs)\nBase URL: https://inference.hetzner.com/api/v1\nDefault model: Qwen/Qwen3.6-35B-A3B-FP8\nModels in catalog: 2 — the two rows of the docs page's Available Models\n  table, with ids copied from the table cells\nVision: true on both catalog rows — the table's Modalities cell reads\n  \"Text, Image\" for each\nStreaming: not declared (false)\nTool calling: not declared (false)\nTools while streaming: not declared (false)\nStructured output: not declared (false)\nStructured output + tools together: not declared (false) — no combined\n  probe was possible without credentials\nEmbeddings: not declared (false)\nThinking: not declared (false)\nService status: the docs page's note reads \"This service is provided for\n  experimental purposes only and is offered \"as is\".\" and \"Performance and\n  availability are not guaranteed, especially during periods of high demand.\"\n  The same note reads \"No backups are created, so you are responsible for\n  backing up your own configurations and should not use the platform for\n  production environments.\"\nBilling: free-tier — the docs FAQ says \"As long as the Inference API\n  remains in experimental status, it is free of charge.\"\nKey format: none declared","hierarchy":{"lvl0":"Getting Started","lvl1":"Hetzner Inference Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"d4f6a66d1666cdbfeb0a1c1823e6e224353df2afbdd955b43174ec987b65abc1","title":"1. Get an API token","url":"/docs/getting-started/providers/hetzner-inference#1-get-an-api-token","content":"Visit: https://experiments.hetzner.com/inference — the page is client-rendered; its public JavaScript bundle labels the token area \"Tokens\" and the button \"Create API Token\" (sign-in was not attempted while building this entry)\nCreate an API token and copy it. The docs' curl examples (https://docs.hetzner.com/general/company-and-policy/experiments/inference/) use the header Authorization: Bearer <YOUR_TOKEN>\nBilling as the vendor states it: \"As long as the Inference API remains in experimental status, it is free of charge.\" (FAQ, same docs page)\nSet HETZNER_INFERENCE_API_KEY in your .env file","hierarchy":{"lvl0":"Getting Started","lvl1":"Hetzner Inference Provider Guide","lvl2":"1. Get an API token","lvl3":""}},
+{"objectID":"c2803366241c7427722b61c11e44322c1c5a4b8f0d3d11d9a8a96e28af68f952","title":"3. Use it","url":"/docs/getting-started/providers/hetzner-inference#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Hetzner Inference Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"7917c433751006555e54a3a035886e9f6a35c63a0f557b8fc8a25e93408bc6ea","title":"CLI","url":"/docs/getting-started/providers/hetzner-inference#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider hetzner-inference\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"hetzner-inference\",\n  credentials: {\n    hetznerInference: { apiKey: process.env.HETZNERINFERENCEAPI_KEY },\n  },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"Hetzner Inference Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"8e792979eed2dc32d3b4d4bc7c895799caa20c3579d1e1d3bbe8b8aa978e47db","title":"Models","url":"/docs/getting-started/providers/hetzner-inference#models","content":"| Model                         | Context | Vision | Notes                                                                                                                                                |\n| ----------------------------- | ------- | ------ | ---------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Qwen/Qwen3.6-35B-A3B-FP8 ⭐ | 262,144 | yes    | NeuroLink default. Type \"Causal LM + Vision (MoE, 35B total / 3B active)\"; named in the docs page's four code examples, including its image example. |\n| Qwen3.8-27B                 | 262,144 | yes    | Fallback. Type \"Dense\"; Modalities \"Text, Image\".                                                                                                    |\n\nThe figures come from the Available Models table of\nhttps://docs.hetzner.com/general/company-and-policy/experiments/inference/\n(retrieved 2026-09-29): Context Length \"262,144 tokens\" and Modalities \"Text,\nImage\" on both rows. The same page says \"Only a selected list of models is\navailable. This selection will change during the experimental phase.\" and \"The\nresponse of the models endpoint is definitive.\"\n\nmodels.defaultContextWindow (32,768) and models.defaultMaxOutputTokens\n(4,096) are placeholders the vendor does not publish. They apply to model ids\noutside the catalog, and the output figure applies to both catalog rows, which\ncarry no maxOutputTokens.\n\nFallback order when the default is unavailable: Qwen3.8-27B.\n\nLicenses, as the page's Open-Source Model Licenses table lists them: rows\n\"Qwen3.6-35B-A3B\" and \"Qwen3.8-27B\", each with Developer \"Alibaba Cloud (Qwen\nTeam)\" and License \"Apache 2.0\". The page also says \"By using this API, you\nacknowledge the applicable license terms of the underlying model(s).\"","hierarchy":{"lvl0":"Getting Started","lvl1":"Hetzner Inference Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"d9365cc302fd5e888114656b8d977c3c64c3ee3a00e03b6f55097d6a139ed573","title":"Rate limits","url":"/docs/getting-started/providers/hetzner-inference#rate-limits","content":"The docs FAQ says \"Current limits are applied per API key:\" followed by a table\nwith Timeframe \"60s\", Input Tokens \"4M\" and Output Tokens \"100k\". A second\ntable, introduced by \"Additionally, we enforce request-level rate-limits as\nfollows:\", lists Timeframe \"60s\" and Requests \"10\". The FAQ continues: \"If you\nexceed any of the rate limits, the API will respond with HTTP Status Code 429.\"\n\nerrorRules maps HTTP 429 to NeuroLink's rate-limit error class and HTTP 401\nto its authentication class.","hierarchy":{"lvl0":"Getting Started","lvl1":"Hetzner Inference Provider Guide","lvl2":"Rate limits","lvl3":""}},
+{"objectID":"3907301ec3897164e413c88d591fccee01805f074593c3ca15c71963e1b7321e","title":"Data handling","url":"/docs/getting-started/providers/hetzner-inference#data-handling","content":"The docs FAQ says \"We do not store the content of request and response and we\ndo not plan on doing so in the future (unless some law requires us to do so).\"","hierarchy":{"lvl0":"Getting Started","lvl1":"Hetzner Inference Provider Guide","lvl2":"Data handling","lvl3":""}},
+{"objectID":"d49f6fc9930a17ca53e2272a8d5819a8ed46b5ca1401de732543f8ecc39b958c","title":"Verification status","url":"/docs/getting-started/providers/hetzner-inference#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the catalog\ncurrently records for Hetzner Inference — docs-verified only, not\nlive-verified:\n\n| Probe                 | Result                                                                                                                                                                                                                                                                                                                 |\n| --------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                | unauthenticated GET https://inference.hetzner.com/api/v1/models, HTTP 401, 2026-09-29 — no key used; the model ids are taken from the docs page's Available Models table, and the roster has not been checked                                                                                                        |\n| Auth-failure shape    | the same unauthenticated GET /models returned HTTP 401, content-type application/json; charset=utf-8, body {\"error\":\"unauthorized\"}; an unauthenticated GET /chat/completions on the same day answered HTTP 404, content-type text/plain; charset=utf-8, body \"404 page not found\". No POST request was sent |\n| Billing               | public docs FAQ, 2026-09-29: \"As long as the Inference API remains in experimental status, it is free of charge. Should this status change, we will notify you in advance via email with detailed information.\"                                                                                                        |\n| Capabilities          | text is true because the docs page shows chat-completion exam","hierarchy":{"lvl0":"Getting Started","lvl1":"Hetzner Inference Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"17df6b8e86219f94d9bd26a3db0e9f35688cc10b829534d1885496ef344b081c","title":"Troubleshooting","url":"/docs/getting-started/providers/hetzner-inference#troubleshooting","content":"| Symptom                               | What the vendor states or what was observed                                                                                                                         |\n| ------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| HTTP 401                              | Observed 2026-09-29: an unauthenticated GET /models answered HTTP 401 with {\"error\":\"unauthorized\"}. NeuroLink reads the token from HETZNER_INFERENCE_API_KEY |\n| HTTP 429                              | Docs FAQ: \"If you exceed any of the rate limits, the API will respond with HTTP Status Code 429.\" Limits are listed under Rate limits               |\n| Model ids differ from the table above | Docs page: \"This selection will change during the experimental phase.\" and \"The response of the models endpoint is definitive.\"                                     |","hierarchy":{"lvl0":"Getting Started","lvl1":"Hetzner Inference Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
+{"objectID":"c29c333d86c1b2abdd231a5ac8a48748495c6011c3629ec82052d532d35e3457","title":"See also","url":"/docs/getting-started/providers/hetzner-inference#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Hetzner Inference Provider Guide","lvl2":"See also","lvl3":""}},
 {"objectID":"97ec9237c6e895e2031d3238459416c0729d15a8f3ea459e4cd29019a9cf2436","title":"HeyGen Provider Guide (avatar)","url":"/docs/getting-started/providers/heygen","content":"HeyGen Provider Guide\n\nTalking-head avatar videos via HeyGen's V2 API\n\nOverview\n\nHeyGen generates studio-quality avatar videos\nfrom a portrait + script. NeuroLink dispatches via\noutput: { mode: 'avatar' }.\n\nKey Facts\nEndpoints: POST /v2/video/generate, GET /v1/video_status.get\nAsync: Submit + poll\nOutput: MP4 (default) / WebM\nRequires: HeyGen account-bound avatar id\n\nQuick Start\nGet an API Key + Avatar ID\n\nhttps://app.heygen.com/settings/api\nand pick an avatar id from your avatar library.\nConfigure\nGenerate\n\nCLI Usage\n\nConfiguration Reference\n\n| Environment Variable    | Required | Description                      |\n| ----------------------- | -------- | -------------------------------- |\n| HEYGEN_API_KEY        | Yes      | HeyGen API key                   |\n| HEYGEN_TEST_AVATAR_ID | No       | Optional avatar id for test runs |\n\nSee Also\nD-ID Provider\nMuseTalk via Replicate","hierarchy":{"lvl0":"Getting Started","lvl1":"HeyGen Provider Guide (avatar)","lvl2":"","lvl3":""}},
 {"objectID":"0d558302f5bda8f47b66e7c9f3d27215777275fe1f89d7a9c13cc89a6c95c13e","title":"HeyGen Provider Guide","url":"/docs/getting-started/providers/heygen#heygen-provider-guide","content":"Talking-head avatar videos via HeyGen's V2 API","hierarchy":{"lvl0":"Getting Started","lvl1":"HeyGen Provider Guide (avatar)","lvl2":"HeyGen Provider Guide","lvl3":""}},
 {"objectID":"d89cf58fb842fd185cd3a4c40891c594f1dea175265449fca992dd86e44aae92","title":"Overview","url":"/docs/getting-started/providers/heygen#overview","content":"HeyGen generates studio-quality avatar videos\nfrom a portrait + script. NeuroLink dispatches via\noutput: { mode: 'avatar' }.","hierarchy":{"lvl0":"Getting Started","lvl1":"HeyGen Provider Guide (avatar)","lvl2":"Overview","lvl3":""}},
@@ -6003,6 +6079,17 @@
 {"objectID":"e36b07253cf3b9f30e41c888c8083b32320bae3c3cc53e6fc824e7d9677f6e07","title":"Verification status","url":"/docs/getting-started/providers/inception-labs#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog records for Inception Labs:\n\n| Probe                 | Result                                                                                                                                                                                                                                    |\n| --------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                | authenticated GET /v1/models, HTTP 200, 2026-09-03                                                                                                                                                                                        |\n| Auth rejection        | HTTP 401 invalid_api_key, 2026-09-03                                                                                                                                                                                                    |\n| Live capability sweep | 2026-09-03 — Full capability sweep on mercury-2: chat, stream, systemrole, contenttextparts, samplingparams, tools, toolsstream, toolsroundtripnull, toolchoicewithouttools, jsonobject, jsonschema and toolsplusschema all |","hierarchy":{"lvl0":"Getting Started","lvl1":"Inception Labs Provider Guide","lvl2":"Verification status","lvl3":""}},
 {"objectID":"7eccde36bee5c7ddb2b800c370a2adba5ae48cbde5f16cf242e969e6a691d8ab","title":"Troubleshooting","url":"/docs/getting-started/providers/inception-labs#troubleshooting","content":"| Symptom                          | Cause                                   | Fix                                                                   |\n| -------------------------------- | --------------------------------------- | --------------------------------------------------------------------- |\n| Invalid Inception Labs API key | INCEPTION_LABS_API_KEY unset or wrong | Check the key at https://platform.inceptionlabs.ai/dashboard/api-keys |\n| Model not found                  | The roster changed since 2026-09-03     | Pick a current id; catalog providers retire models without notice     |","hierarchy":{"lvl0":"Getting Started","lvl1":"Inception Labs Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
 {"objectID":"1f495e1867e86b99eab1619314909fddc3a3bd14172aa094a059683a4daac6c3","title":"See also","url":"/docs/getting-started/providers/inception-labs#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Inception Labs Provider Guide","lvl2":"See also","lvl3":""}},
+{"objectID":"d998c763c0816e5153aa248aea16e97902016580a5274b0dfc77074aba8b95e1","title":"Inceptron Provider Guide","url":"/docs/getting-started/providers/inceptron","content":"Inceptron Provider Guide\n\nInceptron is a Tier-2 catalog provider: an OpenAI-compatible endpoint\ndescribed by one JSON file (src/lib/providers/catalog/inceptron.json) rather\nthan hand-written code.\n\nVerification status: this entry is docs- and roster-verified, not yet\nlive-verified. The fields below come from Inceptron's own public pages,\nan unauthenticated GET /v1/models call and an unauthenticated\nGET /v1/chat/completions call — no account was created and no API key was\nused to build it. evidence.liveMatrix is null until someone runs the live\ncapability matrix with a real key (see\nVerification status below).\n\nKey Facts\nProvider id: inceptron\nProtocol: OpenAI-compatible (/chat/completions) — the Chat Completions\n  API Reference says \"Our API is compliant with OpenAI's Chat Completions API\"\n  (docs)\nBase URL: https://api.inceptron.io/v1\nDefault model: zai-org/GLM-5.3\nModels in catalog: 6 (the full 6-model live roster)\nStreaming: supported — the Chat Completions API Reference documents the\n  stream parameter and a streaming response, and there is a\n  Handling Streaming Responses\n  guide\nTool calling: true — the Chat Completions API Reference and the\n  Tool Calling guide describe\n  OpenAI-compatible tool calling with tools and tool_choice, with worked\n  examples on moonshotai/Kimi-K2.6. The models page tags each of the six\n  model cards tool-calling\nTools while streaming: true — the Chat Completions API Reference has a\n  \"Streaming Tool Call Response\" section and the Tool Calling guide has a\n  \"Handle Streamed Tool Calls\" section\nStructured output: false on this entry. The Chat Completions API\n  Reference request table lists model, messages, temperature,\n  max_tokens, stream, top_p, n, stop, tools and tool_choice; the\n  roster's supported_features field lists json_mode and structured_outputs\n  for the six models. Structured output was not exercised live\nStructured output + tools together: not declared (false) — no\n  combined probe was run without credentials\nEmbeddings: not declared (false)\nThinking: not declared (false). The models page tags each of the six\n  model cards reasoning, and the Kilo Code guide configures reasoningEffort\n  variants low, high and max for zai-org/GLM-5.3\nBilling: recorded as no-free-tier because the catalog schema has no\n  unknown value — a schema placeholder, not a vendor statement\nKey format: none declared\n\nQuick Start\nGet an API key\nVisit: https://console.inceptron.io and sign in or sign up — the sign-in page shows Continue with Google, Continue with GitHub and Sign in with email, and links to https://console.inceptron.io/auth/signup\nCreate an API key — the Introduction page says: \"After signing up, navigate to the account section of the dashboard to create an API key.\" (https://docs.inceptron.io/introduction)\nSet INCEPTRON_API_KEY in your .env file (the docs' examples read INCEPTRONAPIKEY)\n\nThe Authentication guide\n(docs) says:\n\nYou can find your API key in your Inceptron account dashboard under the \"API Keys\" section.\nConfigure\nUse it\n\nPer-request credentials also work:\n\nModels\n\n| Model                                | Context   | Vision | $/M in · out (cache read) | Notes                                                                                                                                                                                                                  |\n| ------------------------------------ | --------- | ------ | ------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| zai-org/GLM-5.3 ⭐                 | 1,048,576 | no     | $1.40 / $4.40 ($0.26)     | NeuroLink default. The model in the docs' Get Started, Introduction, Chat Completions, Error Handling and Streaming code examples and in the Kilo Code and OpenCode config. Tags: text, code, tool-calling, reasoning. |\n| moonshotai/Kimi-K2.6               | 262,144   | yes    | $0.73 / $3.50 ($0.25)     | NeuroLink fallback. The model in the docs' tool-calling examples. Tags: multimodal, tool-calling, reasoning. models.visionModel.                                                                                     |\n| deepseek-ai/DeepSeek-V4-Flash-0731 | 1,048,576 | no     | $0.13 / $0.28 ($0.03)     | NeuroLink fallback. Tags: text, code, tool-calling, reasoning.                                                                                                                                                         |\n| zai-org/GLM-5.2                    | 1,048,576 | no     | $1.20 / $4.20 ($0.26)     | NeuroLink fallback. Tags: text, code, tool-calling, reasoning.                                                                                                                                                         |\n| moonshotai/Kimi-K2.7-Code          | 262,144   | yes    | $0.75 / $3.50 ($0.20)     | Tags: multimodal, ","hierarchy":{"lvl0":"Getting Started","lvl1":"Inceptron Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"68d39b8082a2f3b72b1acd4614547a17dd2bffcd4a43ba4528fb7a470d907dd8","title":"Inceptron Provider Guide","url":"/docs/getting-started/providers/inceptron#inceptron-provider-guide","content":"Inceptron is a Tier-2 catalog provider: an OpenAI-compatible endpoint\ndescribed by one JSON file (src/lib/providers/catalog/inceptron.json) rather\nthan hand-written code.\n\nVerification status: this entry is docs- and roster-verified, not yet\nlive-verified. The fields below come from Inceptron's own public pages,\nan unauthenticated GET /v1/models call and an unauthenticated\nGET /v1/chat/completions call — no account was created and no API key was\nused to build it. evidence.liveMatrix is null until someone runs the live\ncapability matrix with a real key (see\nVerification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"Inceptron Provider Guide","lvl2":"Inceptron Provider Guide","lvl3":""}},
+{"objectID":"919a3280bd716c6f2b06da95e79dffb8bc9506f8702ec8d39c9a1963df7b61a2","title":"Key Facts","url":"/docs/getting-started/providers/inceptron#key-facts","content":"Provider id: inceptron\nProtocol: OpenAI-compatible (/chat/completions) — the Chat Completions\n  API Reference says \"Our API is compliant with OpenAI's Chat Completions API\"\n  (docs)\nBase URL: https://api.inceptron.io/v1\nDefault model: zai-org/GLM-5.3\nModels in catalog: 6 (the full 6-model live roster)\nStreaming: supported — the Chat Completions API Reference documents the\n  stream parameter and a streaming response, and there is a\n  Handling Streaming Responses\n  guide\nTool calling: true — the Chat Completions API Reference and the\n  Tool Calling guide describe\n  OpenAI-compatible tool calling with tools and tool_choice, with worked\n  examples on moonshotai/Kimi-K2.6. The models page tags each of the six\n  model cards tool-calling\nTools while streaming: true — the Chat Completions API Reference has a\n  \"Streaming Tool Call Response\" section and the Tool Calling guide has a\n  \"Handle Streamed Tool Calls\" section\nStructured output: false on this entry. The Chat Completions API\n  Reference request table lists model, messages, temperature,\n  max_tokens, stream, top_p, n, stop, tools and tool_choice; the\n  roster's supported_features field lists json_mode and structured_outputs\n  for the six models. Structured output was not exercised live\nStructured output + tools together: not declared (false) — no\n  combined probe was run without credentials\nEmbeddings: not declared (false)\nThinking: not declared (false). The models page tags each of the six\n  model cards reasoning, and the Kilo Code guide configures reasoningEffort\n  variants low, high and max for zai-org/GLM-5.3\nBilling: recorded as no-free-tier because the catalog schema has no\n  unknown value — a schema placeholder, not a vendor statement\nKey format: none declared","hierarchy":{"lvl0":"Getting Started","lvl1":"Inceptron Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"98222a8f08f959ed3d40c7f2c823e2a837de60c13bdc3cffab5911ac76ab7f24","title":"1. Get an API key","url":"/docs/getting-started/providers/inceptron#1-get-an-api-key","content":"Visit: https://console.inceptron.io and sign in or sign up — the sign-in page shows Continue with Google, Continue with GitHub and Sign in with email, and links to https://console.inceptron.io/auth/signup\nCreate an API key — the Introduction page says: \"After signing up, navigate to the account section of the dashboard to create an API key.\" (https://docs.inceptron.io/introduction)\nSet INCEPTRON_API_KEY in your .env file (the docs' examples read INCEPTRONAPIKEY)\n\nThe Authentication guide\n(docs) says:\n\nYou can find your API key in your Inceptron account dashboard under the \"API Keys\" section.","hierarchy":{"lvl0":"Getting Started","lvl1":"Inceptron Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"61380218fbe2826b4402b4655d1ae1bf5dd65a85c6df5c0bd9cd94cf2b96f1a6","title":"3. Use it","url":"/docs/getting-started/providers/inceptron#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Inceptron Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"85ad3f6db8eb059c955aba593a2a6a1fc4ce1aff275429acca2c06eaa450c9f6","title":"CLI","url":"/docs/getting-started/providers/inceptron#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider inceptron\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"inceptron\",\n  credentials: { inceptron: { apiKey: process.env.INCEPTRONAPIKEY } },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"Inceptron Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"bf7155ddc335ae301b978fea3c6bb95c374b004b25355c5249f367f43690f4b6","title":"Models","url":"/docs/getting-started/providers/inceptron#models","content":"| Model                                | Context   | Vision | $/M in · out (cache read) | Notes                                                                                                                                                                                                                  |\n| ------------------------------------ | --------- | ------ | ------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| zai-org/GLM-5.3 ⭐                 | 1,048,576 | no     | $1.40 / $4.40 ($0.26)     | NeuroLink default. The model in the docs' Get Started, Introduction, Chat Completions, Error Handling and Streaming code examples and in the Kilo Code and OpenCode config. Tags: text, code, tool-calling, reasoning. |\n| moonshotai/Kimi-K2.6               | 262,144   | yes    | $0.73 / $3.50 ($0.25)     | NeuroLink fallback. The model in the docs' tool-calling examples. Tags: multimodal, tool-calling, reasoning. models.visionModel.                                                                                     |\n| deepseek-ai/DeepSeek-V4-Flash-0731 | 1,048,576 | no     | $0.13 / $0.28 ($0.03)     | NeuroLink fallback. Tags: text, code, tool-calling, reasoning.                                                                                                                                                         |\n| zai-org/GLM-5.2                    | 1,048,576 | no     | $1.20 / $4.20 ($0.26)     | NeuroLink fallback. Tags: text, code, tool-calling, reasoning.                                                                                                                                                         |\n| moonshotai/Kimi-K2.7-Code          | 262,144   | yes    | $0.75 / $3.50 ($0.20)     | Tags: multimodal, tool-calling, reasoning.                                       ","hierarchy":{"lvl0":"Getting Started","lvl1":"Inceptron Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"9123069f1d32ebcc9d2e3e54a27de396ccb67e9236f8ea14fe4c9498fbb2558d","title":"Verification status","url":"/docs/getting-started/providers/inceptron#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog currently records for Inceptron — docs- and roster-verified, not\nlive-verified:\n\n| Probe                     | Result                                                                                                                                                                                                                                                                                      |\n| ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                    | unauthenticated GET /v1/models, HTTP 200, 6 models, 2026-09-29 — no key used                                                                                                                                                                                                              |\n| Auth-failure shape        | unauthenticated GET https://api.inceptron.io/v1/chat/completions, HTTP 401, body {\"error\":{\"code\":\"unauthorized\",\"message\":\"Missing or invalid authorization header\",\"type\":\"invalid_request_error\"}}, 2026-09-29 — no key used. errorRules match 401 (probe and docs) and 429 (docs) |\n| Tools / structured output | tool calling and streamed tool calls are documented on the Chat Completions API Reference and the Tool Calling guide; neither tools nor structured output was exercised live, and no combined tools+schema request was sent — structuredOutputWithTools stays false                     |\n| Live capability sweep     | not run. evidence.liveMatrix is null. Before treating this provider as production-ready, run npx tsx test/continuous-test-suite-provider-matrix.ts --provider=inceptron with ","hierarchy":{"lvl0":"Getting Started","lvl1":"Inceptron Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"8defe5c20af661d8067eef4ab75645871ab263520bd5849db706b4ae9c1e6d69","title":"Troubleshooting","url":"/docs/getting-started/providers/inceptron#troubleshooting","content":"The Error Handling page (https://docs.inceptron.io/Guides/error-handling) lists\nthese HTTP status codes, quoted as it shows them:\n\n| Status | Vendor's description                                                                          |\n| ------ | --------------------------------------------------------------------------------------------- |\n| 400    | Your request was malformed. This could be due to missing required parameters or invalid JSON. |\n| 401    | Your API key is missing, invalid, or disabled.                                                |\n| 429    | You have exceeded your rate limit.                                                            |\n| 500    | Something went wrong on our end. Please wait and try again.                                   |","hierarchy":{"lvl0":"Getting Started","lvl1":"Inceptron Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
+{"objectID":"cf3598e26e75bbda6aa314f9a36fa459f6e11a5dd30a73132afd34d3596511d1","title":"Pages opened for this entry","url":"/docs/getting-started/providers/inceptron#pages-opened-for-this-entry","content":"Opened on 2026-09-29 with unauthenticated GET requests:\nhttps://docs.inceptron.io (Get Started)\nhttps://docs.inceptron.io/introduction\nhttps://docs.inceptron.io/API%20Reference/chat-completions\nhttps://docs.inceptron.io/API%20Reference/models\nhttps://docs.inceptron.io/Guides/authentication\nhttps://docs.inceptron.io/Guides/error-handling\nhttps://docs.inceptron.io/Guides/kilo-code\nhttps://docs.inceptron.io/Guides/streaming-responses\nhttps://docs.inceptron.io/Guides/tool-calling\nhttps://www.inceptron.io/models\nhttps://www.inceptron.io/pricing\nhttps://console.inceptron.io\nhttps://console.inceptron.io/auth/signup\nhttps://api.inceptron.io/v1/models\nhttps://api.inceptron.io/v1/chat/completions","hierarchy":{"lvl0":"Getting Started","lvl1":"Inceptron Provider Guide","lvl2":"Pages opened for this entry","lvl3":""}},
+{"objectID":"359e1103de170296ebe6edb44f350f72f7f6e482c00e213867fb9193787f547d","title":"See also","url":"/docs/getting-started/providers/inceptron#see-also","content":"Provider setup overview\nProviders index\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Inceptron Provider Guide","lvl2":"See also","lvl3":""}},
 {"objectID":"65b9dc3932dc6d3ab5c8b97a4dd732baa260a99460b6757ae1c5fc9c9a1fa1f0","title":"Inco Provider Guide","url":"/docs/getting-started/providers/inco","content":"Inco Provider Guide\n\nInco is a Tier-2 catalog provider: OpenAI-wire-compatible with no\nbehavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/inco.json) rather than hand-written code. That\nfile is the source of truth for everything on this page.\n\nVerification status: this entry is docs- and roster-verified, not yet\nlive-verified. Every field below was built from Inco's own published\ndocumentation (https://platform.inco.ai/docs) and an unauthenticated\nGET https://api.inco.ai/v1/models — no API key was used or obtained.\nCapabilities that can only be proven with a working key (tool calling,\nstructured output, vision replies, the exact 401/404/429 error bodies) are\nleft conservative (false) or undocumented until a live capability sweep\nruns. See Live verification below.\n\nKey Facts\nProvider id: inco\nProtocol: OpenAI-compatible (POST /v1/chat/completions); the vendor's\n  docs also describe an Anthropic-SDK-shaped path at the host root\n  (https://api.inco.ai), not used by this entry\nBase URL: https://api.inco.ai/v1\nDefault model: glm-5.3 (editorial pick — Inco's docs name no\n  recommended/default model; chosen for its documented reasoning_effort\n  support and mid-range price among the roster)\nModels in catalog: 10\nStreaming: supported (SSE, per vendor docs)\nTool calling: not documented by the vendor — left false until proven\nStructured output: not documented by the vendor — left false until\n  proven\nEmbeddings: not documented\nBilling: no free tier — strictly prepaid, pay-per-token; a zero balance\n  returns HTTP 402 (credit_balance_exhausted) until you top up\nKey format: sk-inco-...\nAccess: currently waitlist-gated — sign-up is not self-serve\n\nQuick Start\nGet an API key\nVisit: https://platform.inco.ai/waitlist and request access — Inco is\n   currently waitlist-gated, not open signup; existing users sign in at\n   https://platform.inco.ai/sign-in\nOnce approved, create an API key on the dashboard's Keys page\n   (https://platform.inco.ai/keys) — it is shown in full only once and\n   starts with sk-inco-\nAdd prepaid credit before use: billing is strictly pay-per-token with no\n   free tier, and a zero balance returns HTTP 402\n   (credit_balance_exhausted) until you top up\nSet INCO_API_KEY in your .env file\nConfigure\nUse it\n\nPer-request credentials work as they do for every provider:\n\nModels\n\n| Model                      | Context | Vision | $/M in · out (cached)  | Notes                                                                                                                    |\n| -------------------------- | ------- | ------ | ---------------------- | ------------------------------------------------------------------------------------------------------------------------ |\n| glm-5.3 ⭐               | 1M      | no     | $1.40 / $4.40 ($0.26)  | Default (editorial pick). Standard tier, 744B params, exposes reasoning_effort.                                        |\n| deepseek-v4.1-flash      | 1M      | no     | $0.30 / $1.20 ($0.006) | Standard tier, 552B params, reasoning_effort. Fallback.                                                                |\n| kimi-k3                  | 1M      | no     | $3.00 / $15.00 ($0.30) | Standard tier, 2.8T params (MoE), reasoning_effort. Fallback.                                                          |\n| glm-5.3-flash            | 1M      | no     | $0.15 / $0.50 ($0.03)  | Standard tier, 320B params. Fallback.                                                                                    |\n| minimax-m3               | 1M      | yes    | $0.30 / $1.20 ($0.06)  | Standard tier, 428B params, reasoning_effort. Vision per the catalog's modalities field — not live-probed. Fallback. |\n| glm-5.3:fast             | 1M      | no     | $2.80 / $8.80 ($0.52)  | Fast-tier sibling of the default; ~2x price for lower latency. Fallback.                                                 |\n| kimi-k3:fast             | 1M      | no     | $6.00 / $30.00 ($0.60) | Fast-tier sibling of kimi-k3. Fallback.                                                                                |\n| deepseek-v4.1-flash:fast | 1M      | yes    | $0.60 / $2.40 ($0.012) | Fast-tier sibling; vision per modalities (the non-fast id has no modalities field) — not live-probed. Fallback.      |\n| glm-5.3-flash:fast       | 1M      | yes    | $0.15 / $0.50 ($0.03)  | Fast-tier sibling; vision per modalities (the non-fast id has no modalities field) — not live-probed. Fallback.      |\n| minimax-m3:fast          | 1M      | yes    | $0.60 / $2.40 ($0.12)  | Fast-tier sibling of minimax-m3, same vision claim. Fallback.                                                          |\n\nContext window shown is the documented context_length of 1,048,576 tokens\nfor every model (from the live, unauthenticated GET /v1/models response,\n2026-09-28). Inco's catalog does not publish a separate per-request output\ntoken ceiling, so defaultMaxOutputTokens uses a conservative generic\ndefault (4,096) rather","hierarchy":{"lvl0":"Getting Started","lvl1":"Inco Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"c36795cb365b6ebed5016357ea5dc90642ea9a95760a01dced0fb601305cdf0e","title":"Inco Provider Guide","url":"/docs/getting-started/providers/inco#inco-provider-guide","content":"Inco is a Tier-2 catalog provider: OpenAI-wire-compatible with no\nbehavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/inco.json) rather than hand-written code. That\nfile is the source of truth for everything on this page.\n\nVerification status: this entry is docs- and roster-verified, not yet\nlive-verified. Every field below was built from Inco's own published\ndocumentation (https://platform.inco.ai/docs) and an unauthenticated\nGET https://api.inco.ai/v1/models — no API key was used or obtained.\nCapabilities that can only be proven with a working key (tool calling,\nstructured output, vision replies, the exact 401/404/429 error bodies) are\nleft conservative (false) or undocumented until a live capability sweep\nruns. See Live verification below.","hierarchy":{"lvl0":"Getting Started","lvl1":"Inco Provider Guide","lvl2":"Inco Provider Guide","lvl3":""}},
 {"objectID":"6e8cd876e7d09a13939dc02b0a97c644367f684943bfbf984edef9d5e9e93c22","title":"Key Facts","url":"/docs/getting-started/providers/inco#key-facts","content":"Provider id: inco\nProtocol: OpenAI-compatible (POST /v1/chat/completions); the vendor's\n  docs also describe an Anthropic-SDK-shaped path at the host root\n  (https://api.inco.ai), not used by this entry\nBase URL: https://api.inco.ai/v1\nDefault model: glm-5.3 (editorial pick — Inco's docs name no\n  recommended/default model; chosen for its documented reasoning_effort\n  support and mid-range price among the roster)\nModels in catalog: 10\nStreaming: supported (SSE, per vendor docs)\nTool calling: not documented by the vendor — left false until proven\nStructured output: not documented by the vendor — left false until\n  proven\nEmbeddings: not documented\nBilling: no free tier — strictly prepaid, pay-per-token; a zero balance\n  returns HTTP 402 (credit_balance_exhausted) until you top up\nKey format: sk-inco-...\nAccess: currently waitlist-gated — sign-up is not self-serve","hierarchy":{"lvl0":"Getting Started","lvl1":"Inco Provider Guide","lvl2":"Key Facts","lvl3":""}},
@@ -6164,6 +6251,17 @@
 {"objectID":"de358abc64cad163c1666dce7b06fc5f7b3637b9568e420ceb9269a526929d54","title":"Running your own Laya server","url":"/docs/getting-started/providers/laya#running-your-own-laya-server","content":"Laya's example server exposes the same /predict route. Point\nLAYA_BASE_URL at it:","hierarchy":{"lvl0":"Getting Started","lvl1":"Laya Provider Guide","lvl2":"Running your own Laya server","lvl3":""}},
 {"objectID":"e0dd67e8f79c7801d3e199dcd765a559f64a9d65d43cf1611026725a8ae1ee82","title":"Troubleshooting","url":"/docs/getting-started/providers/laya#troubleshooting","content":"Laya requires a base URL — set LAYA_BASE_URL, or pass\n  credentials.laya.baseURL. There is no default endpoint.\nAuthentication failed — the proxy rejected the key. Check it in the\n  LiteLLM Dashboard, including its Allowed Routes. The provider instance does\n  not retry after a rejection.\nA 403 with error code: 1010 — Cloudflare in front of your proxy blocked\n  the client by its signature. Node's fetch is accepted; a proxy or agent that\n  rewrites the user agent may not be.\nexceeded the provider's token limit — the state is larger than Laya\n  reads. Shorten it, or configure TypeSafe for long inputs.\nBuilt-in routing never uses Laya — a TypeSafe key is also set and takes\n  precedence, or Laya has no base URL.","hierarchy":{"lvl0":"Getting Started","lvl1":"Laya Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
 {"objectID":"fb160b657869a262fd7735599ce2c2ffd49423f4a0f7c43f4ef5ee74aa4dcde5","title":"See also","url":"/docs/getting-started/providers/laya#see-also","content":"The decide inference type\nTypeSafe (Jev) Provider Guide\nXOR Provider Guide\nLaya on GitHub","hierarchy":{"lvl0":"Getting Started","lvl1":"Laya Provider Guide","lvl2":"See also","lvl3":""}},
+{"objectID":"df16212357acdf1cff3460cb04e276abe1c702cc845767f49a4bc0cd2a92a763","title":"Lemonfox AI Provider Guide","url":"/docs/getting-started/providers/lemonfox-ai","content":"Lemonfox AI Provider Guide\n\nLemonfox AI is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/lemonfox-ai.json) rather than hand-written code.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's GET https://api.lemonfox.ai/v1/models needs a\nkey (it answers HTTP 401 without one), so the two model ids come from the\nvendor's public chat API page, https://www.lemonfox.ai/apis/chat (retrieved\n2026-09-29), and the roster has not been checked. No account was created and no\nAPI key was used to build it. evidence.liveMatrix is null until someone\nruns the live capability matrix with a real key (see\nVerification status below).\n\nKey Facts\nProvider id: lemonfox-ai (alias lemonfox)\nProtocol: OpenAI-compatible (/chat/completions) — the chat API page says\n  \"Our OpenAI-compatible API takes a list of messages as input and provides an\n  AI-generated (assistant) message as output.\"\nBase URL: https://api.lemonfox.ai/v1\nDefault model: deepseek-v4-flash\nModels in catalog: 2, taken from the model table of\n  https://www.lemonfox.ai/apis/chat\nStreaming: supported — the page's stream parameter reads \"incremental\n  message updates are transmitted as server-sent events with data-only\n  messages.\"\nTool calling: not declared (false) — the page's API Parameters section\n  lists messages, model, max_tokens, stop, stream,\n  frequency_penalty, presence_penalty, temperature and top_p\nTools while streaming: not declared (false)\nStructured output: not declared (false), same parameter list as above\nStructured output + tools together: not declared (false) — no combined\n  probe was possible without credentials\nEmbeddings: not declared\nThinking: not declared\nBilling: free-with-card is the growth queue's classification, one of the\n  three values the catalog schema allows; see Billing below for the\n  vendor's own wording\nKey format: none declared\n\nQuick Start\nGet an API key\nVisit: https://lemonfox.ai/signup (the \"Get started\" and \"Start Your Free Trial\" links on https://www.lemonfox.ai/apis/chat both point to /signup); sign-up was not attempted while building this entry\nCreate an API key at https://lemonfox.ai/apis/keys — https://www.lemonfox.ai/apis/chat links \"create an API key\" to that page, and the API's 401 reply says \"You can obtain an API key from https://lemonfox.ai/apis/keys.\"\nBilling as the vendor states it: see Billing below\nSet LEMONFOX_AI_API_KEY in your .env file\nConfigure\nUse it\n\nPer-request credentials:\n\nBilling\n\nWhat the vendor's public pages show (retrieved 2026-09-29):\nhttps://www.lemonfox.ai/ — \"Try our APIs for 1 month for free.\"\nhttps://www.lemonfox.ai/apis/chat — \"First month for free!\" and \"Start Your\n  Free Trial\"\nhttps://www.lemonfox.ai/terms — Lemon Fox GmbH uses Paddle as its Merchant of\n  Record and offers \"subscription-based pricing and usage-based pricing\"\n\nThe entry records free-with-card, the growth queue's classification, because\nthe catalog schema has no unknown value; it is not a vendor statement of\nsign-up terms.\n\nModels\n\n| Model                  | Context | Price / 1M tokens | Notes                                                                                                                            |\n| ---------------------- | ------- | ----------------- | -------------------------------------------------------------------------------------------------------------------------------- |\n| deepseek-v4-flash ⭐ | 1M      | $0.50             | NeuroLink default. Vendor: \"DeepSeek V4 Flash is our default model — fast, cost-effective, and suitable for most tasks.\"         |\n| mimo-v2.5-pro        | —       | $1.25             | NeuroLink fallback. Vendor: \"MiMo V2.5 Pro is a powerful model from Xiaomi, recommended for complex reasoning and coding tasks.\" |\n\nModel ids, the 1M context figure and the two prices come from the model table\non https://www.lemonfox.ai/apis/chat (retrieved 2026-09-29), whose price column\nis headed \"Price / 1M tokens\". The table's context text for deepseek-v4-flash\nreads \"Supports a 1M token context window.\"; the catalog stores it as 1,000,000\n(NeuroLink's decimal reading of \"1M\"). mimo-v2.5-pro has no context window set.\nThe page also shows the model parameter as \"Specify the model ID to be used.\nDefault: deepseek-v4-flash. Also supported: mimo-v2.5-pro.\"\n\nmodels.defaultContextWindow (32,768) and models.defaultMaxOutputTokens\n(4,096) are placeholders the vendor does not publish, for model ids outside the\ncatalog; the page's max_tokens parameter reads \"integer, optional, default:\ninfinity\". pricingPerMTok is unset on both models because the catalog field\ntakes separate input and output figures and the table has the one \"Price / 1M\ntokens\" column.\n\nEach model's vision flag is false in the catalog, a placeholder for a\nboolean the schema requires; it is not a vendor statement. Each model's\nstatus is production, a value the schema requires.\n\nDeprecated models: a second table on the same page, under the heading\n\"Deprecated","hierarchy":{"lvl0":"Getting Started","lvl1":"Lemonfox AI Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"3fca5359ef393150cf2b043c562fa6d28cdd3d17be9b09b089efaf425beb7ef6","title":"Lemonfox AI Provider Guide","url":"/docs/getting-started/providers/lemonfox-ai#lemonfox-ai-provider-guide","content":"Lemonfox AI is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/lemonfox-ai.json) rather than hand-written code.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's GET https://api.lemonfox.ai/v1/models needs a\nkey (it answers HTTP 401 without one), so the two model ids come from the\nvendor's public chat API page, https://www.lemonfox.ai/apis/chat (retrieved\n2026-09-29), and the roster has not been checked. No account was created and no\nAPI key was used to build it. evidence.liveMatrix is null until someone\nruns the live capability matrix with a real key (see\nVerification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"Lemonfox AI Provider Guide","lvl2":"Lemonfox AI Provider Guide","lvl3":""}},
+{"objectID":"58c275813c578b02ad4927ca1b96bc8b37a07c75c8829608a8098f8fd53256f1","title":"Key Facts","url":"/docs/getting-started/providers/lemonfox-ai#key-facts","content":"Provider id: lemonfox-ai (alias lemonfox)\nProtocol: OpenAI-compatible (/chat/completions) — the chat API page says\n  \"Our OpenAI-compatible API takes a list of messages as input and provides an\n  AI-generated (assistant) message as output.\"\nBase URL: https://api.lemonfox.ai/v1\nDefault model: deepseek-v4-flash\nModels in catalog: 2, taken from the model table of\n  https://www.lemonfox.ai/apis/chat\nStreaming: supported — the page's stream parameter reads \"incremental\n  message updates are transmitted as server-sent events with data-only\n  messages.\"\nTool calling: not declared (false) — the page's API Parameters section\n  lists messages, model, max_tokens, stop, stream,\n  frequency_penalty, presence_penalty, temperature and top_p\nTools while streaming: not declared (false)\nStructured output: not declared (false), same parameter list as above\nStructured output + tools together: not declared (false) — no combined\n  probe was possible without credentials\nEmbeddings: not declared\nThinking: not declared\nBilling: free-with-card is the growth queue's classification, one of the\n  three values the catalog schema allows; see Billing below for the\n  vendor's own wording\nKey format: none declared","hierarchy":{"lvl0":"Getting Started","lvl1":"Lemonfox AI Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"4a6e50f20c9ab14f3f84de83aa5acb0d8c8fbee631d26f72e17042b4d667b62e","title":"1. Get an API key","url":"/docs/getting-started/providers/lemonfox-ai#1-get-an-api-key","content":"Visit: https://lemonfox.ai/signup (the \"Get started\" and \"Start Your Free Trial\" links on https://www.lemonfox.ai/apis/chat both point to /signup); sign-up was not attempted while building this entry\nCreate an API key at https://lemonfox.ai/apis/keys — https://www.lemonfox.ai/apis/chat links \"create an API key\" to that page, and the API's 401 reply says \"You can obtain an API key from https://lemonfox.ai/apis/keys.\"\nBilling as the vendor states it: see Billing below\nSet LEMONFOX_AI_API_KEY in your .env file","hierarchy":{"lvl0":"Getting Started","lvl1":"Lemonfox AI Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"6312deae60aebe813dff2267a13a89df11e2307c99a4a7dc17941ad55e128a74","title":"3. Use it","url":"/docs/getting-started/providers/lemonfox-ai#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Lemonfox AI Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"2620d8bb4d0a22bb0f08b2748ac78680f8cc74789fd8db7331b331688457424a","title":"CLI","url":"/docs/getting-started/providers/lemonfox-ai#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider lemonfox-ai\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"lemonfox-ai\",\n  credentials: { lemonfoxAi: { apiKey: process.env.LEMONFOXAIAPI_KEY } },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"Lemonfox AI Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"9c3861b11e1b91a948b3595988aa33a77f489785871d1e161ad6c20790fcdcfb","title":"Billing","url":"/docs/getting-started/providers/lemonfox-ai#billing","content":"What the vendor's public pages show (retrieved 2026-09-29):\nhttps://www.lemonfox.ai/ — \"Try our APIs for 1 month for free.\"\nhttps://www.lemonfox.ai/apis/chat — \"First month for free!\" and \"Start Your\n  Free Trial\"\nhttps://www.lemonfox.ai/terms — Lemon Fox GmbH uses Paddle as its Merchant of\n  Record and offers \"subscription-based pricing and usage-based pricing\"\n\nThe entry records free-with-card, the growth queue's classification, because\nthe catalog schema has no unknown value; it is not a vendor statement of\nsign-up terms.","hierarchy":{"lvl0":"Getting Started","lvl1":"Lemonfox AI Provider Guide","lvl2":"Billing","lvl3":""}},
+{"objectID":"f461bb87777d24b84e928f9e55f3899158f1d1c2bbeac86dd48ad50fe407c7a8","title":"Models","url":"/docs/getting-started/providers/lemonfox-ai#models","content":"| Model                  | Context | Price / 1M tokens | Notes                                                                                                                            |\n| ---------------------- | ------- | ----------------- | -------------------------------------------------------------------------------------------------------------------------------- |\n| deepseek-v4-flash ⭐ | 1M      | $0.50             | NeuroLink default. Vendor: \"DeepSeek V4 Flash is our default model — fast, cost-effective, and suitable for most tasks.\"         |\n| mimo-v2.5-pro        | —       | $1.25             | NeuroLink fallback. Vendor: \"MiMo V2.5 Pro is a powerful model from Xiaomi, recommended for complex reasoning and coding tasks.\" |\n\nModel ids, the 1M context figure and the two prices come from the model table\non https://www.lemonfox.ai/apis/chat (retrieved 2026-09-29), whose price column\nis headed \"Price / 1M tokens\". The table's context text for deepseek-v4-flash\nreads \"Supports a 1M token context window.\"; the catalog stores it as 1,000,000\n(NeuroLink's decimal reading of \"1M\"). mimo-v2.5-pro has no context window set.\nThe page also shows the model parameter as \"Specify the model ID to be used.\nDefault: deepseek-v4-flash. Also supported: mimo-v2.5-pro.\"\n\nmodels.defaultContextWindow (32,768) and models.defaultMaxOutputTokens\n(4,096) are placeholders the vendor does not publish, for model ids outside the\ncatalog; the page's max_tokens parameter reads \"integer, optional, default:\ninfinity\". pricingPerMTok is unset on both models because the catalog field\ntakes separate input and output figures and the table has the one \"Price / 1M\ntokens\" column.\n\nEach model's vision flag is false in the catalog, a placeholder for a\nboolean the schema requires; it is not a vendor statement. Each model's\nstatus is production, a value the schema requires.\n\nDeprecated models: a second table on the same page, under the heading\n\"Deprecated models\", lists llama-8b-chat (\"Deprecated. L","hierarchy":{"lvl0":"Getting Started","lvl1":"Lemonfox AI Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"00c82c24543bdf3fb8fa8ba81a2d1ab847bed9de7ff1642ac4c24e810a85b7a2","title":"Verification status","url":"/docs/getting-started/providers/lemonfox-ai#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog currently records for Lemonfox AI — docs-verified only, not\nlive-verified:\n\n| Probe                     | Result                                                                                                                                                                                                                                                                                                                             |\n| ------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                    | unauthenticated GET /v1/models, HTTP 401, 2026-09-29 — no key used; model ids taken from https://www.lemonfox.ai/apis/chat; roster not verified                                                                                                                                                                                  |\n| Billing                   | public pages listed under Billing, 2026-09-29 — no signup performed                                                                                                                                                                                                                                                    |\n| Auth-failure shape        | unauthenticated GETs of /v1/models, /v1/chat/completions and /v1 each answered HTTP 401 with the same JSON body (status 401, error.type invalid_request_error, error.code null, error.message beginning \"You didn't provide an API key.\"); errorRules holds one rule, for status 401; no POST request was sent |\n| Tools / structured output | not d","hierarchy":{"lvl0":"Getting Started","lvl1":"Lemonfox AI Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"267ea3afca90723b750a1a533d801f0c7cb4c626173032ad3610cb148f47e6db","title":"Troubleshooting","url":"/docs/getting-started/providers/lemonfox-ai#troubleshooting","content":"| Symptom                                          | Cause                                                                                                                                                                                              | Fix                                                                                                                    |\n| ------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------- |\n| HTTP 401                                         | The vendor's reply to a request with no key: \"You didn't provide an API key. You need to provide your API key in an Authorization header using Bearer auth (i.e. Authorization: Bearer YOUR_KEY).\" | Set LEMONFOX_AI_API_KEY; keys are at https://lemonfox.ai/apis/keys                                                   |\n| llama-8b-chat or llama-70b-chat set as model | The chat API page lists these ids under \"Deprecated models\"                                                                                                                                        | The page says \"use deepseek-v4-flash instead\" for llama-8b-chat and \"use mimo-v2.5-pro instead\" for llama-70b-chat |","hierarchy":{"lvl0":"Getting Started","lvl1":"Lemonfox AI Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
+{"objectID":"7bdf81e725417bdbc7045936fd4598d6231836ee3d1c88d1999be9c8a95315be","title":"See also","url":"/docs/getting-started/providers/lemonfox-ai#see-also","content":"Provider setup overview\nProvider guides\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Lemonfox AI Provider Guide","lvl2":"See also","lvl3":""}},
 {"objectID":"667a3f17b65166ba28882ee85abdf158b10830f8810551f1866cc1e4fb0387c9","title":"Lilac Provider Guide","url":"/docs/getting-started/providers/lilac","content":"Lilac Provider Guide\n\nLilac is a Tier-2 catalog provider: OpenAI-wire-compatible with no\nbehavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/lilac.json) rather than hand-written code. That\nfile is the source of truth for everything on this page.\n\nVerification status: this entry is docs- and roster-verified, not\nyet live-verified. Every model id, context window, output ceiling and\nprice below comes from an unauthenticated GET /v1/models call (no API\nkey used) cross-checked against Lilac's published docs. No request that\nneeds a key — chat completions, streaming, tool calls, structured output —\nhas been probed end to end. Capability flags reflect only what the docs\nstate; run the live matrix (see\nTier-2 onboarding)\nbefore trusting this provider in production.\n\nKey Facts\nProvider id: lilac\nProtocol: OpenAI-compatible (/chat/completions) — docs.getlilac.com\n  states Lilac \"provides an OpenAI-compatible API. If you're already using\n  the OpenAI SDK, you only need to change the base URL and API key.\"\nBase URL: https://api.getlilac.com/v1\nDefault model: moonshotai/kimi-k2.6\nModels in catalog: 4\nStreaming: documented (stream: true, SSE); not live-probed\nTool calling: documented (\"Function definitions with automatic\n  argument extraction,\" supported for all four current models); not\n  live-probed\nStructured output: documented (response_format with json_object\n  or json_schema, supported for all four current models); not\n  live-probed. Gemma 4 carries a documented caveat: combining its reasoning\n  parser with enable_thinking: false \"can silently disable xgrammar-backed\n  structured output.\"\nTools + structured output together: not declared — no combined probe\n  was possible without a key\nEmbeddings: explicitly documented as not supported (along with\n  audio, fine-tuning, the Assistants API, Batch API and file uploads)\nBilling: no free tier — prepaid credit only (Stripe checkout, as\n  little as $5), no minimum spend or contract once funded\nKey format: none documented\nRate limits: 200 requests/minute per organization; excess requests\n  may get HTTP 429 with a Retry-After header\n\nQuick Start\nGet an API key\nVisit: https://console.getlilac.com and sign up with your email or a Google account\nCreate an organization, then go to API Keys in the dashboard and create a new key — it is shown only once, so copy it immediately\nGo to Billing, click Add Credits and complete the Stripe checkout (as little as $5.00) — a positive credit balance is required before you can make any API request; there is no free tier or free credits\nSet LILAC_API_KEY in your .env file\n\nNew-model requests and enterprise monthly-invoicing setup both go through contact@getlilac.com.\nConfigure\nUse it\n\nPer-request credentials work as they do for every provider:\n\nModels\n\n| Model                     | Context | Vision | $/M in · out                 | Notes                                                                                                                                                                                       |\n| ------------------------- | ------- | ------ | ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| moonshotai/kimi-k2.6 ⭐ | 262K    | yes    | $0.70 / $3.50 (cached $0.16) | Default — the model used in every code sample on Lilac's own quickstart and chat-completions docs, including its vision example. Roster-verified only, not capability-probed.               |\n| minimaxai/minimax-m3    | 1M      | yes    | $0.28 / $1.10 (cached $0.05) | Largest context in the roster; native multimodal 428B MoE reasoning model. Fallback.                                                                                                        |\n| zai-org/glm-5.2         | 512K    | no     | $0.90 / $3.00 (cached $0.17) | Only non-vision model on the roster; its reasoning_effort also works as a plain top-level field, not only inside chat_template_kwargs. Fallback.                                        |\n| google/gemma-4-31b-it   | 256K    | yes    | $0.11 / $0.35                | Cheapest model; does not list structured_outputs in its supported parameters (only response_format), and docs flag a structured-output caveat under enable_thinking: false. Fallback. |\n\nContext window and output-ceiling numbers are from GET /v1/models\n(unauthenticated, 2026-09-28); the API reports the per-model\nmax_completion_tokens equal to that same model's context length, so treat\nit as an upper bound rather than a separately proven output cap. Pricing is\ncross-checked against https://docs.getlilac.com/inference/models (same\ndate) and matches exactly.\n\nFallback order when the default is unavailable: minimaxai/minimax-m3 →\nzai-org/glm-5.2 → google/gemma-4-31b-it.\n\nVerification status\n\nTier-2 onboarding requires evidence before a provider is accepted, and\npnpm run veri","hierarchy":{"lvl0":"Getting Started","lvl1":"Lilac Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"6841db5bba9a83d0ecbe60f8407ae263867d208e162245663d22d202c2cb5c6e","title":"Lilac Provider Guide","url":"/docs/getting-started/providers/lilac#lilac-provider-guide","content":"Lilac is a Tier-2 catalog provider: OpenAI-wire-compatible with no\nbehavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/lilac.json) rather than hand-written code. That\nfile is the source of truth for everything on this page.\n\nVerification status: this entry is docs- and roster-verified, not\nyet live-verified. Every model id, context window, output ceiling and\nprice below comes from an unauthenticated GET /v1/models call (no API\nkey used) cross-checked against Lilac's published docs. No request that\nneeds a key — chat completions, streaming, tool calls, structured output —\nhas been probed end to end. Capability flags reflect only what the docs\nstate; run the live matrix (see\nTier-2 onboarding)\nbefore trusting this provider in production.","hierarchy":{"lvl0":"Getting Started","lvl1":"Lilac Provider Guide","lvl2":"Lilac Provider Guide","lvl3":""}},
 {"objectID":"d4c6e475ca68608c38f117c0e72e3e00e3180e895a9891092099432bebdfae77","title":"Key Facts","url":"/docs/getting-started/providers/lilac#key-facts","content":"Provider id: lilac\nProtocol: OpenAI-compatible (/chat/completions) — docs.getlilac.com\n  states Lilac \"provides an OpenAI-compatible API. If you're already using\n  the OpenAI SDK, you only need to change the base URL and API key.\"\nBase URL: https://api.getlilac.com/v1\nDefault model: moonshotai/kimi-k2.6\nModels in catalog: 4\nStreaming: documented (stream: true, SSE); not live-probed\nTool calling: documented (\"Function definitions with automatic\n  argument extraction,\" supported for all four current models); not\n  live-probed\nStructured output: documented (response_format with json_object\n  or json_schema, supported for all four current models); not\n  live-probed. Gemma 4 carries a documented caveat: combining its reasoning\n  parser with enable_thinking: false \"can silently disable xgrammar-backed\n  structured output.\"\nTools + structured output together: not declared — no combined probe\n  was possible without a key\nEmbeddings: explicitly documented as not supported (along with\n  audio, fine-tuning, the Assistants API, Batch API and file uploads)\nBilling: no free tier — prepaid credit only (Stripe checkout, as\n  little as $5), no minimum spend or contract once funded\nKey format: none documented\nRate limits: 200 requests/minute per organization; excess requests\n  may get HTTP 429 with a Retry-After header","hierarchy":{"lvl0":"Getting Started","lvl1":"Lilac Provider Guide","lvl2":"Key Facts","lvl3":""}},
@@ -6322,6 +6420,18 @@
 {"objectID":"effd805db1c992eccfff874a394a8ece66ab29e1a2663effffea816e7941f238","title":"Verification status","url":"/docs/getting-started/providers/mancer#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog records for Mancer:\n\n| Probe                 | Result                                                                                                                                                                                                                                                                                     |\n| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| Roster                | authenticated GET /oai/v1/models; full response retained as evidence/mancer-roster-authenticated.json in the campaign scratchpad and every catalog price/limit machine-checked against it (Mancer re-prices — gpt-oss-120b input moved 0.024 → 0.022 within the day), HTTP 200, 2026-09-03 |\n| Auth rejection        | HTTP 401, 2026-09-03                                                                                                                                                                                                                                                                       |\n| Live capability sweep | 2026-09-03 — 18-probe harness on the free model mytholite: roster, chat, maxcompletiontokens, system role, content parts, sampling params, SSE stream (usage chunk + [DONE]), jsonschema (valid JSON matching schema) and jsonobject                                                   |","hierarchy":{"lvl0":"Getting Started","lvl1":"Mancer Provider Guide","lvl2":"Verification status","lvl3":""}},
 {"objectID":"2fc031ba3f49f74856ae83f42061c95e272c18e9152fdf018a27c507bf27db17","title":"Troubleshooting","url":"/docs/getting-started/providers/mancer#troubleshooting","content":"| Symptom                  | Cause                               | Fix                                                                                                                        |\n| ------------------------ | ----------------------------------- | -------------------------------------------------------------------------------------------------------------------------- |\n| Invalid Mancer API key | MANCER_API_KEY unset or wrong     | Check the key at https://mancer.tech/dashboard                                                                             |\n| Model not found          | The roster changed since 2026-09-03 | Pick a current id; catalog providers retire models without notice                                                          |\n| Tools silently absent    | Mancer declares tools: false      | Use a tool-capable provider for agentic work — see provider capabilities |","hierarchy":{"lvl0":"Getting Started","lvl1":"Mancer Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
 {"objectID":"03eaed001f1323b249a03ebf54953bb3af9079f0e3956ebcbe2e34bef4766534","title":"See also","url":"/docs/getting-started/providers/mancer#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Mancer Provider Guide","lvl2":"See also","lvl3":""}},
+{"objectID":"c4a43493271fa327c125e88509481c384839d0c2ba39da4e65edf736aebee4a2","title":"Meta Model API Provider Guide","url":"/docs/getting-started/providers/meta-model-api","content":"Meta Model API Provider Guide\n\nMeta Model API is a Tier-2 catalog provider: OpenAI-wire-compatible, so its\nentire integration is one JSON file\n(src/lib/providers/catalog/meta-model-api.json) rather than hand-written\ncode. That file is the source of truth for everything on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's GET https://api.meta.ai/v1/models needs a key\n(an unauthenticated GET on 2026-09-29 answered HTTP 401), so the model ids\ncome from Meta's public docs and the roster has not been checked. No account\nwas created and no API key was used to build this entry.\nevidence.liveMatrix is null until someone runs the live capability matrix\nwith a real key (see Verification status below).\n\nKey Facts\nProvider id: meta-model-api\nProtocol: OpenAI-compatible (/chat/completions). The\n  Chat Completions page\n  says \"The endpoint is OpenAI-compatible\" and \"The response matches the OpenAI\n  chat completions shape.\"\nBase URL: https://api.meta.ai/v1 — the Base URL in the At a glance\n  block of the Overview, and the\n  base_url value in the Chat Completions page's OpenAI SDK examples\nDefault model: muse-spark-1.3 — the Models page\n  says \"muse-spark-1.3 is the default model in the code examples throughout\n  these docs.\"\nModels in catalog: 5 — the five rows of the \"Available Muse Spark models\"\n  table on the Models page (three Standard tier, two Contributor tier)\nStreaming: supported — the Chat Completions page says \"Set stream=True to\n  enable streaming:\"\nTool calling: true — the\n  Tool calling page says \"tool calling\n  is fully supported there too\" for Chat Completions\nTools while streaming: true — the Tool calling page says \"Tool-call\n  arguments stream: With stream: true, the model streams arguments\n  incrementally.\"\nStructured output: true — the\n  Structured output page says\n  \"Set responseformat to type: \"jsonschema\" and provide your schema in the\n  json_schema field.\"\nStructured output + tools together: false — no combined probe was run\n  without credentials\nEmbeddings: false\nThinking: false — the entry sets no thinking-level request parameter.\n  The Chat Completions page\n  says \"Muse Spark always reasons, so reasoning_effort: \"none\" returns HTTP\n  400.\" The Reasoning page documents the\n  request parameter: \"On Chat Completions, use the top-level reasoning_effort\n  parameter.\"\nBilling: schema value no-free-tier, a placeholder; see\n  Billing below\nKey format: LLM|{id}|{secret} — the\n  Error handling page lists\n  Malformed API key (not in LLM|{id}|{secret} format) as a cause of HTTP 401;\n  the entry's apiKeyFormat is ^LLM\\|.+\\|.+$\n\nQuick Start\nGet an API key\nVisit: https://dev.meta.ai/ — the page carries a \"Start building\" button whose link target is /api/auth/login\nCreate an API key: the Authentication page (https://dev.meta.ai/docs/authentication) lists the steps \"Log in and open the API keys tab.\", \"Click Create API key, give it a descriptive name, and click Create.\" and \"Copy the key right away. You only see it once.\"\nAuthentication is a Bearer token: the Authentication page says \"Pass the key as a Bearer token in the Authorization header:\", and the Error handling page (https://dev.meta.ai/docs/error-handling) lists Malformed API key (not in LLM|{id}|{secret} format) as a cause of HTTP 401\nBilling as the vendor states it: the Pricing page (https://dev.meta.ai/docs/pricing-rate-limits) says \"You pay only for what you use.\" and the Authentication and billing page (https://dev.meta.ai/docs/muse-code/auth) says \"Meta Model API billing is usage-based: you're billed for the tokens your requests consume.\"\nSet META_MODEL_API_API_KEY in your .env file (the vendor's examples read MODEL_API_KEY, which NeuroLink does not)\nConfigure\nUse it\n\nPer-request credentials use the same call shape as the other catalog providers:\n\nBilling\n\nThe Pricing page (https://dev.meta.ai/docs/pricing-rate-limits) says \"You pay\nonly for what you use.\" and lists these prices per 1M tokens:\n\n| Tier        | Cached input | Input | Output |\n| ----------- | ------------ | ----- | ------ |\n| Standard    | $0.15        | $1.25 | $4.25  |\n| Contributor | $0.002       | $0.10 | $0.20  |\n\nThe Authentication and billing page (https://dev.meta.ai/docs/muse-code/auth)\nsays \"Meta Model API billing is usage-based: you're billed for the tokens your\nrequests consume.\" and lists two steps for a team admin: \"Add a payment method.\"\nand \"Create an API key.\" The Pricing page's Muse Voice Transcribe paragraph says\n\"ZDR is priced at parity with Standard, and platform free-tier credits apply.\"\n\nThe entry records the schema value no-free-tier as a placeholder: the schema\nhas no unknown value, and the value is not a vendor statement.\n\nRate limits on the Pricing page: Standard tier 3,000 requests per minute and\n4,000,000 tokens per minute; Contributor tier 100 requests per minute and\n3,000,000 tokens per minute. The page says \"Limits apply per team, not per API\nkey.\"\n\nModels\n\n| Model                        | Tier      ","hierarchy":{"lvl0":"Getting Started","lvl1":"Meta Model API Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"00bea98432dfe235c69a768b7d4818ed9060bef5d4428d7e48cf3c06a75a9f50","title":"Meta Model API Provider Guide","url":"/docs/getting-started/providers/meta-model-api#meta-model-api-provider-guide","content":"Meta Model API is a Tier-2 catalog provider: OpenAI-wire-compatible, so its\nentire integration is one JSON file\n(src/lib/providers/catalog/meta-model-api.json) rather than hand-written\ncode. That file is the source of truth for everything on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's GET https://api.meta.ai/v1/models needs a key\n(an unauthenticated GET on 2026-09-29 answered HTTP 401), so the model ids\ncome from Meta's public docs and the roster has not been checked. No account\nwas created and no API key was used to build this entry.\nevidence.liveMatrix is null until someone runs the live capability matrix\nwith a real key (see Verification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"Meta Model API Provider Guide","lvl2":"Meta Model API Provider Guide","lvl3":""}},
+{"objectID":"95d53345e325157b1a204e08dbe66c0d6145f987a1bf2e84cc67de04ee9854cb","title":"Key Facts","url":"/docs/getting-started/providers/meta-model-api#key-facts","content":"Provider id: meta-model-api\nProtocol: OpenAI-compatible (/chat/completions). The\n  Chat Completions page\n  says \"The endpoint is OpenAI-compatible\" and \"The response matches the OpenAI\n  chat completions shape.\"\nBase URL: https://api.meta.ai/v1 — the Base URL in the At a glance\n  block of the Overview, and the\n  base_url value in the Chat Completions page's OpenAI SDK examples\nDefault model: muse-spark-1.3 — the Models page\n  says \"muse-spark-1.3 is the default model in the code examples throughout\n  these docs.\"\nModels in catalog: 5 — the five rows of the \"Available Muse Spark models\"\n  table on the Models page (three Standard tier, two Contributor tier)\nStreaming: supported — the Chat Completions page says \"Set stream=True to\n  enable streaming:\"\nTool calling: true — the\n  Tool calling page says \"tool calling\n  is fully supported there too\" for Chat Completions\nTools while streaming: true — the Tool calling page says \"Tool-call\n  arguments stream: With stream: true, the model streams arguments\n  incrementally.\"\nStructured output: true — the\n  Structured output page says\n  \"Set responseformat to type: \"jsonschema\" and provide your schema in the\n  json_schema field.\"\nStructured output + tools together: false — no combined probe was run\n  without credentials\nEmbeddings: false\nThinking: false — the entry sets no thinking-level request parameter.\n  The Chat Completions page\n  says \"Muse Spark always reasons, so reasoning_effort: \"none\" returns HTTP\n  400.\" The Reasoning page documents the\n  request parameter: \"On Chat Completions, use the top-level reasoning_effort\n  parameter.\"\nBilling: schema value no-free-tier, a placeholder; see\n  Billing below\nKey format: LLM|{id}|{secret} — the\n  Error handling page lists\n  Malformed API key (not in LLM|{id}|{secret} format) as a cause of HTTP 401;\n  the entry's apiKeyFormat is ^LLM\\|.+\\|.+$","hierarchy":{"lvl0":"Getting Started","lvl1":"Meta Model API Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"315e803ffce5048a28914d91a5062a409fe51656821fc655bbdece566579ea00","title":"1. Get an API key","url":"/docs/getting-started/providers/meta-model-api#1-get-an-api-key","content":"Visit: https://dev.meta.ai/ — the page carries a \"Start building\" button whose link target is /api/auth/login\nCreate an API key: the Authentication page (https://dev.meta.ai/docs/authentication) lists the steps \"Log in and open the API keys tab.\", \"Click Create API key, give it a descriptive name, and click Create.\" and \"Copy the key right away. You only see it once.\"\nAuthentication is a Bearer token: the Authentication page says \"Pass the key as a Bearer token in the Authorization header:\", and the Error handling page (https://dev.meta.ai/docs/error-handling) lists Malformed API key (not in LLM|{id}|{secret} format) as a cause of HTTP 401\nBilling as the vendor states it: the Pricing page (https://dev.meta.ai/docs/pricing-rate-limits) says \"You pay only for what you use.\" and the Authentication and billing page (https://dev.meta.ai/docs/muse-code/auth) says \"Meta Model API billing is usage-based: you're billed for the tokens your requests consume.\"\nSet META_MODEL_API_API_KEY in your .env file (the vendor's examples read MODEL_API_KEY, which NeuroLink does not)","hierarchy":{"lvl0":"Getting Started","lvl1":"Meta Model API Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"c8c9eedeb453afab0b73251ad9b516f371050a99aee9aac5ce3d31d437c99436","title":"3. Use it","url":"/docs/getting-started/providers/meta-model-api#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Meta Model API Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"420f0fb6f1c3b0d859d631959b2c39ef9428079c0abfdd844cc56354f1aa7052","title":"CLI","url":"/docs/getting-started/providers/meta-model-api#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider meta-model-api\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"meta-model-api\",\n  credentials: { metaModelApi: { apiKey: process.env.METAMODELAPIAPIKEY } },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"Meta Model API Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"3507b30e84648a93da1ebc1ff585a9495349f46ebd2625f164244167bd5a495c","title":"Billing","url":"/docs/getting-started/providers/meta-model-api#billing","content":"The Pricing page (https://dev.meta.ai/docs/pricing-rate-limits) says \"You pay\nonly for what you use.\" and lists these prices per 1M tokens:\n\n| Tier        | Cached input | Input | Output |\n| ----------- | ------------ | ----- | ------ |\n| Standard    | $0.15        | $1.25 | $4.25  |\n| Contributor | $0.002       | $0.10 | $0.20  |\n\nThe Authentication and billing page (https://dev.meta.ai/docs/muse-code/auth)\nsays \"Meta Model API billing is usage-based: you're billed for the tokens your\nrequests consume.\" and lists two steps for a team admin: \"Add a payment method.\"\nand \"Create an API key.\" The Pricing page's Muse Voice Transcribe paragraph says\n\"ZDR is priced at parity with Standard, and platform free-tier credits apply.\"\n\nThe entry records the schema value no-free-tier as a placeholder: the schema\nhas no unknown value, and the value is not a vendor statement.\n\nRate limits on the Pricing page: Standard tier 3,000 requests per minute and\n4,000,000 tokens per minute; Contributor tier 100 requests per minute and\n3,000,000 tokens per minute. The page says \"Limits apply per team, not per API\nkey.\"","hierarchy":{"lvl0":"Getting Started","lvl1":"Meta Model API Provider Guide","lvl2":"Billing","lvl3":""}},
+{"objectID":"c95a365d6b982149ef118df3b4ef55833d45c34fb2e2808f80a984706bb7063f","title":"Models","url":"/docs/getting-started/providers/meta-model-api#models","content":"| Model                        | Tier        | Context   | Vision | $/M in · out (cached input) | Notes                                                                                                                                                                                                                                 |\n| ---------------------------- | ----------- | --------- | ------ | --------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| muse-spark-1.3 ⭐          | Standard    | 1,048,576 | yes    | $1.25 / $4.25 ($0.15)       | NeuroLink default. Models page: \"the latest version, tuned for agentic workflows (multi-step tool, browser, and long-horizon tasks) with improved coding over 1.2.\" and \"Recommended for new work.\" Output figure 131072 (see below). |\n| muse-spark-1.2             | Standard    | 1,048,576 | yes    | $1.25 / $4.25 ($0.15)       | NeuroLink fallback. Models page: \"the previous version.\" Home page card: \"A coding-optimized model purpose-built for agentic workflows.\"                                                                                              |\n| muse-spark-1.1             | Standard    | 1,048,576 | yes    | $1.25 / $4.25 ($0.15)       | NeuroLink fallback. Models page: \"the original version.\" Home page card: \"Built for agentic workflows, coding, computer use & multimodal perception.\"                                                                                 |\n| muse-spark-1.3-contributor | Contributor | 1,048,576 | yes    | $0.10 / $0.20 ($0.002)      | Models page: the Contributor variant \"trades a lower price for permission to train on your prompts and completions\". Not in models.fallbacks.                                                                                       |\n| muse-spark-1.2-contributor | ","hierarchy":{"lvl0":"Getting Started","lvl1":"Meta Model API Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"8b6857a6ee4c13957648460707c3733024f9a8a20000fab97cf74c9427282b92","title":"Vendor-documented request parameters","url":"/docs/getting-started/providers/meta-model-api#vendor-documented-request-parameters","content":"These are statements on Meta's own pages about request fields on Chat\nCompletions. They are quoted as written and were not exercised against the API.\n\n| Request                       | What the vendor page says                                                                                                                                                                              |\n| ----------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| tool_choice other than auto | Tool calling page: \"tool_choice must be \"auto\": Only \"auto\" (the default) is supported on both Chat Completions and the Responses API; \"none\", \"required\", and named function choices return HTTP 400\" |\n| reasoning_effort: \"none\"    | Chat Completions page: \"Muse Spark always reasons, so reasoning_effort: \"none\" returns HTTP 400.\"                                                                                                      |\n| n above 1                   | Chat Completions page: \"Only n=1 is supported; values greater than 1 return HTTP 400.\"                                                                                                                 |\n| stop                        | Chat Completions page, OpenAI compatibility notes table: \"Not supported on reasoning models. This matches OpenAI's behavior on o3 and o4-mini.\"                                                        |\n| logprobs: true              | Chat Completions page: \"logprobs: true returns HTTP 400\"                                                                                                                                               |\n| max_tokens                  | Chat Completions page, Parameters table: \"The deprecated alias max_tokens is still accepted.\"                                                                                         ","hierarchy":{"lvl0":"Getting Started","lvl1":"Meta Model API Provider Guide","lvl2":"Vendor-documented request parameters","lvl3":""}},
+{"objectID":"9d28dc29f4b76724c759418fc318ffd6e7d76baf7d66f145bbb94c69d8ef9ccb","title":"Verification status","url":"/docs/getting-started/providers/meta-model-api#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the catalog\ncurrently records for Meta Model API — docs-verified only, not\nlive-verified:\n\n| Probe                     | Result                                                                                                                                                                                                                                                                                                                                               |\n| ------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                    | unauthenticated GET https://api.meta.ai/v1/models answered HTTP 401 on 2026-09-29, so model ids are taken from the Models page; the roster has not been checked. The List models reference shows GET /models called with a Bearer key            |\n| Auth-failure shape        | unauthenticated GET https://api.meta.ai/v1/models: HTTP 401, content-type: application/json, body {\"error\":{\"code\":\"invalid_api_key\",\"message\":\"Unauthorized\",\"param\":null,\"type\":\"authentication_error\"}}. An unauthenticated GET https://api.meta.ai/v1/chat/completions answered HTTP 401 with the same body and the header allow: POST |\n| Billing                   | public Pricing and Authentication and billing pages, quoted in Billing above; no signup performed, 2026-09-29                                                                                                                                                                                                                            |\n| Tools / structured output | ","hierarchy":{"lvl0":"Getting Started","lvl1":"Meta Model API Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"7535e1c5a2f2e7e3b8715a49eb5996cb6daa7fa578be2df578a188401d927339","title":"Troubleshooting","url":"/docs/getting-started/providers/meta-model-api#troubleshooting","content":"The Vendor statement column quotes the vendor's own pages.\n\n| Symptom                             | Vendor statement                                                                                                                                                    | NeuroLink note                                                                      |\n| ----------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------- |\n| HTTP 401                            | Error handling page: \"The API key was missing, invalid, or revoked.\" Its fix line: \"Send a valid Authorization: Bearer $MODELAPIKEY header.\"                      | NeuroLink reads META_MODEL_API_API_KEY; the vendor's examples use MODEL_API_KEY |\n| HTTP 402                            | Error handling page: \"The request cannot be completed due to a billing issue.\" Its fix line: \"Check account status and billing details in the Model API dashboard.\" | The example body's error.code is billing_not_configured                         |\n| HTTP 404, code model_not_found    | Quickstart page: \"404 modelnotfound: use a valid model ID such as muse-spark-1.3 (the default in these examples) or muse-spark-1.1 exactly.\"                      | The five catalog ids are listed in Models                                |\n| HTTP 429                            | Error handling page: \"Your team has exceeded the rate limit.\" Its fix line: \"Implement exponential backoff with jitter.\"                                            | Limits are listed in Billing                                            |\n| HTTP 504 on a non-streaming request | Chat Completions page: \"a non-streaming request that runs too long returns HTTP 504\". Error handling page fix line: \"Stream the response by setting stream: true.\"  | Use neurolink.strea","hierarchy":{"lvl0":"Getting Started","lvl1":"Meta Model API Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
+{"objectID":"57b46158b04483758b7c94c97896457fd9ad976c83728009bec8293bdbfd0ce0","title":"See also","url":"/docs/getting-started/providers/meta-model-api#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility\nMeta Model API pages opened for this entry: Home, Overview, Quickstart, Authentication, Models, Pricing and rate limits, Chat Completions, Tool calling, Structured output, Reasoning, Image understanding, Coding agents, Authentication and billing, Error handling","hierarchy":{"lvl0":"Getting Started","lvl1":"Meta Model API Provider Guide","lvl2":"See also","lvl3":""}},
 {"objectID":"cfedd052236b6720db1dd71055fa4ee7af6e05619e746a639565b7c931107f9d","title":"MiniMax Provider Guide","url":"/docs/getting-started/providers/minimax","content":"MiniMax Provider Guide\n\nMiniMax is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/minimax.json) rather than hand-written code.\nThat file is the source of truth for everything on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. MiniMax's GET https://api.minimax.io/v1/models answers\nHTTP 401 without a key, so the model ids come from MiniMax's public docs and\nthe roster has not been checked. No account was created and no API key was\nused to build the entry. evidence.liveMatrix is null until someone runs\nthe live capability matrix with a real key (see\nVerification status below).\n\nKey Facts\nProvider id: minimax\nProtocol: OpenAI-compatible (/chat/completions) — MiniMax's own\n  OpenAI SDK page\n  sets OPENAI_BASE_URL=https://api.minimax.io/v1 and calls\n  client.chat.completions.create\nBase URL: https://api.minimax.io/v1\nDefault model: MiniMax-M3\nModels in catalog: 9 — the nine ids in the Supported Models table of the\n  OpenAI SDK page, which are also the model enum of the\n  Chat Completions reference\n  (roster not verified)\nStreaming: supported — the Chat Completions reference documents stream\n  (\"Whether to use streaming output, defaults to false. When set to true,\n  the response will be returned in chunks.\")\nTool calling: model-dependent — the Chat Completions reference lists\n  tools (\"Function tools are supported.\") and returns tool_calls; none of it\n  was exercised. With model-dependent, NeuroLink falls back to its\n  model-registry default per model\nTools while streaming: not declared (false)\nStructured output: not declared (false)\nStructured output + tools together: not declared (false) — no combined\n  probe was run without credentials\nEmbeddings: not declared\nThinking: the catalog capabilities.thinking is false, and the entry\n  sets none of MiniMax's thinking, reasoning_effort or reasoning_split\n  request parameters. The Chat Completions reference says of MiniMax-M3:\n  \"adaptive thinking is on by default\", and of MiniMax-M3.1-Flash-Preview:\n  \"always thinks\". The OpenAI SDK page says of max_tokens: \"Thinking tokens\n  count toward it too, so a value that is too small yields\n  finish_reason: \"length\" with an empty content.\"\nVision: true for MiniMax-M3 and MiniMax-M3.1-Flash-Preview, where\n  the OpenAI SDK page says \"Image and video inputs are supported by\n  MiniMax-M3.1-Flash-Preview and MiniMax-M3 through OpenAI-compatible\n  message content parts\"\nBilling: free-tier — the schema's closest value, see\n  Billing below\nKey format: not validated by NeuroLink (apiKeyFormat: null)\n\nQuick Start\nGet an API key\nVisit: https://platform.minimax.io/login?source=platform_docs and register or log in (https://platform.minimax.io/docs/guides/quickstart-preparation)\nPay-as-you-go: open API Keys > Create new secret key at https://platform.minimax.io/user-center/basic-information/interface-key and copy the API Key (https://platform.minimax.io/docs/guides/quickstart-preparation)\nToken Plan: view your Subscription Key at https://platform.minimax.io/user-center/payment/token-plan. MiniMax-M3.1-Flash-Preview is stated as available only through Token Plan and MiniMax Code for now, and the Subscription Key is stated as not interchangeable with pay-as-you-go API Keys (https://platform.minimax.io/docs/api-reference/text-openai-api, https://platform.minimax.io/docs/token-plan/intro)\nBilling as the vendor words it: \"Pay-as-you-go uses standard Open Platform API Keys and consumes your account balance by actual usage.\" (https://platform.minimax.io/docs/guides/pricing-paygo) and \"New users without subscription can try the free quota from Pay-as-you-go\" (https://platform.minimax.io/docs/solutions/eigent, a tutorial dated January 23, 2026)\nSet MINIMAX_API_KEY in your .env file\nConfigure\nUse it\n\nPer-request credentials work as they do for every provider:\n\nBilling\n\nMiniMax's pay-as-you-go pricing page\n(https://platform.minimax.io/docs/guides/pricing-paygo) says: \"Pay-as-you-go\nuses standard Open Platform API Keys and consumes your account balance by\nactual usage.\" The Prerequisites page\n(https://platform.minimax.io/docs/guides/quickstart-preparation) says: \"For\npay-as-you-go, access Billing/Balance to top up if needed.\" MiniMax's Eigent\ntutorial (https://platform.minimax.io/docs/solutions/eigent, dated January 23,\n2026 and written for MiniMax M2.1) says: \"New users without subscription can\ntry the free quota from Pay-as-you-go\".\n\nThe catalog schema has no unknown billing value, so the entry records\nfree-tier as the closest value. It is not a MiniMax statement of terms.\n\nModels\n\n| Model                        | Context   | Max output | Vision | $/M in · out (cache read) | Notes                                                                                                                                                                                                                                                                                                        ","hierarchy":{"lvl0":"Getting Started","lvl1":"MiniMax Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"c80bae4d2aa2e431395c1a10e67a7316aa8a3121754ef8e9cd4aa263c70eee94","title":"MiniMax Provider Guide","url":"/docs/getting-started/providers/minimax#minimax-provider-guide","content":"MiniMax is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/minimax.json) rather than hand-written code.\nThat file is the source of truth for everything on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. MiniMax's GET https://api.minimax.io/v1/models answers\nHTTP 401 without a key, so the model ids come from MiniMax's public docs and\nthe roster has not been checked. No account was created and no API key was\nused to build the entry. evidence.liveMatrix is null until someone runs\nthe live capability matrix with a real key (see\nVerification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"MiniMax Provider Guide","lvl2":"MiniMax Provider Guide","lvl3":""}},
 {"objectID":"63c9d5774bf861eba46f5de81ec4a3d9f0ea889f2933f7233cba2806bdc8899c","title":"Key Facts","url":"/docs/getting-started/providers/minimax#key-facts","content":"Provider id: minimax\nProtocol: OpenAI-compatible (/chat/completions) — MiniMax's own\n  OpenAI SDK page\n  sets OPENAI_BASE_URL=https://api.minimax.io/v1 and calls\n  client.chat.completions.create\nBase URL: https://api.minimax.io/v1\nDefault model: MiniMax-M3\nModels in catalog: 9 — the nine ids in the Supported Models table of the\n  OpenAI SDK page, which are also the model enum of the\n  Chat Completions reference\n  (roster not verified)\nStreaming: supported — the Chat Completions reference documents stream\n  (\"Whether to use streaming output, defaults to false. When set to true,\n  the response will be returned in chunks.\")\nTool calling: model-dependent — the Chat Completions reference lists\n  tools (\"Function tools are supported.\") and returns tool_calls; none of it\n  was exercised. With model-dependent, NeuroLink falls back to its\n  model-registry default per model\nTools while streaming: not declared (false)\nStructured output: not declared (false)\nStructured output + tools together: not declared (false) — no combined\n  probe was run without credentials\nEmbeddings: not declared\nThinking: the catalog capabilities.thinking is false, and the entry\n  sets none of MiniMax's thinking, reasoning_effort or reasoning_split\n  request parameters. The Chat Completions reference says of MiniMax-M3:\n  \"adaptive thinking is on by default\", and of MiniMax-M3.1-Flash-Preview:\n  \"always thinks\". The OpenAI SDK page says of max_tokens: \"Thinking tokens\n  count toward it too, so a value that is too small yields\n  finish_reason: \"length\" with an empty content.\"\nVision: true for MiniMax-M3 and MiniMax-M3.1-Flash-Preview, where\n  the OpenAI SDK page says \"Image and video inputs are supported by\n  MiniMax-M3.1-Flash-Preview and MiniMax-M3 through OpenAI-compatible\n  message content parts\"\nBilling: free-tier — the schema's closest value, see\n  Billing below\nKey format: not validated by NeuroLink (apiKeyFormat: null)","hierarchy":{"lvl0":"Getting Started","lvl1":"MiniMax Provider Guide","lvl2":"Key Facts","lvl3":""}},
@@ -6381,6 +6491,17 @@
 {"objectID":"3b83698318a22fb8015c4fba394fcaa63da10ed1e961d12897dbf67f6410dccd","title":"Verification status","url":"/docs/getting-started/providers/moark#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog currently records for Moark — deliberately thinner than a\nlive-verified entry, since no key was created:\n\n| Probe                 | Result                                                                                                                                                                                                                                                     |\n| --------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                | unauthenticated GET https://moark.com/v1/models, HTTP 200, 222 models, 2026-09-28                                                                                                                                                                        |\n| Docs cross-check      | docs/openapi/v1, docs/products/apis, docs/products/apis/texts/text-generation, docs/products/apis/texts/function-calling, docs/billing/purchase — all fetched 2026-09-28, confirm OpenAI-compatible wire shape, Bearer auth, and prepaid billing |\n| Auth rejection        | not probed — would require a POST request, out of scope for credential-free onboarding                                                                                                                                                                 |\n| Live capability sweep | not run — no key was created or used                                                                                                                                                                                                                   |\n\nBecause no authenticated or POST request was made, capabilities.tools is\nrecorded as \"model","hierarchy":{"lvl0":"Getting Started","lvl1":"Moark Provider Guide","lvl2":"Verification status","lvl3":""}},
 {"objectID":"45340dcdd3f1c711d874178072b930664a8298ac66f0e7005cf30fdca7363fbf","title":"Troubleshooting","url":"/docs/getting-started/providers/moark#troubleshooting","content":"| Symptom                                    | Cause                                                                                          | Fix                                                                                                                                       |\n| ------------------------------------------ | ---------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |\n| Requests fail with an auth-shaped error    | MOARK_API_KEY unset, wrong, or the account has no funded package                             | Check the token at https://moark.com/dashboard/tokens and confirm a prepaid package is active                                             |\n| Model not found                            | The roster changed since 2026-09-28                                                            | Pick a current id from the unauthenticated GET https://moark.com/v1/models roster                                                       |\n| Structured output not returned as expected | This entry doesn't send response_format — Moark only documents guided_json/guided_choice | Not currently wired through the generic OpenAI-compat client; treat structuredOutput as unsupported until a live probe proves otherwise |\n| Tool calls silently ignored                | Function calling is documented as model-dependent, not universal                               | Confirm the chosen model is one of Moark's documented Function-Calling models before relying on tools                                   |","hierarchy":{"lvl0":"Getting Started","lvl1":"Moark Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
 {"objectID":"e716f0196dff4264a6cf90d4f76e00e364f8a9ad052afed344476189ee5c8e5d","title":"See also","url":"/docs/getting-started/providers/moark#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration, and the live-verification steps this entry still needs\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Moark Provider Guide","lvl2":"See also","lvl3":""}},
+{"objectID":"b9c84595c5ca87aa713e3f84ba91e83e969bd6e3727a070ffefe3c235769a36b","title":"ModelScope Provider Guide","url":"/docs/getting-started/providers/modelscope","content":"ModelScope Provider Guide\n\nModelScope is a Tier-2 catalog provider: OpenAI-compatible, defined by one\nJSON file (src/lib/providers/catalog/modelscope.json) rather than\nhand-written code. This page is written from that file.\n\nVerification status: this entry is docs- and roster-verified, not yet\nlive-verified. The fields below come from ModelScope's own public\ndocumentation and unauthenticated GET requests — no account was created and\nno API key was used to build it. evidence.liveMatrix is null until\nsomeone runs the live capability matrix with a real key (see\nVerification status below).\n\nThe docs text on this page was read on 2026-09-29 from the raw document files\nthat the docs site loads, because the rendered pages at modelscope.cn/docs\nare a JavaScript shell. The English build is\nhttps://resouces.modelscope.cn/document/docdata/2026-9-28_15-50-EN/dist/model-service/API-Inference/intro/intro_EN.md\n(and the matching limits, codewhale, magicube, accounts/registration and\naccounts/token files); the Chinese build is under\nhttps://resouces.modelscope.cn/document/docdata/2026-9-28_15-49-CN/dist/index.json\n(its model-service/API-Inference/intro/intro_CN.md sibling holds the Chinese intro page).\nQuotes below are English unless a Chinese build is named.\n\nKey Facts\nProvider id: modelscope\nProtocol: OpenAI-compatible (/chat/completions) — the intro page\n  (docs) says\n  \"ModelScope's API-Inference currently provides OpenAI API-compatible\n  interfaces for large language models.\"\nBase URL: https://api-inference.modelscope.cn/v1\nDefault model: Qwen/Qwen3.5-35B-A3B\nModels in catalog: 12 (selected from the 35-model roster)\nStreaming: supported — the intro page's chat example calls\n  client.chat.completions.create(...) with stream=True\nVision: vision: true on Qwen/Qwen3.5-35B-A3B — the intro page's\n  \"Vision Models\" example calls that id with an image_url content part. It is\n  also true on the other three Qwen3.5 ids (the intro page says \"integrated\n  models like Qwen3.5 that support vision\") and on Qwen/Qwen3.8-27B,\n  Qwen/Qwen3.8-Flash-Next, MiniMax/MiniMax-M3 and\n  stepfun-ai/Step-3.7-Flash (ModelScope's public model API lists their task\n  as image-text-to-text); see Models\nTool calling: false\nTools while streaming: false\nStructured output: false\nStructured output + tools together: false — no combined request was\n  sent, because no API key was used\nEmbeddings: false\nThinking: true — ModelScope's Codewhale integration page\n  (https://modelscope.cn/docs/ecosystem-integrations/api-usage/codewhale) says\n  \"Qwen and GLM series models support reasoning_content streaming output\"\nBilling: free-tier — see Billing below\n\nQuick Start\nGet an API key\nVisit: https://modelscope.cn/home and register or log in with the \"Log in/Register\" button in the top right corner (https://modelscope.cn/docs/accounts/registration)\nBind an Alibaba Cloud account and complete real-name verification: \"After account registration, you must bind your Alibaba Cloud account and complete real-name verification before using API-Inference.\" (https://modelscope.cn/docs/model-service/API-Inference/intro; binding steps: https://modelscope.cn/docs/accounts/aliyun-binding-and-authorization)\nCreate an access token at https://modelscope.cn/my/myaccesstoken; the token guide (https://modelscope.cn/docs/accounts/token) has you specify a validity period, \"Long-term use\" or \"Short-term use\"\nFree for registered users: \"API-Inference is provided free of charge to registered ModelScope users.\" (intro page); the limits page (https://modelscope.cn/docs/model-service/API-Inference/limits) states that API Inference \"implements certain limits on usage quotas and concurrency\"\nSet MODELSCOPE_API_KEY in your .env file\nConfigure\nUse it\n\nPer-request credentials use the same shape as the other catalog providers:\n\nBilling\n\nThe entry records free-tier. What the vendor's pages say:\nIntro page: \"API-Inference is provided free of charge to registered\n  ModelScope users.\"\nLimits page (https://modelscope.cn/docs/model-service/API-Inference/limits):\n  \"The free inference API is powered by Alibaba Cloud computing resources.\"\n  and \"Your ModelScope account must first be linked to an Alibaba Cloud\n  account.\"\nLimits page: \"Please do not use it for online tasks requiring high\n  concurrency or SLA guarantees\". It continues \"If you have commercial usage\n  requirements, we recommend using APIs from commercial platforms.\"\nLimits page: \"The allowed concurrency for different models will be\n  dynamically rate-limited according to platform load\"\nLimits page: \"API Inference calls can be redeemed by magicubes.\" with three\n  cost tiers, \"Lightweight models: ~0.5 Magicubes per call\", \"Standard models:\n  ~1 Magicube per call\" and \"Flagship models: ~2 Magicubes per call\".\nMagicube page (https://modelscope.cn/docs/magicube/intro): Magicubes can be\n  redeemed for \"Civision inference, Civision training, and API Inference\n  services\". Its earning table lists \"Daily Login Bonus\" (action \"Sign in\",\n  reward \"200 Magicubes","hierarchy":{"lvl0":"Getting Started","lvl1":"ModelScope Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"a76727f4d9ed7c8b1b19b3d4bedbc417f7f606be9f29c4c49e951bf578209534","title":"ModelScope Provider Guide","url":"/docs/getting-started/providers/modelscope#modelscope-provider-guide","content":"ModelScope is a Tier-2 catalog provider: OpenAI-compatible, defined by one\nJSON file (src/lib/providers/catalog/modelscope.json) rather than\nhand-written code. This page is written from that file.\n\nVerification status: this entry is docs- and roster-verified, not yet\nlive-verified. The fields below come from ModelScope's own public\ndocumentation and unauthenticated GET requests — no account was created and\nno API key was used to build it. evidence.liveMatrix is null until\nsomeone runs the live capability matrix with a real key (see\nVerification status below).\n\nThe docs text on this page was read on 2026-09-29 from the raw document files\nthat the docs site loads, because the rendered pages at modelscope.cn/docs\nare a JavaScript shell. The English build is\nhttps://resouces.modelscope.cn/document/docdata/2026-9-28_15-50-EN/dist/model-service/API-Inference/intro/intro_EN.md\n(and the matching limits, codewhale, magicube, accounts/registration and\naccounts/token files); the Chinese build is under\nhttps://resouces.modelscope.cn/document/docdata/2026-9-28_15-49-CN/dist/index.json\n(its model-service/API-Inference/intro/intro_CN.md sibling holds the Chinese intro page).\nQuotes below are English unless a Chinese build is named.","hierarchy":{"lvl0":"Getting Started","lvl1":"ModelScope Provider Guide","lvl2":"ModelScope Provider Guide","lvl3":""}},
+{"objectID":"055c98a5bcb8b11eefac030fa8b97cbfd82ad75548f3f2c3295d88a72cce2b73","title":"Key Facts","url":"/docs/getting-started/providers/modelscope#key-facts","content":"Provider id: modelscope\nProtocol: OpenAI-compatible (/chat/completions) — the intro page\n  (docs) says\n  \"ModelScope's API-Inference currently provides OpenAI API-compatible\n  interfaces for large language models.\"\nBase URL: https://api-inference.modelscope.cn/v1\nDefault model: Qwen/Qwen3.5-35B-A3B\nModels in catalog: 12 (selected from the 35-model roster)\nStreaming: supported — the intro page's chat example calls\n  client.chat.completions.create(...) with stream=True\nVision: vision: true on Qwen/Qwen3.5-35B-A3B — the intro page's\n  \"Vision Models\" example calls that id with an image_url content part. It is\n  also true on the other three Qwen3.5 ids (the intro page says \"integrated\n  models like Qwen3.5 that support vision\") and on Qwen/Qwen3.8-27B,\n  Qwen/Qwen3.8-Flash-Next, MiniMax/MiniMax-M3 and\n  stepfun-ai/Step-3.7-Flash (ModelScope's public model API lists their task\n  as image-text-to-text); see Models\nTool calling: false\nTools while streaming: false\nStructured output: false\nStructured output + tools together: false — no combined request was\n  sent, because no API key was used\nEmbeddings: false\nThinking: true — ModelScope's Codewhale integration page\n  (https://modelscope.cn/docs/ecosystem-integrations/api-usage/codewhale) says\n  \"Qwen and GLM series models support reasoning_content streaming output\"\nBilling: free-tier — see Billing below","hierarchy":{"lvl0":"Getting Started","lvl1":"ModelScope Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"ee5d12538bf347a8658e1e6aac368ab79e2d2c8079328a72d6e626d8090beb4c","title":"1. Get an API key","url":"/docs/getting-started/providers/modelscope#1-get-an-api-key","content":"Visit: https://modelscope.cn/home and register or log in with the \"Log in/Register\" button in the top right corner (https://modelscope.cn/docs/accounts/registration)\nBind an Alibaba Cloud account and complete real-name verification: \"After account registration, you must bind your Alibaba Cloud account and complete real-name verification before using API-Inference.\" (https://modelscope.cn/docs/model-service/API-Inference/intro; binding steps: https://modelscope.cn/docs/accounts/aliyun-binding-and-authorization)\nCreate an access token at https://modelscope.cn/my/myaccesstoken; the token guide (https://modelscope.cn/docs/accounts/token) has you specify a validity period, \"Long-term use\" or \"Short-term use\"\nFree for registered users: \"API-Inference is provided free of charge to registered ModelScope users.\" (intro page); the limits page (https://modelscope.cn/docs/model-service/API-Inference/limits) states that API Inference \"implements certain limits on usage quotas and concurrency\"\nSet MODELSCOPE_API_KEY in your .env file","hierarchy":{"lvl0":"Getting Started","lvl1":"ModelScope Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"baa463440ebdbac32d23093a8cc7782c99bc1cab59cc33c7692aade58e61d218","title":"3. Use it","url":"/docs/getting-started/providers/modelscope#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"ModelScope Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"edc50a003617537c6a2af428227530371572ba06fd99bc95b95661138b408864","title":"CLI","url":"/docs/getting-started/providers/modelscope#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider modelscope\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"modelscope\",\n  credentials: { modelscope: { apiKey: process.env.MODELSCOPEAPIKEY } },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"ModelScope Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"4f097009563bf07d438a4273449dca4ae278f598f0fa9c8f9764bfc25b23c812","title":"Billing","url":"/docs/getting-started/providers/modelscope#billing","content":"The entry records free-tier. What the vendor's pages say:\nIntro page: \"API-Inference is provided free of charge to registered\n  ModelScope users.\"\nLimits page (https://modelscope.cn/docs/model-service/API-Inference/limits):\n  \"The free inference API is powered by Alibaba Cloud computing resources.\"\n  and \"Your ModelScope account must first be linked to an Alibaba Cloud\n  account.\"\nLimits page: \"Please do not use it for online tasks requiring high\n  concurrency or SLA guarantees\". It continues \"If you have commercial usage\n  requirements, we recommend using APIs from commercial platforms.\"\nLimits page: \"The allowed concurrency for different models will be\n  dynamically rate-limited according to platform load\"\nLimits page: \"API Inference calls can be redeemed by magicubes.\" with three\n  cost tiers, \"Lightweight models: ~0.5 Magicubes per call\", \"Standard models:\n  ~1 Magicube per call\" and \"Flagship models: ~2 Magicubes per call\".\nMagicube page (https://modelscope.cn/docs/magicube/intro): Magicubes can be\n  redeemed for \"Civision inference, Civision training, and API Inference\n  services\". Its earning table lists \"Daily Login Bonus\" (action \"Sign in\",\n  reward \"200 Magicubes/day\") and \"Account Linking Bonus\" (action \"Link\n  Alibaba Cloud account\", reward \"50 Magicubes/day\").","hierarchy":{"lvl0":"Getting Started","lvl1":"ModelScope Provider Guide","lvl2":"Billing","lvl3":""}},
+{"objectID":"9978dafd5dbea20d24fc79ba3caec8d67637b0199beaf0dcc8beb30c6adde6ba","title":"Models","url":"/docs/getting-started/providers/modelscope#models","content":"| Model                                   | vision | Notes                                                                                                                                                                                                                                                                                                       |\n| --------------------------------------- | -------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Qwen/Qwen3.5-35B-A3B ⭐               | true     | NeuroLink default. The id used in the intro page's chat, Anthropic-compatible and Vision Models examples; models.visionModel.                                                                                                                                                                             |\n| Qwen/Qwen3.5-27B                      | true     | Fallback. Named in the Chinese intro page's Responses API example and in the LangChain integration page's examples (https://modelscope.cn/docs/ecosystem-integrations/api-usage/langchain). The intro page says \"integrated models like Qwen3.5 that support vision\". Model API task: image-text-to-text. |\n| deepseek-ai/DeepSeek-V4-Pro-0813      | false    | Fallback. Listed on the roster. Model API task: text-generation.                                                                                                                                                                                                                                          |\n| ZhipuAI/GLM-5.2                       | false    | Fallback. Listed on the roster. Model API task: text-generation.                                                                                                                 ","hierarchy":{"lvl0":"Getting Started","lvl1":"ModelScope Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"1c28229396186265d27c1ace13c50f9c5a6be7cebc0f4a0b85e02d535d522d86","title":"Verification status","url":"/docs/getting-started/providers/modelscope#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog currently records for ModelScope — docs- and roster-verified, not\nlive-verified:\n\n| Probe                 | Result                                                                                                                                                                                                                                                                                                                                                                                                                                                          |\n| --------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                | unauthenticated GET /v1/models, HTTP 200, 35 models, 2026-09-29 — no key used                                                                                                                                                                                                                                                                                                                                                                                 |\n| Billing               | intro page: \"API-Inference is provided free of charge to registered ModelScope users.\"; limits page: \"free of charge\", 2026-09-29                                                                                                                                                                                             ","hierarchy":{"lvl0":"Getting Started","lvl1":"ModelScope Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"660b4b3a2e9be2323181c59b50632daf5db57245b7e9dbf878560d12537f6676","title":"Troubleshooting","url":"/docs/getting-started/providers/modelscope#troubleshooting","content":"Each row is a statement from a ModelScope page, quoted from the docs text\ndescribed at the top of this page.\n\n| Situation                                 | What the vendor says                                                                                                                                                                                      | Page   |\n| ----------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------ |\n| Newly registered account                  | \"After account registration, you must bind your Alibaba Cloud account and complete real-name verification before using API-Inference.\"                                                                    | intro  |\n| A model id is no longer served            | \"Over time, as new models are launched, older models may be deprecated and no longer supported. To ensure your API calls work properly, please configure a currently supported model ID.\"                 | intro  |\n| A model id is no longer served            | \"As new models are released, older models may gradually be removed from API Inference.\"                                                                                                                   | limits |\n| Reasoning models                          | \"Please refer to the API-Inference sample code on the model page as the authoritative source\", \"especially for reasoning models, as their calling methods may have subtle differences from standard LLMs\" | intro  |\n| Concurrency or quota limits               | \"The allowed concurrency for different models will be dynamically rate-limited according to platform load\"                                                                                                | limits |\n| Production traffic with concurrency needs | \"Please do not use it for onlin","hierarchy":{"lvl0":"Getting Started","lvl1":"ModelScope Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
+{"objectID":"169116cb9b2ee240e882a92bf369cdf5d05375eddbd4a17031dcf3560fb871ac","title":"See also","url":"/docs/getting-started/providers/modelscope#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"ModelScope Provider Guide","lvl2":"See also","lvl3":""}},
 {"objectID":"4edd22b292b861e3eb9d1984a7e4202708507d8241b41fa76af5909c78caf17a","title":"Moonshot AI (Kimi) Provider Guide","url":"/docs/getting-started/providers/moonshot-ai","content":"Moonshot AI (Kimi) Provider Guide\n\nMoonshot AI's Kimi API is a Tier-2 catalog provider: OpenAI-wire-compatible,\nso its integration is one JSON file (src/lib/providers/catalog/moonshot-ai.json)\nrather than hand-written code. That file is the source of truth for everything\non this page. The one behavioural setting it carries is the\nreplayReasoningContent quirk, explained under Key Facts.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's GET /v1/models needs a key (an unauthenticated\nGET answers HTTP 401), so the model ids come from the vendor's public docs at\nhttps://platform.kimi.ai/docs/models and the roster has not been checked.\nevidence.liveMatrix is null until someone runs the live capability matrix\nwith a real key (see Verification status below). No\naccount was created and no API key was used to build this entry.\n\nKey Facts\nProvider id: moonshot-ai (aliases moonshot, kimi)\nProtocol: OpenAI-compatible (/chat/completions). The\n  Quickstart says: \"Kimi API lets you\n  interact with Kimi models and is compatible with both the OpenAI and Anthropic\n  API formats.\"\nBase URL: https://api.moonshot.ai/v1. The docs and console live on\n  platform.kimi.ai and call the product the Kimi API; the API host is\n  api.moonshot.ai.\nDefault model: kimi-k3\nModels in catalog: 4 — the models the\n  Model List names under \"Multi-modal\n  Model\". The chat request schema in the vendor's\n  OpenAPI file names the same four\n  ids.\nStreaming: supported. The\n  streaming guide\n  documents stream responses as Content-Type: text/event-stream (SSE) ending\n  with data: [DONE].\nTool calling: true — the\n  tool-calls guide\n  documents the tools parameter and tool_calls (including tool calls in\n  streaming output), and the\n  Kimi K3,\n  Kimi K2.7 Code\n  and Kimi K2.6\n  pages describe tool calling for their models. The\n  parameter reference says\n  kimi-k3 supports tool_choice values auto / none / required, while\n  kimi-k2.6 and kimi-k2.7-code \"return an error if it is passed\" for\n  required.\nTools while streaming: true, per the tool-calls guide section \"Handle\n  tool_calls in Streaming Output\"\nStructured output: supported — response_format accepts json_object and\n  json_schema\n  (response_format guide).\n  For kimi-k2.6 the same guide states: \"kimi-k2.6 occasionally behaves\n  unstably with complex schemas; for example, $ref may return a Markdown code\n  block, oneOf may be ignored, and partial=true may output fields outside the\n  schema.\"\nStructured output + tools together: not declared (false) — no combined\n  probe was run without credentials\nEmbeddings: not declared\nThinking: not declared (false) on this entry. The vendor's\n  Thinking Models\n  page documents reasoning_content, reasoning_effort for kimi-k3 and the\n  thinking parameter for kimi-k2.6; the generic catalog provider does not\n  send reasoning_effort or thinking, so NeuroLink's thinkingLevel is not\n  mapped to them.\nReasoning replay (quirks.replayReasoningContent: true): the Thinking\n  Models page says \"For K3, this is required in multi-turn conversations and\n  tool-call loops\", and that for kimi-k2.7-code \"you must therefore (not\n  optionally) keep the reasoning_content of historical assistant messages in\n  messages as-is\". The quirk sends the assistant turns' reasoning_content\n  back on later requests. It has not been exercised against the live API.\nBilling: no-free-tier — see Billing below\nKey format: not declared\n\nQuick Start\nGet an API key\nVisit: https://platform.kimi.ai/console/api-keys and sign in, then create and copy an API key (https://platform.kimi.ai/docs/overview describes signing in to the Kimi API Platform and creating a key under API Keys)\nCreate the key on platform.kimi.ai: the errors page states that keys issued on platform.kimi.ai are independent from keys issued on other regional Kimi platforms, and that \"Mixing keys across platforms returns 401.\" (https://platform.kimi.ai/docs/api/errors)\nTop up before use: \"To prevent abuse, you need to recharge at least $1 to start using, and when your cumulative recharge reaches $5, you will receive a $5 voucher.\" (https://platform.kimi.ai/docs/pricing/limits); the Kimi K3 page states \"Kimi K3 is a flagship model: it is unlocked after a successful top-up (minimum $1).\" (https://platform.kimi.ai/docs/guide/kimi-k3-quickstart)\nSet MOONSHOT_AI_API_KEY in your .env file (MOONSHOT_API_KEY, the variable Kimi's own docs use, is also read)\nConfigure\nUse it\n\nPer-request credentials work as they do for the other catalog providers:\n\nBilling\n\nThe Recharge and Rate Limiting\npage says: \"To prevent abuse, you need to recharge at least $1 to start using,\nand when your cumulative recharge reaches $5, you will receive a $5 voucher.\" The\nCompare with Other Kimi Products\npage describes the Kimi API Open Platform as \"pay-as-you-go billing with no\nsubscription plan\"; the Troubleshooting page repeats \"pay-as-you-go with no\nsubscription plan\". The entry records no-free-tier.\n\nThe\nTroubleshooting page also\nanswers \"C","hierarchy":{"lvl0":"Getting Started","lvl1":"Moonshot AI (Kimi) Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"2733232385d5e17ab8c37f9cf9b20f4743c02e60a05ae0b99c5a52b9dc960a50","title":"Moonshot AI (Kimi) Provider Guide","url":"/docs/getting-started/providers/moonshot-ai#moonshot-ai-kimi-provider-guide","content":"Moonshot AI's Kimi API is a Tier-2 catalog provider: OpenAI-wire-compatible,\nso its integration is one JSON file (src/lib/providers/catalog/moonshot-ai.json)\nrather than hand-written code. That file is the source of truth for everything\non this page. The one behavioural setting it carries is the\nreplayReasoningContent quirk, explained under Key Facts.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's GET /v1/models needs a key (an unauthenticated\nGET answers HTTP 401), so the model ids come from the vendor's public docs at\nhttps://platform.kimi.ai/docs/models and the roster has not been checked.\nevidence.liveMatrix is null until someone runs the live capability matrix\nwith a real key (see Verification status below). No\naccount was created and no API key was used to build this entry.","hierarchy":{"lvl0":"Getting Started","lvl1":"Moonshot AI (Kimi) Provider Guide","lvl2":"Moonshot AI (Kimi) Provider Guide","lvl3":""}},
 {"objectID":"6c9de492370c1b3bb61033e73d6c0bf044313d79545c326aa1c19ac8ab4fef49","title":"Key Facts","url":"/docs/getting-started/providers/moonshot-ai#key-facts","content":"Provider id: moonshot-ai (aliases moonshot, kimi)\nProtocol: OpenAI-compatible (/chat/completions). The\n  Quickstart says: \"Kimi API lets you\n  interact with Kimi models and is compatible with both the OpenAI and Anthropic\n  API formats.\"\nBase URL: https://api.moonshot.ai/v1. The docs and console live on\n  platform.kimi.ai and call the product the Kimi API; the API host is\n  api.moonshot.ai.\nDefault model: kimi-k3\nModels in catalog: 4 — the models the\n  Model List names under \"Multi-modal\n  Model\". The chat request schema in the vendor's\n  OpenAPI file names the same four\n  ids.\nStreaming: supported. The\n  streaming guide\n  documents stream responses as Content-Type: text/event-stream (SSE) ending\n  with data: [DONE].\nTool calling: true — the\n  tool-calls guide\n  documents the tools parameter and tool_calls (including tool calls in\n  streaming output), and the\n  Kimi K3,\n  Kimi K2.7 Code\n  and Kimi K2.6\n  pages describe tool calling for their models. The\n  parameter reference says\n  kimi-k3 supports tool_choice values auto / none / required, while\n  kimi-k2.6 and kimi-k2.7-code \"return an error if it is passed\" for\n  required.\nTools while streaming: true, per the tool-calls guide section \"Handle\n  tool_calls in Streaming Output\"\nStructured output: supported — response_format accepts json_object and\n  json_schema\n  (response_format guide).\n  For kimi-k2.6 the same guide states: \"kimi-k2.6 occasionally behaves\n  unstably with complex schemas; for example, $ref may return a Markdown code\n  block, oneOf may be ignored, and partial=true may output fields outside the\n  schema.\"\nStructured output + tools together: not declared (false) — no combined\n  probe was run without credentials\nEmbeddings: not declared\nThinking: not declared (false) on this entry. The vendor's\n  Thinking Models\n  page documents reasoning_content, reasoning_effort for kimi-k3 and the\n  thinking parameter for kimi-k2.6; the generic catalog provider does not\n  send reasoning_effort or thinking, so NeuroL","hierarchy":{"lvl0":"Getting Started","lvl1":"Moonshot AI (Kimi) Provider Guide","lvl2":"Key Facts","lvl3":""}},
@@ -6727,6 +6848,17 @@
 {"objectID":"42aa9cf24ddb1baadfd869caa4f7f24e41404184d44a78f57b4377b8dfef44cb","title":"Verification status","url":"/docs/getting-started/providers/ovhcloud#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog records for OVHcloud AI Endpoints — deliberately credential-free:\n\n| Probe                 | Result                                                                                                                                                                                                                                                                                                                  |\n| --------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                | unauthenticated GET /v1/models, HTTP 200, 2026-09-28 — 24 models returned; no key used                                                                                                                                                                                                                            |\n| Auth rejection        | not probed — would require an authenticated request, which this credential-free onboarding does not send. The errorRules entry for authentication failures is taken verbatim from OVHcloud's written docs (\"403 Forbidden: Authentication Failed\"), not from a live probe                                             |\n| Live capability sweep | not run (evidence.liveMatrix is null). capabilities.tools, .streaming, .structuredOutput and .thinking are set from OVHcloud's own getting-started guide, capabilities guide, and the gpt-oss-120b catalog card's \"Supported Features\" / \"Output Formats\" lists — not from a live request of any kind |\n\nBecause no live request was ever made, treat every capability flag here as\ndoc-asserted, not wire-proven until","hierarchy":{"lvl0":"Getting Started","lvl1":"OVHcloud AI Endpoints Provider Guide","lvl2":"Verification status","lvl3":""}},
 {"objectID":"3ee83d1cb747b6e8ba97384beb145e3da82eaf0487ba7e1e317026fe4c226499","title":"Troubleshooting","url":"/docs/getting-started/providers/ovhcloud#troubleshooting","content":"| Symptom                         | Cause                                                            | Fix                                                                                                            |\n| ------------------------------- | ---------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------- |\n| Requests fail immediately       | Project has no payment method attached (\"Discovery mode\")        | Add a payment method to the Public Cloud project in the OVHcloud manager before creating/using an access token |\n| Invalid or revoked ... token  | OVH_AI_ENDPOINTS_ACCESS_TOKEN unset, wrong, or revoked         | Check/recreate the token under AI & Machine Learning > AI Endpoints in the OVHcloud manager                    |\n| Frequent 429s                   | Authenticated limit is 400 requests/minute per project per model | Pace requests and/or request a higher limit from OVHcloud support                                              |\n| Model not found                 | The roster changed since 2026-09-28                              | Pick a current id from the unauthenticated GET /v1/models roster                                             |\n| Tool calls silently unsupported | capabilities.tools is model-dependent                          | Use a model the catalog page marks Function calling: Yes (e.g. gpt-oss-120b, not Qwen2.5-VL-72B-Instruct)  |","hierarchy":{"lvl0":"Getting Started","lvl1":"OVHcloud AI Endpoints Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
 {"objectID":"015b1be7b7a266e86eed27ae5055b285417aba0c547b038da1ea805b4a19f868","title":"See also","url":"/docs/getting-started/providers/ovhcloud#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration, and what a credentialed live-verification pass still needs to add\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"OVHcloud AI Endpoints Provider Guide","lvl2":"See also","lvl3":""}},
+{"objectID":"c4fb7d85d3b83371c444c9e165107487259d3e01a4a2601bb490209569aa66b2","title":"Parasail Provider Guide","url":"/docs/getting-started/providers/parasail","content":"Parasail Provider Guide\n\nParasail is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/parasail.json) rather than hand-written code. That\nfile is the source of truth for this page. The\nAuthentication page\nsays \"The API is fully OpenAI-compatible.\"\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. Parasail's GET https://api.parasail.io/v1/models needs a\nkey (an unauthenticated GET on 2026-09-29 answered HTTP 401), so the model ids\ncome from Parasail's public docs\n(Models page,\nretrieved 2026-09-29) and the roster has not been checked. No account was\ncreated and no API key was used to build this entry. evidence.liveMatrix is\nnull until someone runs the live capability matrix with a real key (see\nVerification status below).\n\nKey Facts\nProvider id: parasail\nProtocol: OpenAI-compatible (/chat/completions) — the\n  Authentication page\n  says \"All Parasail API requests use bearer token authentication. The API is\n  fully OpenAI-compatible.\"\nBase URL: https://api.parasail.io/v1\nDefault model: parasail-llama-33-70b-fp8 (NeuroLink default)\nModels in catalog: 12 (curated from the 33 rows of the Models page)\nStreaming: supported — the\n  Chat Completions reference\n  has a Streaming section describing stream: true with server-sent events\nTool calling: model-dependent — the\n  Tool/Function Calling guide\n  lists the serverless models that return structured tool calls in a table and\n  names other models that \"don't support the tools parameter today\"\nTools while streaming: not declared (false) — no combined request was\n  sent\nStructured output: supported — the\n  Structured Output guide\n  documents response_format with type json_schema and guided_json, and\n  lists models in a table with a \"Guided JSON / JSON Schema\" column\nStructured output + tools together: not declared (false) — no combined\n  probe was possible without credentials, so NeuroLink omits response_format\n  automatically whenever tools are attached\nEmbeddings: not declared on this catalog entry. The Chat Completions\n  reference's endpoint table lists POST /v1/embeddings, but NeuroLink's\n  generic ConfiguredOpenAICompatProvider (the class Tier-2 catalog entries\n  use) does not implement embed()/embedMany(), so this flag tracks that,\n  not the vendor's own API surface\nThinking: not declared — the entry sets no reasoning request parameter,\n  although the\n  Model-specific Notes page\n  documents model-specific thinking and reasoning controls\nBilling: recorded as no-free-tier, which is the schema placeholder\n  (the catalog schema has no unknown value), not a vendor statement of signup\n  terms — see Billing below\nKey format: none declared\n\nQuick Start\nGet an API key\nVisit: https://www.saas.parasail.io/keys — the link the Authentication page gives for getting an API key; sign-in was not attempted while building this entry\nCreate an API key and copy it when it is shown — the Authentication page steps read \"Click Create API Key.\" and \"Copy the key immediately—it's displayed only once.\"\nBilling as the vendor states it: the Pricing page says \"To use models, create API keys, and access paid platform services, add a credit card. Without a card, you can still view the platform but can't use models or API keys.\"\nSet PARASAIL_API_KEY in your .env file (the docs' examples use the environment variable PARASAIL_API_KEY)\nConfigure\nUse it\n\nPer-request credentials work as they do for other NeuroLink providers:\n\nBilling\n\nThe Pricing page\nsays \"To use models, create API keys, and access paid platform services, add a\ncredit card. Without a card, you can still view the platform but can't use\nmodels or API keys.\" The\nLimits and Quotas page\nhas a rate-limit table with a product class \"Serverless - Free\" (RPM column\n\"5\"). The catalog's billingPolicy field takes one of three values and holds\nno-free-tier here as a placeholder; it is not a vendor statement of signup\nterms.\n\nModels\n\n| Model                                    | Context   | Max output | Vision | $/M in · out (cached)  | Notes                                                                                                                                                                                                          |\n| ---------------------------------------- | --------- | ---------- | ------ | ---------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| parasail-llama-33-70b-fp8 ⭐           | 131,072   | 16,384     | no     | $0.22 / $0.50 ($0.11)  | NeuroLink default. Chat Completions guide example; Tools ✅ and Tool Choice ✅; Y under Guided JSON / JSON Schema, Regex and Choice.                                                                           |\n| parasail-llama-4-maverick-instruct-fp8 | 524,288   | 32,768     | no     | $0.35 / $1.00 ($0.17)  | Tools ✅ and Tool Choice ✅; Y under","hierarchy":{"lvl0":"Getting Started","lvl1":"Parasail Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"7bc01eb7a31258978d29ab07102c20808c857403086c38db263672738c936965","title":"Parasail Provider Guide","url":"/docs/getting-started/providers/parasail#parasail-provider-guide","content":"Parasail is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/parasail.json) rather than hand-written code. That\nfile is the source of truth for this page. The\nAuthentication page\nsays \"The API is fully OpenAI-compatible.\"\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. Parasail's GET https://api.parasail.io/v1/models needs a\nkey (an unauthenticated GET on 2026-09-29 answered HTTP 401), so the model ids\ncome from Parasail's public docs\n(Models page,\nretrieved 2026-09-29) and the roster has not been checked. No account was\ncreated and no API key was used to build this entry. evidence.liveMatrix is\nnull until someone runs the live capability matrix with a real key (see\nVerification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"Parasail Provider Guide","lvl2":"Parasail Provider Guide","lvl3":""}},
+{"objectID":"1db37567c33f9f106dbc78bce6c3d64e7922f5458a75d1477094e9bc80a491a2","title":"Key Facts","url":"/docs/getting-started/providers/parasail#key-facts","content":"Provider id: parasail\nProtocol: OpenAI-compatible (/chat/completions) — the\n  Authentication page\n  says \"All Parasail API requests use bearer token authentication. The API is\n  fully OpenAI-compatible.\"\nBase URL: https://api.parasail.io/v1\nDefault model: parasail-llama-33-70b-fp8 (NeuroLink default)\nModels in catalog: 12 (curated from the 33 rows of the Models page)\nStreaming: supported — the\n  Chat Completions reference\n  has a Streaming section describing stream: true with server-sent events\nTool calling: model-dependent — the\n  Tool/Function Calling guide\n  lists the serverless models that return structured tool calls in a table and\n  names other models that \"don't support the tools parameter today\"\nTools while streaming: not declared (false) — no combined request was\n  sent\nStructured output: supported — the\n  Structured Output guide\n  documents response_format with type json_schema and guided_json, and\n  lists models in a table with a \"Guided JSON / JSON Schema\" column\nStructured output + tools together: not declared (false) — no combined\n  probe was possible without credentials, so NeuroLink omits response_format\n  automatically whenever tools are attached\nEmbeddings: not declared on this catalog entry. The Chat Completions\n  reference's endpoint table lists POST /v1/embeddings, but NeuroLink's\n  generic ConfiguredOpenAICompatProvider (the class Tier-2 catalog entries\n  use) does not implement embed()/embedMany(), so this flag tracks that,\n  not the vendor's own API surface\nThinking: not declared — the entry sets no reasoning request parameter,\n  although the\n  Model-specific Notes page\n  documents model-specific thinking and reasoning controls\nBilling: recorded as no-free-tier, which is the schema placeholder\n  (the catalog schema has no unknown value), not a vendor statement of signup\n  terms — see Billing below\nKey format: none declared","hierarchy":{"lvl0":"Getting Started","lvl1":"Parasail Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"987c6a257812c68977124c7ce3a87a21cde91b38f306312132487091c94db118","title":"1. Get an API key","url":"/docs/getting-started/providers/parasail#1-get-an-api-key","content":"Visit: https://www.saas.parasail.io/keys — the link the Authentication page gives for getting an API key; sign-in was not attempted while building this entry\nCreate an API key and copy it when it is shown — the Authentication page steps read \"Click Create API Key.\" and \"Copy the key immediately—it's displayed only once.\"\nBilling as the vendor states it: the Pricing page says \"To use models, create API keys, and access paid platform services, add a credit card. Without a card, you can still view the platform but can't use models or API keys.\"\nSet PARASAIL_API_KEY in your .env file (the docs' examples use the environment variable PARASAIL_API_KEY)","hierarchy":{"lvl0":"Getting Started","lvl1":"Parasail Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"1478ece04ff01fddd6da781b69c7dfb89ff4af794105edade9e86cb9e5a322f2","title":"3. Use it","url":"/docs/getting-started/providers/parasail#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Parasail Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"cc39c5e85f28a6665587f95142fb9ab79861142a389d77f024a4e371f5b61cd5","title":"CLI","url":"/docs/getting-started/providers/parasail#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider parasail\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"parasail\",\n  credentials: { parasail: { apiKey: process.env.PARASAILAPIKEY } },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"Parasail Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"d8dae177f59f26dfc81738791f39b34cbed96b6f08d31621988407b3413f1a73","title":"Billing","url":"/docs/getting-started/providers/parasail#billing","content":"The Pricing page\nsays \"To use models, create API keys, and access paid platform services, add a\ncredit card. Without a card, you can still view the platform but can't use\nmodels or API keys.\" The\nLimits and Quotas page\nhas a rate-limit table with a product class \"Serverless - Free\" (RPM column\n\"5\"). The catalog's billingPolicy field takes one of three values and holds\nno-free-tier here as a placeholder; it is not a vendor statement of signup\nterms.","hierarchy":{"lvl0":"Getting Started","lvl1":"Parasail Provider Guide","lvl2":"Billing","lvl3":""}},
+{"objectID":"c659184b794ec6fd8a7c787b0db2b35b3487b60687ba5a3ab07cc85a8a84fe37","title":"Models","url":"/docs/getting-started/providers/parasail#models","content":"| Model                                    | Context   | Max output | Vision | $/M in · out (cached)  | Notes                                                                                                                                                                                                          |\n| ---------------------------------------- | --------- | ---------- | ------ | ---------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| parasail-llama-33-70b-fp8 ⭐           | 131,072   | 16,384     | no     | $0.22 / $0.50 ($0.11)  | NeuroLink default. Chat Completions guide example; Tools ✅ and Tool Choice ✅; Y under Guided JSON / JSON Schema, Regex and Choice.                                                                           |\n| parasail-llama-4-maverick-instruct-fp8 | 524,288   | 32,768     | no     | $0.35 / $1.00 ($0.17)  | Tools ✅ and Tool Choice ✅; Y under Guided JSON / JSON Schema, Regex and Choice. Fallback.                                                                                                                    |\n| parasail-gpt-oss-120b                  | 131,072   | 131,072    | no     | $0.10 / $0.75 ($0.055) | Tools ✅ and Tool Choice ✅. Model-specific Notes page has \"GPT-OSS reasoning control\" and \"Structured outputs with GPT-OSS\" sections. Fallback.                                                               |\n| parasail-gpt-oss-20b                   | 131,072   | 131,072    | no     | $0.03 / $0.15 ($0.02)  | Tools ✅ and Tool Choice ✅. Same Model-specific Notes sections as parasail-gpt-oss-120b. Fallback.                                                                                                          |\n| parasail-deepseek-v4-flash             | 1,048,576 | 1,048,576  | no     | $0.14 / $0.28 ($0.07)  | Tools ✅ and Tool Choice ✅. Fallback.   ","hierarchy":{"lvl0":"Getting Started","lvl1":"Parasail Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"e4a90009c7bcd26ccb6a5309dfd66d6dc17c46b9abbfb292b212fe38b41c1b98","title":"Verification status","url":"/docs/getting-started/providers/parasail#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog currently records for Parasail — docs-verified only, not yet\nlive-verified:\n\n| Probe                     | Result                                                                                                                                                                                                                                                                                                                                                                                                    |\n| ------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                    | unauthenticated GET https://api.parasail.io/v1/models answered HTTP 401 on 2026-09-29 — no key used, so the model ids are taken from the Models page (retrieved 2026-09-29) and the roster is not verified                                                                                                                                                                                              |\n| Billing                   | the Pricing page says \"To use models, create API keys, and access paid platform services, add a credit card. Without a card, you can still view the platform but can't use models or API keys.\"; the Limits and Quotas page has a \"Serverless - Free\" rate-limit row; no signup was performed, 2026-09-29                                                                                                 |\n| Auth-failure shape        | unauthenticated GETs of /v1/models, /v1/cha","hierarchy":{"lvl0":"Getting Started","lvl1":"Parasail Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"7524ca685dabe987464872496673f6a1795cb28e182c63b7eea6e8e6f2f7de4d","title":"Documented error statuses","url":"/docs/getting-started/providers/parasail#documented-error-statuses","content":"The\nChat Completions reference\nsays \"Errors use OpenAI-compatible status codes and a JSON body with an error\nobject (message, type, code).\" and lists these statuses:\n\n| Status | Parasail's description                                                                 |\n| ------ | -------------------------------------------------------------------------------------- |\n| 400  | Malformed request—invalid JSON, missing required field, or unsupported parameter value |\n| 401  | Missing or invalid API key                                                             |\n| 403  | API key lacks access to the requested model or resource                                |\n| 404  | Model or endpoint not found                                                            |\n| 429  | Rate limit or quota exceeded—back off and retry                                        |\n| 500  | Internal server error—retry with exponential backoff                                   |\n\nThe\nTool/Function Calling guide\nsays of models outside its table: \"Depending on the model, a request with tools\nreturns an error or plain text with no tool_calls.\"","hierarchy":{"lvl0":"Getting Started","lvl1":"Parasail Provider Guide","lvl2":"Documented error statuses","lvl3":""}},
+{"objectID":"f48bba8c2e9813155262f99a41ecc882205dc495aa27c27bb0b50c527a0f8a5d","title":"See also","url":"/docs/getting-started/providers/parasail#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility\nParasail docs pages used for this entry: Models, Pricing, Authentication, Chat Completions reference, Tool/Function Calling, Structured Output, Multi-Modal, Model-specific Notes, Limits and Quotas","hierarchy":{"lvl0":"Getting Started","lvl1":"Parasail Provider Guide","lvl2":"See also","lvl3":""}},
 {"objectID":"5e3a315038085bf3d2d31cbaaf7a07c7df8228093af856dd3a697f19736edf24","title":"Pareto Inference Provider Guide","url":"/docs/getting-started/providers/pareto-inference","content":"Pareto Inference Provider Guide\n\nVerification status: this entry is docs- and roster-verified only —\nnot yet live-verified. It was onboarded credential-free: no Pareto\nInference API key was ever created or used. Every field below comes from\nPareto's public docs (https://docs.paretoinference.com/) and an\nunauthenticated GET /v1/models call (no auth header). No POST\nrequest was ever sent, so no generate, stream, tool-calling or\nstructured-output capability has been exercised end to end. Treat\ncapabilities.tools and .thinking as documentation-grade, not\nwire-proven, until evidence.liveMatrix is filled in by a live run.\n\nPareto Inference is a Tier-2 catalog provider: OpenAI-wire-compatible\nwith no behavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/pareto-inference.json) rather than hand-written\ncode. That file is the source of truth for everything on this page.\n\nKey Facts\nProvider id: pareto-inference\nProtocol: OpenAI-compatible (/chat/completions) — \"Pareto accepts\n  only OpenAI Chat Completions.\"\nBase URL: https://api.paretoinference.com/v1\nDefault model: z-ai/glm-5.3-flash (GLM 5.3 Flash; the docs also\n  document a bare alias, glm-5.3-flash, for the same model)\nModels in catalog: 1 — the only model Pareto serves. Confirmed by an\n  unauthenticated GET /v1/models (no key needed), which returns exactly\n  one id.\nStreaming: documented (SSE, text in choices[0].delta.content, tool\n  calls in choices[0].delta.tool_calls, terminal data: [DONE]) — not\n  live-probed.\nTool calling: documented (tools, tool_choice) but the vendor's own\n  request-parameter table hedges it with \"Model support can differ,\" with no\n  model-specific confirmation — set to model-dependent, not true.\nStructured output: response_format is a documented parameter but\n  carries the same \"Model support can differ\" hedge as tools; the catalog\n  schema has no model-dependent option for this field, so it is set\n  false rather than asserted from a hedged table. structuredOutputWithTools\n  is false — no combined probe was possible credential-free.\nReasoning: reasoning_effort (\"Sets the reasoning level\") is\n  documented as a plain, unhedged request parameter — unlike tools /\n  response_format / tool_choice / logprobs, it carries no \"Model\n  support can differ\" caveat — the basis for capabilities.thinking: true.\nVision: not documented anywhere on the site.\nEmbeddings: not documented anywhere on the site.\nBilling: no free tier. A payment card and prepaid credits are\n  required before a key is issued.\nSignup: https://paretoinference.com/dashboard\nKey format: none declared.\nData handling: Pareto documents zero data retention (ZDR) — request\n  content is not kept after a request finishes.\n\nQuick Start\nGet an API key\nVisit: https://paretoinference.com/dashboard and sign in\nAdd a payment card — Pareto has no free tier; a card and prepaid credits\n   are required before a key is issued\n   (https://docs.paretoinference.com/pricing)\nBuy prepaid credits, then create your API key from the dashboard\nSet PARETO_INFERENCE_API_KEY in your .env file\nConfigure\nUse it\n\nPer-request credentials work as they do for every provider:\n\nModels\n\n| Model                   | Context   | Vision | $/M in · out · cached         | Notes                                                                                                                                                                                                                                       |\n| ----------------------- | --------- | ------ | ----------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| z-ai/glm-5.3-flash ⭐ | 131,072\\ | no     | $0.03 / $0.10 (cached $0.006) | Only model Pareto serves. Max output documented as 1–131,072 tokens (default 131,072). \\Context window is not published by Pareto — this figure reuses the documented output ceiling as a conservative floor, not a stated context length. |\n\n\\ Pareto's own docs state it does not* disclose GLM 5.3 Flash's serving\ndetails (\"We do not disclose the technical details of our GLM 5.3 Flash\nserving system\"), and no context-window number appears on any public page.\nmodels.defaultContextWindow (131,072) is therefore the documented\noutput ceiling reused as a floor, flagged in the catalog entry's\ndescription — correct it once Pareto publishes a real figure or an\nauthenticated probe reveals one.\n\nFallback order: none — z-ai/glm-5.3-flash is the only model Pareto\nserves, so it is both the default and its own (schema-exempt) single-entry\nfallback list.\n\nVerification status\n\nTier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog records for Pareto Inference — and, just as importantly, what it\ndoes not yet record:\n\n| Probe           ","hierarchy":{"lvl0":"Getting Started","lvl1":"Pareto Inference Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"6a8ee157b685405e8c480486655e4656ea272f63493e36006b7ac43e499b5e27","title":"Pareto Inference Provider Guide","url":"/docs/getting-started/providers/pareto-inference#pareto-inference-provider-guide","content":"Verification status: this entry is docs- and roster-verified only —\nnot yet live-verified. It was onboarded credential-free: no Pareto\nInference API key was ever created or used. Every field below comes from\nPareto's public docs (https://docs.paretoinference.com/) and an\nunauthenticated GET /v1/models call (no auth header). No POST\nrequest was ever sent, so no generate, stream, tool-calling or\nstructured-output capability has been exercised end to end. Treat\ncapabilities.tools and .thinking as documentation-grade, not\nwire-proven, until evidence.liveMatrix is filled in by a live run.\n\nPareto Inference is a Tier-2 catalog provider: OpenAI-wire-compatible\nwith no behavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/pareto-inference.json) rather than hand-written\ncode. That file is the source of truth for everything on this page.","hierarchy":{"lvl0":"Getting Started","lvl1":"Pareto Inference Provider Guide","lvl2":"Pareto Inference Provider Guide","lvl3":""}},
 {"objectID":"4098c852271191df4a2cf6cfcd19b7832504f8a2e019abcce21852d7bc292fe3","title":"Key Facts","url":"/docs/getting-started/providers/pareto-inference#key-facts","content":"Provider id: pareto-inference\nProtocol: OpenAI-compatible (/chat/completions) — \"Pareto accepts\n  only OpenAI Chat Completions.\"\nBase URL: https://api.paretoinference.com/v1\nDefault model: z-ai/glm-5.3-flash (GLM 5.3 Flash; the docs also\n  document a bare alias, glm-5.3-flash, for the same model)\nModels in catalog: 1 — the only model Pareto serves. Confirmed by an\n  unauthenticated GET /v1/models (no key needed), which returns exactly\n  one id.\nStreaming: documented (SSE, text in choices[0].delta.content, tool\n  calls in choices[0].delta.tool_calls, terminal data: [DONE]) — not\n  live-probed.\nTool calling: documented (tools, tool_choice) but the vendor's own\n  request-parameter table hedges it with \"Model support can differ,\" with no\n  model-specific confirmation — set to model-dependent, not true.\nStructured output: response_format is a documented parameter but\n  carries the same \"Model support can differ\" hedge as tools; the catalog\n  schema has no model-dependent option for this field, so it is set\n  false rather than asserted from a hedged table. structuredOutputWithTools\n  is false — no combined probe was possible credential-free.\nReasoning: reasoning_effort (\"Sets the reasoning level\") is\n  documented as a plain, unhedged request parameter — unlike tools /\n  response_format / tool_choice / logprobs, it carries no \"Model\n  support can differ\" caveat — the basis for capabilities.thinking: true.\nVision: not documented anywhere on the site.\nEmbeddings: not documented anywhere on the site.\nBilling: no free tier. A payment card and prepaid credits are\n  required before a key is issued.\nSignup: https://paretoinference.com/dashboard\nKey format: none declared.\nData handling: Pareto documents zero data retention (ZDR) — request\n  content is not kept after a request finishes.","hierarchy":{"lvl0":"Getting Started","lvl1":"Pareto Inference Provider Guide","lvl2":"Key Facts","lvl3":""}},
@@ -6747,6 +6879,17 @@
 {"objectID":"9c27a11c0ebcaad3730b5040169bf7e59b61e12c50477d166c250d91e57717c2","title":"Configuration Reference","url":"/docs/getting-started/providers/perplexity#configuration-reference","content":"| Environment Variable  | Required | Default                     |\n| --------------------- | -------- | --------------------------- |\n| PERPLEXITY_API_KEY  | Yes      | —                           |\n| PERPLEXITY_MODEL    | No       | sonar                     |\n| PERPLEXITY_BASE_URL | No       | https://api.perplexity.ai |","hierarchy":{"lvl0":"Getting Started","lvl1":"Perplexity Provider Guide","lvl2":"Configuration Reference","lvl3":""}},
 {"objectID":"b67f2a3fac01aa89f00439994b86dc4e53d345274ba20ce64db2f4f9d6577523","title":"Feature Support Matrix","url":"/docs/getting-started/providers/perplexity#feature-support-matrix","content":"| Feature           | Support      |\n| ----------------- | ------------ |\n| Text generation   | Yes          |\n| Streaming         | Yes          |\n| Tool calling      | No           |\n| Structured output | Limited      |\n| Web search        | Yes (native) |\n| Citations         | Yes          |","hierarchy":{"lvl0":"Getting Started","lvl1":"Perplexity Provider Guide","lvl2":"Feature Support Matrix","lvl3":""}},
 {"objectID":"863a4c9129e2042f2c209c6d79faf1a589d15399b222cef42341b701ce775a0c","title":"See Also","url":"/docs/getting-started/providers/perplexity#see-also","content":"Anthropic Provider — web-search via the web_search tool\nVertex Provider — Google search grounding","hierarchy":{"lvl0":"Getting Started","lvl1":"Perplexity Provider Guide","lvl2":"See Also","lvl3":""}},
+{"objectID":"2085fe13de3c871057e70fbc1ba2d37f1825f635c6d9528764fdc45d76fe6744","title":"Poolside Provider Guide","url":"/docs/getting-started/providers/poolside","content":"Poolside Provider Guide\n\nPoolside is a Tier-2 catalog provider: its entire integration is one JSON\nfile (src/lib/providers/catalog/poolside.json) rather than hand-written code.\nThat file is the source of truth for everything on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. Poolside's GET https://inference.poolside.ai/v1/models\nneeds a key (an unauthenticated GET answered HTTP 401), so the model id comes\nfrom Poolside's public docs and the roster has not been checked. No account\nwas created and no API key was used to build it. evidence.liveMatrix is\nnull until someone runs the live capability matrix with a real key (see\nVerification status below).\n\nKey Facts\nProvider id: poolside\nProtocol: OpenAI-compatible (/chat/completions) — the\n  Poolside API page opens with\n  \"Call Poolside models through an OpenAI-compatible API.\"\nBase URL: https://inference.poolside.ai/v1 (the \"Poolside-hosted\n  inference\" row of the Access methods table on the same page)\nDefault model: poolside/laguna-s-2.1\nModels in catalog: 1 — the model id the docs' examples use against the\n  hosted base URL\nStreaming: supported — the\n  examples page documents\n  setting stream to true to receive \"a series of chunks returned as\n  server-sent events\"\nTool calling: supported (true) — the examples page's \"Extend models with\n  tools\" section shows a tools array and a returned tool_calls array on\n  poolside/laguna-s-2.1\nTools while streaming: not declared (false) — no request combining them\n  was sent\nStructured output: not declared (false) — no request using\n  response_format was sent\nStructured output + tools together: not declared (false) — no combined\n  probe was sent\nEmbeddings: not declared — the overview page's Available endpoints table\n  lists two endpoints, GET /v1/models and POST /v1/chat/completions\nThinking: not declared (false) — the entry sends no thinking request\n  parameter. The examples page says \"Poolside-hosted inference enables thinking\n  by default.\" and documents setting chat_template_kwargs.enable_thinking to\n  false to turn it off for a request\nReasoning content: quirks.replayReasoningContent is set, because the\n  examples page says \"For agentic workflows with Poolside models, preserve\n  reasoning_content from assistant responses when you include those responses in\n  follow-up requests.\" No multi-turn request was sent\nBilling: free-tier — one of the three values the catalog schema allows;\n  see Billing below\nKey format: none declared\n\nQuick Start\nGet an API key\nVisit: https://platform.poolside.ai/ — https://docs.poolside.ai/get-started/log-in.md says of the Poolside Platform option: \"sign in to Poolside Platform or create an account\"\nCreate an API key: https://docs.poolside.ai/api/overview.md says \"Sign in to Poolside Platform, open the API Keys tab, and click New key.\"\nBilling as the vendor states it: https://docs.poolside.ai/get-started/log-in.md describes the Poolside Platform option as \"free developer access\" and says \"The API key created through Poolside Platform is for Poolside-hosted inference.\"\nAuthentication is HTTP Bearer: https://docs.poolside.ai/api/overview.md shows the header Authorization: Bearer <api-key> and exports the key as POOLSIDEAPIKEY, the name NeuroLink reads. Set POOLSIDE_API_KEY in your .env file\nConfigure\nUse it\n\nPer-request credentials work the same way as for the other catalog providers:\n\nBilling\n\nThe log-in page describes the\nPoolside Platform option as \"free developer access\" and says \"The API key\ncreated through Poolside Platform is for Poolside-hosted inference.\" The catalog\nschema has three billing values (free-tier, free-with-card, no-free-tier);\nthe entry holds free-tier, built from that wording.\n\nModels\n\n| Model                      | Context | Vision | Notes                                                                                                                                                                                                                                                                                                                        |\n| -------------------------- | ------- | ------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| poolside/laguna-s-2.1 ⭐ | not set | no     | NeuroLink default — the model id the API page's quickstart examples and the examples page's examples use against https://inference.poolside.ai/v1. The supported-models page lists \"118B total, 8B active per token\", \"Mixture of Experts\" and \"Text-to-text\". |\n\nValues come from Poolside's public docs, retrieved 2026-09-29:\nContext — the catalog entry sets no contextWindow for this model, so\n  models.defaultContextWindow (128,000) applies. The Context window row of the\n  supported-mo","hierarchy":{"lvl0":"Getting Started","lvl1":"Poolside Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"246fe064c68a09a615422277d825f7537bc3c7d8cfdf3cbca1a6f902279369f4","title":"Poolside Provider Guide","url":"/docs/getting-started/providers/poolside#poolside-provider-guide","content":"Poolside is a Tier-2 catalog provider: its entire integration is one JSON\nfile (src/lib/providers/catalog/poolside.json) rather than hand-written code.\nThat file is the source of truth for everything on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. Poolside's GET https://inference.poolside.ai/v1/models\nneeds a key (an unauthenticated GET answered HTTP 401), so the model id comes\nfrom Poolside's public docs and the roster has not been checked. No account\nwas created and no API key was used to build it. evidence.liveMatrix is\nnull until someone runs the live capability matrix with a real key (see\nVerification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"Poolside Provider Guide","lvl2":"Poolside Provider Guide","lvl3":""}},
+{"objectID":"3cf9f1d461fe520b9110f9d1e32d4000fd91eeeeb908a498d0fc61faa5947a06","title":"Key Facts","url":"/docs/getting-started/providers/poolside#key-facts","content":"Provider id: poolside\nProtocol: OpenAI-compatible (/chat/completions) — the\n  Poolside API page opens with\n  \"Call Poolside models through an OpenAI-compatible API.\"\nBase URL: https://inference.poolside.ai/v1 (the \"Poolside-hosted\n  inference\" row of the Access methods table on the same page)\nDefault model: poolside/laguna-s-2.1\nModels in catalog: 1 — the model id the docs' examples use against the\n  hosted base URL\nStreaming: supported — the\n  examples page documents\n  setting stream to true to receive \"a series of chunks returned as\n  server-sent events\"\nTool calling: supported (true) — the examples page's \"Extend models with\n  tools\" section shows a tools array and a returned tool_calls array on\n  poolside/laguna-s-2.1\nTools while streaming: not declared (false) — no request combining them\n  was sent\nStructured output: not declared (false) — no request using\n  response_format was sent\nStructured output + tools together: not declared (false) — no combined\n  probe was sent\nEmbeddings: not declared — the overview page's Available endpoints table\n  lists two endpoints, GET /v1/models and POST /v1/chat/completions\nThinking: not declared (false) — the entry sends no thinking request\n  parameter. The examples page says \"Poolside-hosted inference enables thinking\n  by default.\" and documents setting chat_template_kwargs.enable_thinking to\n  false to turn it off for a request\nReasoning content: quirks.replayReasoningContent is set, because the\n  examples page says \"For agentic workflows with Poolside models, preserve\n  reasoning_content from assistant responses when you include those responses in\n  follow-up requests.\" No multi-turn request was sent\nBilling: free-tier — one of the three values the catalog schema allows;\n  see Billing below\nKey format: none declared","hierarchy":{"lvl0":"Getting Started","lvl1":"Poolside Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"0473e398409c69bbff129c7e7661af0a8c1206ded44c459e526deffe51efb38a","title":"1. Get an API key","url":"/docs/getting-started/providers/poolside#1-get-an-api-key","content":"Visit: https://platform.poolside.ai/ — https://docs.poolside.ai/get-started/log-in.md says of the Poolside Platform option: \"sign in to Poolside Platform or create an account\"\nCreate an API key: https://docs.poolside.ai/api/overview.md says \"Sign in to Poolside Platform, open the API Keys tab, and click New key.\"\nBilling as the vendor states it: https://docs.poolside.ai/get-started/log-in.md describes the Poolside Platform option as \"free developer access\" and says \"The API key created through Poolside Platform is for Poolside-hosted inference.\"\nAuthentication is HTTP Bearer: https://docs.poolside.ai/api/overview.md shows the header Authorization: Bearer <api-key> and exports the key as POOLSIDEAPIKEY, the name NeuroLink reads. Set POOLSIDE_API_KEY in your .env file","hierarchy":{"lvl0":"Getting Started","lvl1":"Poolside Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"1ba4b5ee1ceec247fe3c01f23307db6a6f63524398f3b199ade21753eee2f597","title":"3. Use it","url":"/docs/getting-started/providers/poolside#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Poolside Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"07a320368a94b93f68ebaea187075b23dcf62a1a3a080e83b7dea52a47549313","title":"CLI","url":"/docs/getting-started/providers/poolside#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider poolside\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"poolside\",\n  credentials: { poolside: { apiKey: process.env.POOLSIDEAPIKEY } },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"Poolside Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"cf2d42279209983e361bb87311eed47de7a08324990e27b9bc7ef6590312249d","title":"Billing","url":"/docs/getting-started/providers/poolside#billing","content":"The log-in page describes the\nPoolside Platform option as \"free developer access\" and says \"The API key\ncreated through Poolside Platform is for Poolside-hosted inference.\" The catalog\nschema has three billing values (free-tier, free-with-card, no-free-tier);\nthe entry holds free-tier, built from that wording.","hierarchy":{"lvl0":"Getting Started","lvl1":"Poolside Provider Guide","lvl2":"Billing","lvl3":""}},
+{"objectID":"4568f22e9818f56bad11acca7e61c2e09bbd51c8d771ee96f6228ad2f4486bbb","title":"Models","url":"/docs/getting-started/providers/poolside#models","content":"| Model                      | Context | Vision | Notes                                                                                                                                                                                                                                                                                                                        |\n| -------------------------- | ------- | ------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| poolside/laguna-s-2.1 ⭐ | not set | no     | NeuroLink default — the model id the API page's quickstart examples and the examples page's examples use against https://inference.poolside.ai/v1. The supported-models page lists \"118B total, 8B active per token\", \"Mixture of Experts\" and \"Text-to-text\". |\n\nValues come from Poolside's public docs, retrieved 2026-09-29:\nContext — the catalog entry sets no contextWindow for this model, so\n  models.defaultContextWindow (128,000) applies. The Context window row of the\n  supported-models page\n  shows \"1M tokens\" for Laguna S 2.1, and the same page says \"Model\n  availability, provider-specific variants, and model IDs can vary by access\n  method.\"\nVision — false. The\n  model release notes say\n  Laguna S 2.1 \"is text-to-text and does not support vision inputs\".\nDescription — the release notes say Laguna S 2.1 is \"built for agentic\n  coding and long-horizon work\". The supported-models page lists Reasoning as\n  \"Native reasoning with thinking on or off per request\".\nPricing — no pricingPerMTok is set.\n\nmodels.defaultContextWindow (128,000) is a placeholder, not a vendor figure.\nmodels.defaultMaxOutputTokens (32,768) equals the max_tokens default in the\nControl generation table on the\nexamples page; it is n","hierarchy":{"lvl0":"Getting Started","lvl1":"Poolside Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"81c89238453ea4d2228fd6b5c89f3519ddf2ee332aaaeda469498d532d4a3256","title":"Verification status","url":"/docs/getting-started/providers/poolside#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog currently records for Poolside — docs-verified only, not\nlive-verified:\n\n| Probe                     | Result                                                                                                                                                                                                                                                                                                              |\n| ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                    | unauthenticated GET https://inference.poolside.ai/v1/models answered HTTP 401 without a key on 2026-09-29, so the model id is taken from https://docs.poolside.ai/api/overview.md (retrieved 2026-09-29); roster not verified                                                                                     |\n| Billing                   | https://docs.poolside.ai/get-started/log-in.md describes the Poolside Platform option as \"free developer access\"; https://platform.poolside.ai/ opened and shows the title \"Poolside Platform\"; no signup was performed, 2026-09-29                                                                                 |\n| Auth-failure shape        | unauthenticated GET /v1/models answered HTTP 401, content-type text/plain; charset=utf-8, plain-text body \"No Authorization header provided\"; unauthenticated GET /v1/chat/completions answered HTTP 405 with an empty body. No POST request was sent. errorRules carry 401 (observed) and 403 (documented) |\n| Tools / structured output | function calling is documented on https://docs.poolside.ai/","hierarchy":{"lvl0":"Getting Started","lvl1":"Poolside Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"76e78b54080a037cc5f8c3d51956388a7b4c6ab8064695c46ae3d88e0a4c0ed2","title":"Troubleshooting","url":"/docs/getting-started/providers/poolside#troubleshooting","content":"| Symptom                                                   | Cause                                                                                                                                                                                                                      | Fix                                                                                                |\n| --------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------- |\n| HTTP 401 with the body No Authorization header provided | Observed on 2026-09-29 for an unauthenticated GET /v1/models; https://docs.poolside.ai/api/overview.md says \"Poolside-hosted inference and OpenRouter require an API key.\"                                               | The same page says \"Send it as a Bearer token in the Authorization header\"; set POOLSIDE_API_KEY |\n| 403 Forbidden: please check the api-key you provided    | Listed under \"Fix API key or token errors\" on https://docs.poolside.ai/cli/troubleshooting.md, which says \"These errors usually mean the prompt reached the agent, but the agent or model request could not authenticate.\" | That page's first step is \"Check whether authentication environment variables are set.\"            |","hierarchy":{"lvl0":"Getting Started","lvl1":"Poolside Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
+{"objectID":"4b681fd42e1b24e317838d91533cff73607270571d14eef644476729ef065003","title":"See also","url":"/docs/getting-started/providers/poolside#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Poolside Provider Guide","lvl2":"See also","lvl3":""}},
 {"objectID":"0dc11e2e9b21ce8d74d7356335e489afbf48de63ab5bd1de93f8f20dc8ecf1a8","title":"Prime Intellect Provider Guide","url":"/docs/getting-started/providers/prime-intellect","content":"Prime Intellect Provider Guide\n\nPrime Intellect Inference is a Tier-2 catalog provider: OpenAI-wire-compatible\nwith no behavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/prime-intellect.json) rather than hand-written\ncode. That file is the source of truth for everything on this page.\n\nVerification status: this entry is docs- and roster-verified, not yet\nlive-verified. Every field below comes from Prime Intellect's own public\ndocumentation, its public OpenAPI spec, and unauthenticated GET requests to\nhttps://api.pinference.ai — no API key was created or used to build it, and\nno POST was sent. evidence.liveMatrix is null until someone runs the live\ncapability matrix with a real key (see Verification status\nbelow).\n\nKey Facts\nProvider id: prime-intellect\nProtocol: OpenAI-compatible (/chat/completions) — Prime's inference\n  overview calls it \"OpenAI-compatible API access\" and shows the official\n  openai client pointed at a custom base_url\n  (https://docs.primeintellect.ai/inference/overview)\nBase URL: https://api.pinference.ai/api/v1. The inference host\n  (pinference.ai) is a different domain from the docs and dashboard host\n  (primeintellect.ai); both are confirmed on the vendor's own pages\nDefault model: openai/gpt-4.1-mini\nModels in catalog: 12 (curated from a 125-model roster read on 2026-09-29;\n  the discovery queue recorded 124, so the roster moves)\nWhat it is: a gateway. 119 of the 125 roster entries are serving:\n\"gateway\" (routed to upstream providers); the other 6 are serving:\n\"hosted\" (served on Prime infrastructure) and are third-party Qwen and GLM\n  models. No Prime-trained model appears on the roster\nStreaming: supported — documented on the Advanced Usage and Chat\n  Completions reference pages (stream: true)\nTool calling: model-dependent — the docs pages do not describe function\n  calling, but the roster's own per-model supported_parameters field lists\n  tools and tool_choice for 111 of 125 models and omits them for others\n  (see Verification status for the basis)\nStructured output: declared true on the same basis — response_format\n  is listed for 106 of 125 roster models, structured_outputs for 102. It is\n  per-model, not universal\nStructured output + tools together: not declared (false) — no combined\n  probe was possible without credentials\nEmbeddings / thinking: not declared. No inference page describes either\nBilling: no-free-tier — Prime states billing is \"automatic deduction\n  from your Prime Intellect account balance\". No free tier or trial credit is\n  documented on the pages read. The catalog schema has no \"unknown\" billing\n  value, so no-free-tier here means none documented, not _vendor-confirmed\n  none_\nKey format: none declared by Prime Intellect\n\nQuick Start\nGet an API key\nVisit: https://app.primeintellect.ai/dashboard/tokens (Settings -> API Keys) and sign in\nClick Generate New Key and enable the Inference permission — without it requests fail with authentication errors (https://docs.primeintellect.ai/inference/overview); the key is shown only once, so copy it straight away (https://docs.primeintellect.ai/api-reference/api-keys)\nBilling is automatic deduction from your Prime Intellect account balance (https://docs.primeintellect.ai/inference/overview); no free tier or trial credit is documented on the pages read, so add funds at https://app.primeintellect.ai/dashboard/billing and confirm current terms before the first call\nSet PRIME_INTELLECT_API_KEY in your .env file (PRIME_API_KEY, the variable Prime's own docs use, is also read)\nConfigure\nUse it\n\nPer-request credentials work as they do for every provider:\n\nModels\n\n| Model                                | Context   | Vision | $/M in · out                 | Notes                                                                                                                                                                |\n| ------------------------------------ | --------- | ------ | ---------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| openai/gpt-4.1-mini ⭐             | 1,047,576 | yes    | $0.40 / $1.60                | Recommended — Prime's Evaluating Environments guide lists it as \"Fast, cost-effective (default)\" and uses it as the default model of its inference-backed eval flow. |\n| openai/gpt-4.1                     | 1,047,576 | yes    | $2 / $8                      | Listed in the same guide as \"Higher quality\"; fallback.                                                                                                              |\n| anthropic/claude-sonnet-4.5        | 1,000,000 | yes    | $3 / $15                     | Listed in the same guide as \"Strong reasoning\"; fallback.                                                                                                            |\n| meta-llama/llama-3.3-70b-instruct  | 131,072   | no     | $1.","hierarchy":{"lvl0":"Getting Started","lvl1":"Prime Intellect Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"e849ee91aa4616cfc65077bd44442aa2342cb5aa2809da781abbf72e7ef44771","title":"Prime Intellect Provider Guide","url":"/docs/getting-started/providers/prime-intellect#prime-intellect-provider-guide","content":"Prime Intellect Inference is a Tier-2 catalog provider: OpenAI-wire-compatible\nwith no behavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/prime-intellect.json) rather than hand-written\ncode. That file is the source of truth for everything on this page.\n\nVerification status: this entry is docs- and roster-verified, not yet\nlive-verified. Every field below comes from Prime Intellect's own public\ndocumentation, its public OpenAPI spec, and unauthenticated GET requests to\nhttps://api.pinference.ai — no API key was created or used to build it, and\nno POST was sent. evidence.liveMatrix is null until someone runs the live\ncapability matrix with a real key (see Verification status\nbelow).","hierarchy":{"lvl0":"Getting Started","lvl1":"Prime Intellect Provider Guide","lvl2":"Prime Intellect Provider Guide","lvl3":""}},
 {"objectID":"54313a0132807b7d460a6334f82ad9b6f2b0e833e61eeb34c228cf651328a56c","title":"Key Facts","url":"/docs/getting-started/providers/prime-intellect#key-facts","content":"Provider id: prime-intellect\nProtocol: OpenAI-compatible (/chat/completions) — Prime's inference\n  overview calls it \"OpenAI-compatible API access\" and shows the official\n  openai client pointed at a custom base_url\n  (https://docs.primeintellect.ai/inference/overview)\nBase URL: https://api.pinference.ai/api/v1. The inference host\n  (pinference.ai) is a different domain from the docs and dashboard host\n  (primeintellect.ai); both are confirmed on the vendor's own pages\nDefault model: openai/gpt-4.1-mini\nModels in catalog: 12 (curated from a 125-model roster read on 2026-09-29;\n  the discovery queue recorded 124, so the roster moves)\nWhat it is: a gateway. 119 of the 125 roster entries are serving:\n\"gateway\" (routed to upstream providers); the other 6 are serving:\n\"hosted\" (served on Prime infrastructure) and are third-party Qwen and GLM\n  models. No Prime-trained model appears on the roster\nStreaming: supported — documented on the Advanced Usage and Chat\n  Completions reference pages (stream: true)\nTool calling: model-dependent — the docs pages do not describe function\n  calling, but the roster's own per-model supported_parameters field lists\n  tools and tool_choice for 111 of 125 models and omits them for others\n  (see Verification status for the basis)\nStructured output: declared true on the same basis — response_format\n  is listed for 106 of 125 roster models, structured_outputs for 102. It is\n  per-model, not universal\nStructured output + tools together: not declared (false) — no combined\n  probe was possible without credentials\nEmbeddings / thinking: not declared. No inference page describes either\nBilling: no-free-tier — Prime states billing is \"automatic deduction\n  from your Prime Intellect account balance\". No free tier or trial credit is\n  documented on the pages read. The catalog schema has no \"unknown\" billing\n  value, so no-free-tier here means none documented, not _vendor-confirmed\n  none_\nKey format: none declared by Prime Intellect","hierarchy":{"lvl0":"Getting Started","lvl1":"Prime Intellect Provider Guide","lvl2":"Key Facts","lvl3":""}},
@@ -6765,6 +6908,17 @@
 {"objectID":"b542e878ae561e1cd9d7ea83a1a95d493712f64171d7fbd98a2819ce32ab3cbb","title":"Supported Models","url":"/docs/getting-started/providers/recraft#supported-models","content":"| Model ID        | Output | Notes                     |\n| --------------- | ------ | ------------------------- |\n| recraftv3     | Raster | Default; current flagship |\n| recraftv3-svg | SVG    | Native vector output      |\n| recraftv2     | Raster | Previous generation       |","hierarchy":{"lvl0":"Getting Started","lvl1":"Recraft Provider Guide (image-gen)","lvl2":"Supported Models","lvl3":""}},
 {"objectID":"8b6c0c2cc6eda6858431c784ce846bac4040fca7b7fb7e1d8b78994d71dbd2c9","title":"Configuration Reference","url":"/docs/getting-started/providers/recraft#configuration-reference","content":"| Environment Variable | Required | Default     |\n| -------------------- | -------- | ----------- |\n| RECRAFT_API_KEY    | Yes      | —           |\n| RECRAFT_MODEL      | No       | recraftv3 |","hierarchy":{"lvl0":"Getting Started","lvl1":"Recraft Provider Guide (image-gen)","lvl2":"Configuration Reference","lvl3":""}},
 {"objectID":"a486a24ebd4845bec154166c9db68f9d2a4ef200eab97990b9384f23ab7a3ae5","title":"See Also","url":"/docs/getting-started/providers/recraft#see-also","content":"Stability AI Provider\nIdeogram Provider","hierarchy":{"lvl0":"Getting Started","lvl1":"Recraft Provider Guide (image-gen)","lvl2":"See Also","lvl3":""}},
+{"objectID":"253e96d7ea40ad1aea03bc5cb594922747b4cfc6eafdf54b8b1a8711a513a431","title":"Reka AI Provider Guide","url":"/docs/getting-started/providers/reka","content":"Reka AI Provider Guide\n\nReka AI is a Tier-2 catalog provider: its entire integration is one JSON\nfile (src/lib/providers/catalog/reka.json) rather than hand-written code.\nThat file is the source of truth for everything on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. Reka's GET https://api.reka.ai/v1/models needs a key (it\nanswers HTTP 401 without one), so the three model ids come from Reka's public\ndocs (Models page, retrieved\n2026-09-29) and the roster has not been checked. No account was created, no\nAPI key was used and no POST request was sent to build it.\nevidence.liveMatrix is null until someone runs the live capability matrix\nwith a real key (see Verification status below).\n\nKey Facts\nProvider id: reka\nEndpoint: /chat/completions — the\n  Quickstart says \"our API is fully\n  OpenAI-compatible\"\nBase URL: https://api.reka.ai/v1\nDefault model: reka-flash\nModels in catalog: 3 — the ids on the Models page (reka-flash,\n  reka-edge, reka-edge-2603)\nStreaming: supported — the\n  Chat overview says \"The Chat API\n  supports streaming\"\nTool calling: model-dependent — the\n  Function Calling page\n  documents the tools parameter and tool_calls, and says \"Currently, only\n  Reka Flash supports function calling.\"\nTools while streaming: not declared (false) — no request combining them\n  was sent\nStructured output: not declared (false) — the ChatRequest on the\n  Chat API reference lists\n  messages, model, frequency_penalty, max_tokens, presence_penalty,\n  seed, stop, stream, temperature, tool_choice, tools, top_k and\n  top_p\nStructured output + tools together: not declared (false) — no combined\n  probe was run without credentials\nEmbeddings: not declared\nThinking: not declared\nVision: reka-flash, reka-edge and reka-edge-2603 are marked\n  vision: true from the vendor's image examples (see Models)\nBilling: billingPolicy holds free-tier, one of the three values the\n  catalog schema allows — the vendor wording is quoted in\n  Billing below\nKey format: none declared\n\nQuick Start\nGet an API key\nVisit: https://platform.reka.ai/sign-up (the \"Start for free\" and \"Get started\" links on https://platform.reka.ai/pricing point to /sign-up). The Quickstart (https://docs.reka.ai/quickstart.md) says \"Create a free account on the Reka Platform to access your API key.\" and the FAQ (https://docs.reka.ai/resources/faqs.md) answers \"How do I get an API key?\" with \"Go to Platform, > API Keys to generate or copy your key.\"\nBilling as the vendor states it: https://docs.reka.ai/pricing.md says \"Get started with no upfront costs.\"; the FAQ (https://docs.reka.ai/resources/faqs.md) answers \"Do I need to pre-pay?\" with \"Yes. Add credits to your account before making requests.\" and says the balance error reads \"P001: Insufficient Balance\" when the balance hits $0\nAuthentication: the vendor's REST examples send the header X-Api-Key (https://docs.reka.ai/chat/overview.md) and the OpenAPI file https://docs.reka.ai/openapi/api-reference.yaml declares one security scheme, an apiKey in the header X-Api-Key; the OpenAI Python SDK examples pass apikey=\"YOURAPI_KEY\" to the client (https://docs.reka.ai/quickstart.md)\nSet REKA_API_KEY in your .env file\nConfigure\nUse it\n\nPer-request credentials work as they do for every provider:\n\nBilling\n\nWhat the vendor's pages say, as opened on 2026-09-29:\nThe Quickstart (https://docs.reka.ai/quickstart.md): \"Create a free account on\n  the Reka Platform to access your API key.\"\nThe FAQ (https://docs.reka.ai/resources/faqs.md), \"Do I need to pre-pay?\":\n  \"Yes. Add credits to your account before making requests.\" It adds that when\n  the balance hits $0 the error reads \"P001: Insufficient Balance\".\nThe API pricing page (https://docs.reka.ai/pricing.md) has a \"Pay as you go\"\n  heading and says \"Get started with no upfront costs. You only pay for what you\n  use.\"\nThe platform pricing page (https://platform.reka.ai/pricing) shows a \"Pay as\n  you go\" tile with the text \"Add credits only when you need them.\" and a \"Start\n  for free\" link to /sign-up; the page also carries the text \"Free credits used\".\n\nbillingPolicy holds free-tier, one of the three values the catalog schema\nallows (free-tier, free-with-card, no-free-tier).\n\nModels\n\n| Model            | Context | Vision | $/M in · out  | Notes                                                                                                                                                                                                         |\n| ---------------- | ------- | ------ | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| reka-flash ⭐  | —       | yes    | $0.80 / $2.00 | NeuroLink default. Named in the code examples of the Chat overview, Function Calling and Chat API reference pages; the pricing page describes \"Reka Flash\" as \"Fast and cost-efficient model for ","hierarchy":{"lvl0":"Getting Started","lvl1":"Reka AI Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"38095f1d07a68493e80f61e00e63dc03b2c3f1f7ddfc60ed826901938191b33e","title":"Reka AI Provider Guide","url":"/docs/getting-started/providers/reka#reka-ai-provider-guide","content":"Reka AI is a Tier-2 catalog provider: its entire integration is one JSON\nfile (src/lib/providers/catalog/reka.json) rather than hand-written code.\nThat file is the source of truth for everything on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. Reka's GET https://api.reka.ai/v1/models needs a key (it\nanswers HTTP 401 without one), so the three model ids come from Reka's public\ndocs (Models page, retrieved\n2026-09-29) and the roster has not been checked. No account was created, no\nAPI key was used and no POST request was sent to build it.\nevidence.liveMatrix is null until someone runs the live capability matrix\nwith a real key (see Verification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"Reka AI Provider Guide","lvl2":"Reka AI Provider Guide","lvl3":""}},
+{"objectID":"b02f09d4dbdb71bc5dad5c0e801689e956e1f45e74e10d9fc471032ab2d34b3e","title":"Key Facts","url":"/docs/getting-started/providers/reka#key-facts","content":"Provider id: reka\nEndpoint: /chat/completions — the\n  Quickstart says \"our API is fully\n  OpenAI-compatible\"\nBase URL: https://api.reka.ai/v1\nDefault model: reka-flash\nModels in catalog: 3 — the ids on the Models page (reka-flash,\n  reka-edge, reka-edge-2603)\nStreaming: supported — the\n  Chat overview says \"The Chat API\n  supports streaming\"\nTool calling: model-dependent — the\n  Function Calling page\n  documents the tools parameter and tool_calls, and says \"Currently, only\n  Reka Flash supports function calling.\"\nTools while streaming: not declared (false) — no request combining them\n  was sent\nStructured output: not declared (false) — the ChatRequest on the\n  Chat API reference lists\n  messages, model, frequency_penalty, max_tokens, presence_penalty,\n  seed, stop, stream, temperature, tool_choice, tools, top_k and\n  top_p\nStructured output + tools together: not declared (false) — no combined\n  probe was run without credentials\nEmbeddings: not declared\nThinking: not declared\nVision: reka-flash, reka-edge and reka-edge-2603 are marked\n  vision: true from the vendor's image examples (see Models)\nBilling: billingPolicy holds free-tier, one of the three values the\n  catalog schema allows — the vendor wording is quoted in\n  Billing below\nKey format: none declared","hierarchy":{"lvl0":"Getting Started","lvl1":"Reka AI Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"387a63f66e05b9721faebe894f1be59d37ca90a54446fb46a92597c11e63392b","title":"1. Get an API key","url":"/docs/getting-started/providers/reka#1-get-an-api-key","content":"Visit: https://platform.reka.ai/sign-up (the \"Start for free\" and \"Get started\" links on https://platform.reka.ai/pricing point to /sign-up). The Quickstart (https://docs.reka.ai/quickstart.md) says \"Create a free account on the Reka Platform to access your API key.\" and the FAQ (https://docs.reka.ai/resources/faqs.md) answers \"How do I get an API key?\" with \"Go to Platform, > API Keys to generate or copy your key.\"\nBilling as the vendor states it: https://docs.reka.ai/pricing.md says \"Get started with no upfront costs.\"; the FAQ (https://docs.reka.ai/resources/faqs.md) answers \"Do I need to pre-pay?\" with \"Yes. Add credits to your account before making requests.\" and says the balance error reads \"P001: Insufficient Balance\" when the balance hits $0\nAuthentication: the vendor's REST examples send the header X-Api-Key (https://docs.reka.ai/chat/overview.md) and the OpenAPI file https://docs.reka.ai/openapi/api-reference.yaml declares one security scheme, an apiKey in the header X-Api-Key; the OpenAI Python SDK examples pass apikey=\"YOURAPI_KEY\" to the client (https://docs.reka.ai/quickstart.md)\nSet REKA_API_KEY in your .env file","hierarchy":{"lvl0":"Getting Started","lvl1":"Reka AI Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"fa1555bea79084e58dc26d47a4b84902ff751b53983cd3d38a46298530cc33ab","title":"3. Use it","url":"/docs/getting-started/providers/reka#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Reka AI Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"14c149de1fbf294e39961c7048587e20abfaeda1f31064d9f15b8afa4b69bc6f","title":"CLI","url":"/docs/getting-started/providers/reka#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider reka\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"reka\",\n  credentials: { reka: { apiKey: process.env.REKAAPIKEY } },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"Reka AI Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"24b90c27fd9b6a0f9aa811dc072f50dcdbc865d66d37e282250e575ad113224e","title":"Billing","url":"/docs/getting-started/providers/reka#billing","content":"What the vendor's pages say, as opened on 2026-09-29:\nThe Quickstart (https://docs.reka.ai/quickstart.md): \"Create a free account on\n  the Reka Platform to access your API key.\"\nThe FAQ (https://docs.reka.ai/resources/faqs.md), \"Do I need to pre-pay?\":\n  \"Yes. Add credits to your account before making requests.\" It adds that when\n  the balance hits $0 the error reads \"P001: Insufficient Balance\".\nThe API pricing page (https://docs.reka.ai/pricing.md) has a \"Pay as you go\"\n  heading and says \"Get started with no upfront costs. You only pay for what you\n  use.\"\nThe platform pricing page (https://platform.reka.ai/pricing) shows a \"Pay as\n  you go\" tile with the text \"Add credits only when you need them.\" and a \"Start\n  for free\" link to /sign-up; the page also carries the text \"Free credits used\".\n\nbillingPolicy holds free-tier, one of the three values the catalog schema\nallows (free-tier, free-with-card, no-free-tier).","hierarchy":{"lvl0":"Getting Started","lvl1":"Reka AI Provider Guide","lvl2":"Billing","lvl3":""}},
+{"objectID":"4ab41102e701a4abfc0245d47b4c2bb799159cfec1967263d3ac1651dae9b9c4","title":"Models","url":"/docs/getting-started/providers/reka#models","content":"| Model            | Context | Vision | $/M in · out  | Notes                                                                                                                                                                                                         |\n| ---------------- | ------- | ------ | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| reka-flash ⭐  | —       | yes    | $0.80 / $2.00 | NeuroLink default. Named in the code examples of the Chat overview, Function Calling and Chat API reference pages; the pricing page describes \"Reka Flash\" as \"Fast and cost-efficient model for most tasks\". |\n| reka-edge      | —       | yes    | $0.10 / $0.10 | Listed as \"reka-edge (or reka-edge-2603)\" on the Models page and the Quickstart; the pricing page describes \"Reka Edge\" as \"Compact model ideal for on-device execution\". Fallback.                           |\n| reka-edge-2603 | —       | yes    | $0.10 / $0.10 | Named in the same table row as reka-edge; the Models page shows it in the example output of GET /v1/models. Vision and prices are those of the reka-edge row.                                           |\n\nModel ids come from https://docs.reka.ai/chat/models.md, which says \"Our baseline\nmodels always available for public access are:\" and lists reka-flash and\nreka-edge (or reka-edge-2603). Prices come from https://docs.reka.ai/pricing.md\n(\"Input Tokens (per 1M)\" and \"Output Tokens (per 1M)\" columns, rows named \"Reka\nFlash\" and \"Reka Edge\"); the Models page says \"For full listing of models and\npricing, see the Reka API Pricing page\".\n\nVision: the first curl example on https://docs.reka.ai/overview.md sends an\nimage_url content part to reka-flash, and the Quickstart's \"First request\"\nexample (https://docs.reka.ai/quickstart.md) sends an image_url content part to\nreka-edge with the comment","hierarchy":{"lvl0":"Getting Started","lvl1":"Reka AI Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"264988d5885746bdddc0250edfc1ff32781c3cea6012cd76b865bc92f2e56941","title":"Verification status","url":"/docs/getting-started/providers/reka#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the catalog\ncurrently records for Reka AI — docs-verified only, not live-verified:\n\n| Probe                     | Result                                                                                                                                                                                                                                                                                                                         |\n| ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| Roster                    | unauthenticated GET /v1/models answered HTTP 401 on 2026-09-29, so the model ids come from https://docs.reka.ai/chat/models.md; roster not verified                                                                                                                                                                      |\n| Auth-failure shape        | the same GET returned the JSON body {\"error\":{\"message\":\"Unauthorized\",\"type\":\"authentication_error\",\"code\":null,\"param\":null}}; evidence.authProbe records status 401 and code authentication_error (the body's error.type, because error.code is null). errorRules match 401, 429, 500 and the FAQ's P001 text |\n| Chat endpoint             | an unauthenticated GET /v1/chat/completions answered HTTP 405 with header allow: POST and body {\"detail\":\"Method Not Allowed\"}; no POST request was sent                                                                                                                                                                 |\n| Billing                   | https://docs.reka.ai/","hierarchy":{"lvl0":"Getting Started","lvl1":"Reka AI Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"571cbf193e411b2b478403e7f7e01ec48075061372c8ca2350399a470729c5de","title":"Troubleshooting","url":"/docs/getting-started/providers/reka#troubleshooting","content":"Each row is the Error Type and Client Action columns of the table on https://docs.reka.ai/errors.md.\n\n| Symptom  | Vendor statement       | Vendor's client action                                                                         |\n| -------- | ---------------------- | ---------------------------------------------------------------------------------------------- |\n| HTTP 401 | authentication_error | \"Ensure that you're using a valid Reka API key\"                                                |\n| HTTP 429 | rate_limit_error     | \"Wait until your rate limit is restored and retry, or upgrade your API tier for higher limits\" |\n| HTTP 500 | server_error         | \"Retry with backoff. If this persists, contact Reka at contact@reka.ai\"                        |","hierarchy":{"lvl0":"Getting Started","lvl1":"Reka AI Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
+{"objectID":"499b23903fab98f2f8ceddc45f2091ae0ac3905c402ac0a0ab16fc11d348ff32","title":"See also","url":"/docs/getting-started/providers/reka#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Reka AI Provider Guide","lvl2":"See also","lvl3":""}},
 {"objectID":"23ac078dd4da3da1822d08cb3542ee6ca5982fdd10438b924f1978b1dbcb9b77","title":"Replicate Provider Guide","url":"/docs/getting-started/providers/replicate","content":"Replicate Provider Guide\n\nOne auth token, five modalities — LLMs + image + video + avatar + music\nunder a single REPLICATE_API_TOKEN\n\nOverview\n\nReplicate is a universal hosted-model gateway. NeuroLink wraps it as a\nmulti-modal provider so a single token gets you:\n\n| Modality      | How                                                                        | Default model                      |\n| ------------- | -------------------------------------------------------------------------- | ---------------------------------- |\n| LLM       | provider: \"replicate\" chat / streaming                                   | meta/meta-llama-3.1-70b-instruct |\n| Image gen | provider: \"replicate\" with a model id matching IMAGE_GENERATION_MODELS | black-forest-labs/flux-1.1-pro   |\n| Video     | output: { mode: \"video\", video: { provider: \"replicate\" } }              | atonamy/wan-alpha                |\n| Avatar    | output: { mode: \"avatar\", avatar: { provider: \"replicate\" } }            | lucataco/musetalk                |\n| Music     | output: { mode: \"music\", music: { provider: \"replicate\" } }              | meta/musicgen                    |\n\nArchitectural detail: see docs/provider-integration/22-adding-multimodal-provider.md — Replicate is the canonical worked example.\n\nKey Facts\nProtocol: Async prediction lifecycle — POST /v1/predictions →\n  poll until succeeded → fetch output. NeuroLink uses\n  Prefer: wait=60 so short jobs complete in the initial POST and skip\n  polling entirely.\nDefault base URL: https://api.replicate.com\nAuth: Authorization: Token $REPLICATE_API_TOKEN\nPricing: Per compute-second (not per-token) — NeuroLink reports a\n  symbolic per-token rate so cost dashboards stay populated, but real\n  billing is via Replicate's invoice\nStreaming: Synthetic single-chunk stream from the predict result\n  (true SSE streaming planned for a follow-up)\nTool calling: Not supported — Replicate predictions are stateless\nReasoning trace: Model-dependent (e.g., DeepSeek R1 on Replicate\n  exposes its reasoning trace in the output array)\n\nQuick Start\nGet an API Token\n\nSign up at https://replicate.com/ and create\nan API token at\nhttps://replicate.com/account/api-tokens.\nConfigure Environment\nGenerate Your First Response\n\nSDK Usage by Modality\n\nLLM (chat / streaming)\n\nStreaming:\n\nImage Generation\n\nOther supported image models on Replicate (pass via model:):\nblack-forest-labs/flux-1.1-pro (default)\nblack-forest-labs/flux-schnell\nstability-ai/stable-diffusion-3.5-large\nstability-ai/stable-diffusion-3.5-large-turbo\nplaygroundai/playground-v2.5-1024px-aesthetic\nideogram-ai/ideogram-v3\n\nVideo Generation\n\nAvatar (MuseTalk)\n\nMusic Generation (MusicGen)\n\nCLI Usage\n\nConfiguration Reference\n\n| Environment Variable  | Required | Default                            | Description                    |\n| --------------------- | -------- | ---------------------------------- | ------------------------------ |\n| REPLICATE_API_TOKEN | Yes      | —                                  | Replicate API token (r8_...) |\n| REPLICATE_MODEL     | No       | meta/meta-llama-3.1-70b-instruct | Default LLM model              |\n| REPLICATE_BASE_URL  | No       | https://api.replicate.com        | Base URL                       |\n\nFeature Support Matrix\n\n| Feature           | LLM                      | Image         | Video             | Avatar | Music |\n| ----------------- | ------------------------ | ------------- | ----------------- | ------ | ----- |\n| Streaming         | Synthetic (single chunk) | N/A           | N/A               | N/A    | N/A   |\n| Tool calling      | No                       | N/A           | N/A               | N/A    | N/A   |\n| Structured output | Limited                  | N/A           | N/A               | N/A    | N/A   |\n| Vision input      | Model-dependent          | Yes (img2img) | Yes (start frame) | Yes    | No    |\n\nCost Notes\n\nReplicate bills by compute seconds, not by tokens. NeuroLink reports\na symbolic per-token rate so cost-attribution dashboards have non-zero\nvalues, but the authoritative billing is from Replicate's own\npricing dashboard.\n\nTroubleshooting\n\n\"Invalid Replicate API token\"\n\nGet / rotate at\nhttps://replicate.com/account/api-tokens.\n\n\"Replicate model 'X' not found\"\n\nUse the owner/name or owner/name:version format. Browse the catalog\nat https://replicate.com/explore.\n\nCold-start delays\n\nFirst-call latency on rare models can spike (the inference container\nneeds to warm). Subsequent calls reuse the warm container. NeuroLink\ncaps polling at 5 minutes by default — bump\nREPLICATE_BASE_URL and Prefer: wait=60 configuration in the lifecycle\nhelper if you regularly hit this.\n\nStreaming feels chunky\n\nThe current implementation runs the prediction synchronously and emits\na single chunk. True SSE streaming is planned — for now use OpenAI / xAI\n/ Groq for low-latency token streaming.\n\nOutput is a URL, not base64\n\nNeuroLink downloads the URL and converts to base64 to keep the\nimageOutput contract uniform. If you see a raw","hierarchy":{"lvl0":"Getting Started","lvl1":"Replicate Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"52425552801d9aeb1b7a7b1a3792894c8d0903d1f2f5d6a28f16d0ac2940f0d6","title":"Replicate Provider Guide","url":"/docs/getting-started/providers/replicate#replicate-provider-guide","content":"One auth token, five modalities — LLMs + image + video + avatar + music\nunder a single REPLICATE_API_TOKEN","hierarchy":{"lvl0":"Getting Started","lvl1":"Replicate Provider Guide","lvl2":"Replicate Provider Guide","lvl3":""}},
 {"objectID":"b258ca5506cf013895d40ece72b1afaf5bc1c4f341849735f4d06095914e9b2e","title":"Overview","url":"/docs/getting-started/providers/replicate#overview","content":"Replicate is a universal hosted-model gateway. NeuroLink wraps it as a\nmulti-modal provider so a single token gets you:\n\n| Modality      | How                                                                        | Default model                      |\n| ------------- | -------------------------------------------------------------------------- | ---------------------------------- |\n| LLM       | provider: \"replicate\" chat / streaming                                   | meta/meta-llama-3.1-70b-instruct |\n| Image gen | provider: \"replicate\" with a model id matching IMAGE_GENERATION_MODELS | black-forest-labs/flux-1.1-pro   |\n| Video     | output: { mode: \"video\", video: { provider: \"replicate\" } }              | atonamy/wan-alpha                |\n| Avatar    | output: { mode: \"avatar\", avatar: { provider: \"replicate\" } }            | lucataco/musetalk                |\n| Music     | output: { mode: \"music\", music: { provider: \"replicate\" } }              | meta/musicgen                    |\n\nArchitectural detail: see docs/provider-integration/22-adding-multimodal-provider.md — Replicate is the canonical worked example.","hierarchy":{"lvl0":"Getting Started","lvl1":"Replicate Provider Guide","lvl2":"Overview","lvl3":""}},
@@ -6855,6 +7009,16 @@
 {"objectID":"7dfad5f669595e5b60f634483324080f1f9c05979e641172d8955be31bdfca19","title":"Verify endpoint status","url":"/docs/getting-started/providers/sagemaker#verify-endpoint-status","content":"aws sagemaker describe-endpoint \\\n  --endpoint-name my-endpoint \\\n  --region us-east-1\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"Amazon SageMaker Provider Guide","lvl2":"Verify endpoint status","lvl3":""}},
 {"objectID":"a94e36be6bd76d0cc347eec562a467b16c6e5e80dc1afd09fd2c485dcecfd625","title":"Related Documentation","url":"/docs/getting-started/providers/sagemaker#related-documentation","content":"AWS Bedrock Provider - Serverless foundation models on AWS (supports streaming and embeddings)\nProvider Setup - General provider configuration\nHugging Face Provider - Direct Hugging Face Inference API access","hierarchy":{"lvl0":"Getting Started","lvl1":"Amazon SageMaker Provider Guide","lvl2":"Related Documentation","lvl3":""}},
 {"objectID":"ed525641c5fafea19eea16784251d4ca1c2aa9b0ad5ae1926eba282b65ed9b7b","title":"Additional Resources","url":"/docs/getting-started/providers/sagemaker#additional-resources","content":"SageMaker Docs - Official documentation\nSageMaker Pricing - Instance and inference pricing\nSageMaker Console - Manage endpoints\nJumpStart Models - Pre-built model catalog\nHugging Face on SageMaker - Deploy HF models to SageMaker\n\nNeed Help? Join our GitHub Discussions or open an issue.","hierarchy":{"lvl0":"Getting Started","lvl1":"Amazon SageMaker Provider Guide","lvl2":"Additional Resources","lvl3":""}},
+{"objectID":"c69e13f51b8da8fb7cdbb5637c4d539fbb7038f943221a5cd7114f4407d8ce46","title":"Sakana AI Provider Guide","url":"/docs/getting-started/providers/sakana-ai","content":"Sakana AI Provider Guide\n\nSakana AI is a Tier-2 catalog provider: it is expressed as OpenAI-wire-compatible\nwith no quirks block, so its entire integration is one JSON file\n(src/lib/providers/catalog/sakana-ai.json) rather than hand-written code.\nThat file is the source of truth for the facts on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's GET https://api.sakana.ai/v1/models needs a\nkey (it answers HTTP 401 without one), so the model ids come from Sakana AI's\npublic Models page and the roster has not been checked. No account was created\nand no API key was used to build it. evidence.liveMatrix is null until\nsomeone runs the live capability matrix with a real key (see\nVerification status below).\n\nKey Facts\nProvider id: sakana-ai (alias sakana)\nProtocol: OpenAI-compatible (/chat/completions). The Models page\n  (console.sakana.ai/models) also lists\n  Responses, Models and Anthropic-compatible Messages endpoints and says: \"For\n  generation requests, we strongly recommend using the Responses API, for better\n  performance.\" This entry sends /chat/completions, which the same page\n  documents with the line \"Use /v1/chat/completions when you want the OpenAI\n  Chat Completions API shape.\"\nBase URL: https://api.sakana.ai/v1 (the Get Started page,\n  console.sakana.ai/get-started, shows\n  the OpenAI Python SDK with base_url = \"https://api.sakana.ai/v1\")\nDefault model: fugu\nModels in catalog: 9, copied from the Supported models table on the Models\n  page. The table's other two ids, fugu-cyber and fugu-cyber-v1.0, are left\n  out of the catalog: the page says \"In order to use Fugu Cyber, users must\n  submit an access request form detailing their intended use case and providing\n  verified contact information.\"\nStreaming: supported — the Chat Completions field table lists stream\n  (\"Stream the response.\"), and the Sakana Namazu tab lists Streaming as\n  \"Supported\"\nTool calling: model-dependent — the Chat Completions field tables list\n  tools (\"Tool definitions the model may call.\") and tool_choice for Fugu,\n  and tools (\"Function tool definitions or built-in tools\") for Sakana Namazu;\n  not exercised with a key\nTools while streaming: not declared (false) — no page documents tools\n  and streaming together\nStructured output: supported — the Fugu Chat Completions table lists\n  response_format (\"Structured output with text, json_object, or\n  jsonschema.\"), and the Sakana Namazu tab lists \"jsonschema and json_object\"\nStructured output + tools together: not declared (false) — no combined\n  probe was run without credentials\nEmbeddings: not declared\nThinking: declared — the Fugu Chat Completions table lists\n  reasoning_effort with an effort value of high, xhigh or max, and the\n  Sakana Namazu tab says \"Sakana Namazu supports extended thinking\". Neither was\n  exercised through NeuroLink\nBilling: catalog value no-free-tier. The Pricing page\n  (console.sakana.ai/pricing) lists Pay as\n  you go rates per model and three Subscription Plans (Standard $20/month, Pro\n  $100/month, Max $200/month)\nKey format: none declared. The Get Started page's Claude Code example\n  writes the key as \"fish_...\" with the comment # your Sakana key; NeuroLink\n  does not validate a prefix\n\nQuick Start\nGet an API key\nVisit: https://console.sakana.ai/overview and sign in - the page shows \"Login with Google\" and \"Send login link\"\nCreate an API key - the Get Started page (https://console.sakana.ai/get-started) says: \"Before using Fugu or Sakana Namazu, create an API key and copy the generated key. The key is shown only once, so store it somewhere secure before closing the dialog.\"\nBilling as the vendor states it: the Pricing page (https://console.sakana.ai/pricing) lists Pay as you go rates per model and Subscription Plans (Standard $20/month, Pro $100/month, Max $200/month); the Get Started page says Sakana Namazu \"is billed purely on a pay-as-you-go (per-token) basis.\"\nSet SAKANA_AI_API_KEY in your .env file (SAKANA_API_KEY, which the Get Started page's curl example reads, is accepted as a fallback; the Models page's Python example reads FUGU_API_KEY and FUGU_BASE_URL, which NeuroLink does not)\nConfigure\nUse it\n\nPer-request credentials work as they do for other providers:\n\nModels\n\n| Model                | Context | Vision | $/M in · out (cached) | Notes                                                                                                           |\n| -------------------- | ------- | ------ | --------------------- | --------------------------------------------------------------------------------------------------------------- |\n| fugu ⭐            | 1M      | yes    | not recorded          | NeuroLink default. Models page: \"The default Fugu model.\" Fugu overview: \"the ideal default for everyday work.\" |\n| fugu-ultra         | 1M      | yes    | $5 / $30 ($0.50)      | Models page: \"The Fugu Ultra model, defaults to fugu-ultra-v2.0.\" Priced as fugu-ultra-v2.0.                  |\n| fugu-ultra-v2.0  ","hierarchy":{"lvl0":"Getting Started","lvl1":"Sakana AI Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"4bdbaf980cae430df988750cb1409d7f9d280437fd98e5bd73ac538154f2e5d0","title":"Sakana AI Provider Guide","url":"/docs/getting-started/providers/sakana-ai#sakana-ai-provider-guide","content":"Sakana AI is a Tier-2 catalog provider: it is expressed as OpenAI-wire-compatible\nwith no quirks block, so its entire integration is one JSON file\n(src/lib/providers/catalog/sakana-ai.json) rather than hand-written code.\nThat file is the source of truth for the facts on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's GET https://api.sakana.ai/v1/models needs a\nkey (it answers HTTP 401 without one), so the model ids come from Sakana AI's\npublic Models page and the roster has not been checked. No account was created\nand no API key was used to build it. evidence.liveMatrix is null until\nsomeone runs the live capability matrix with a real key (see\nVerification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"Sakana AI Provider Guide","lvl2":"Sakana AI Provider Guide","lvl3":""}},
+{"objectID":"dde3b7fa1971790ee9b9926cdb09e6cf3ad3e0fc9f0916b3f41a5104b78649d2","title":"Key Facts","url":"/docs/getting-started/providers/sakana-ai#key-facts","content":"Provider id: sakana-ai (alias sakana)\nProtocol: OpenAI-compatible (/chat/completions). The Models page\n  (console.sakana.ai/models) also lists\n  Responses, Models and Anthropic-compatible Messages endpoints and says: \"For\n  generation requests, we strongly recommend using the Responses API, for better\n  performance.\" This entry sends /chat/completions, which the same page\n  documents with the line \"Use /v1/chat/completions when you want the OpenAI\n  Chat Completions API shape.\"\nBase URL: https://api.sakana.ai/v1 (the Get Started page,\n  console.sakana.ai/get-started, shows\n  the OpenAI Python SDK with base_url = \"https://api.sakana.ai/v1\")\nDefault model: fugu\nModels in catalog: 9, copied from the Supported models table on the Models\n  page. The table's other two ids, fugu-cyber and fugu-cyber-v1.0, are left\n  out of the catalog: the page says \"In order to use Fugu Cyber, users must\n  submit an access request form detailing their intended use case and providing\n  verified contact information.\"\nStreaming: supported — the Chat Completions field table lists stream\n  (\"Stream the response.\"), and the Sakana Namazu tab lists Streaming as\n  \"Supported\"\nTool calling: model-dependent — the Chat Completions field tables list\n  tools (\"Tool definitions the model may call.\") and tool_choice for Fugu,\n  and tools (\"Function tool definitions or built-in tools\") for Sakana Namazu;\n  not exercised with a key\nTools while streaming: not declared (false) — no page documents tools\n  and streaming together\nStructured output: supported — the Fugu Chat Completions table lists\n  response_format (\"Structured output with text, json_object, or\n  jsonschema.\"), and the Sakana Namazu tab lists \"jsonschema and json_object\"\nStructured output + tools together: not declared (false) — no combined\n  probe was run without credentials\nEmbeddings: not declared\nThinking: declared — the Fugu Chat Completions table lists\n  reasoning_effort with an effort value of high, xhigh or max, and the\n  Sakana Namazu","hierarchy":{"lvl0":"Getting Started","lvl1":"Sakana AI Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"a79c3e494e2b89617d3a74499a627e61a75ed99459bd3971bb5f64e5c514c151","title":"1. Get an API key","url":"/docs/getting-started/providers/sakana-ai#1-get-an-api-key","content":"Visit: https://console.sakana.ai/overview and sign in - the page shows \"Login with Google\" and \"Send login link\"\nCreate an API key - the Get Started page (https://console.sakana.ai/get-started) says: \"Before using Fugu or Sakana Namazu, create an API key and copy the generated key. The key is shown only once, so store it somewhere secure before closing the dialog.\"\nBilling as the vendor states it: the Pricing page (https://console.sakana.ai/pricing) lists Pay as you go rates per model and Subscription Plans (Standard $20/month, Pro $100/month, Max $200/month); the Get Started page says Sakana Namazu \"is billed purely on a pay-as-you-go (per-token) basis.\"\nSet SAKANA_AI_API_KEY in your .env file (SAKANA_API_KEY, which the Get Started page's curl example reads, is accepted as a fallback; the Models page's Python example reads FUGU_API_KEY and FUGU_BASE_URL, which NeuroLink does not)","hierarchy":{"lvl0":"Getting Started","lvl1":"Sakana AI Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"f22b087503a18d5a914c318566c855ca3080b27e48825f347c21cc8bb8c1a7ab","title":"3. Use it","url":"/docs/getting-started/providers/sakana-ai#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Sakana AI Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"fdaedc58934888426c133d7ca6720684d6dc4bdf794d2988f2cf0b3cfc8f0ee3","title":"CLI","url":"/docs/getting-started/providers/sakana-ai#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider sakana-ai\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"sakana-ai\",\n  credentials: { sakanaAi: { apiKey: process.env.SAKANAAIAPI_KEY } },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"Sakana AI Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"8ca144dc917802207afd38cbc11d00b848ca9e06de82ad373420e8883f156ac3","title":"Models","url":"/docs/getting-started/providers/sakana-ai#models","content":"| Model                | Context | Vision | $/M in · out (cached) | Notes                                                                                                           |\n| -------------------- | ------- | ------ | --------------------- | --------------------------------------------------------------------------------------------------------------- |\n| fugu ⭐            | 1M      | yes    | not recorded          | NeuroLink default. Models page: \"The default Fugu model.\" Fugu overview: \"the ideal default for everyday work.\" |\n| fugu-ultra         | 1M      | yes    | $5 / $30 ($0.50)      | Models page: \"The Fugu Ultra model, defaults to fugu-ultra-v2.0.\" Priced as fugu-ultra-v2.0.                  |\n| fugu-ultra-v2.0    | 1M      | yes    | $5 / $30 ($0.50)      | Models page: \"V2.0 of Fugu Ultra.\" Pricing page: \"Fixed pricing for fugu-ultra-v2.0 per 1M tokens.\"             |\n| fugu-ultra-v1.1    | 1M      | yes    | not recorded          | Models page: \"V1.1 of Fugu Ultra.\"                                                                              |\n| fugu-ultra-v1.0    | 1M      | yes    | not recorded          | Models page: \"V1.0 of Fugu Ultra, also known as fugu-ultra-20260615.\"                                           |\n| fugu-max           | 1M      | yes    | $2 / $6 ($0.25)       | Models page: \"The Fugu Max model, defaults to fugu-max-v1.0.\" Priced as fugu-max-v1.0.                        |\n| fugu-max-v1.0      | 1M      | yes    | $2 / $6 ($0.25)       | Models page: \"V1.0 of Fugu Max, optimized for cost-performance.\" Pricing page: \"regardless of context length.\"  |\n| sakana-namazu      | 256K    | yes    | $0.95 / $4.00 ($0.15) | Models page: \"Alias that points to the latest version (currently sakana-namazu-v1.0).\"                          |\n| sakana-namazu-v1.0 | 256K    | yes    | $0.95 / $4.00 ($0.15) | Models page: \"V1.0 of the Sakana Namazu model. A Japanese-specialized LLM.\"                                     |\n\nSources. Model ids c","hierarchy":{"lvl0":"Getting Started","lvl1":"Sakana AI Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"e440f8a3944119705452b4e4b314c23399667042fd12fc2172a73c7fdce92e43","title":"Verification status","url":"/docs/getting-started/providers/sakana-ai#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the catalog\ncurrently records for Sakana AI — docs-verified only, not yet\nlive-verified:\n\n| Probe                     | Result                                                                                                                                                                                                                                                                                                                                                                                   |\n| ------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                    | unauthenticated GET https://api.sakana.ai/v1/models answers HTTP 401 without a key, 2026-09-29 — model ids are taken from https://console.sakana.ai/models; the roster has not been checked                                                                                                                                                                                            |\n| Auth-failure shape        | unauthenticated GET /v1/models returned HTTP 401 with JSON body {\"error\":{\"message\":\"Missing API key\",\"type\":\"authentication_error\",\"param\":null,\"code\":null}}, 2026-09-29; errorRules holds one rule, for status 401, and evidence.authProbe.code records the body's error.type because error.code is null. An unauthenticated GET /v1/chat/completions answered HTTP 405 |\n| Billing                   | the Pricing page lists Pay as you go rates and Subscription Plans at $20/month, $100/month and $200/month; the Get Started p","hierarchy":{"lvl0":"Getting Started","lvl1":"Sakana AI Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"535b640f9827b93ee1fc1989ffeddfb34f93243c908cea478eeb2490872a8aa3","title":"Troubleshooting","url":"/docs/getting-started/providers/sakana-ai#troubleshooting","content":"Each row below is a statement from a Sakana AI page or the observed response\nbody; NeuroLink has not exercised them with a key.\n\n| Symptom                                         | What the vendor page or response says                                                                                                                                                 | Source                                   |\n| ----------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------- |\n| HTTP 401 with error.message \"Missing API key\" | Body returned by an unauthenticated GET https://api.sakana.ai/v1/models on 2026-09-29; the Get Started page's curl example sends the header Authorization: Bearer $SAKANA_API_KEY | api.sakana.ai response; Get Started page |\n| Client-side timeouts with fugu-ultra          | \"For complex tasks, especially when using fugu-ultra and fugu-cyber, you may need to increase client-side timeouts.\"                                                                  | Get Started page                         |\n| sakana-namazu requests and a subscription     | \"Sakana Namazu is not included in subscription plans — it is billed purely on a pay-as-you-go (per-token) basis.\"                                                                     | Get Started page                         |\n| A fugu-cyber id is needed                     | \"In order to use Fugu Cyber, users must submit an access request form detailing their intended use case and providing verified contact information.\"                                  | Models page                              |\n| Sampling fields have no effect                  | The Fugu Chat Completions table lists temperature, top_p, stop, seed, frequency_penalty and presence_penalty as \"Accepted but ignored.\"                      ","hierarchy":{"lvl0":"Getting Started","lvl1":"Sakana AI Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
+{"objectID":"678b820278936bd9c76c4a1d812d401ef54b3d4c8d8c4cc49e01bc30c37f9ce3","title":"See also","url":"/docs/getting-started/providers/sakana-ai#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Sakana AI Provider Guide","lvl2":"See also","lvl3":""}},
 {"objectID":"0a26140d8305e97ec7c162263ae7f808cc4d3d7d6a9e6854f8b69200332a577e","title":"SambaNova Provider Guide","url":"/docs/getting-started/providers/sambanova","content":"SambaNova Provider Guide\n\nOpen-weight flagships (Llama 3.3 70B, GPT-OSS 120B, DeepSeek V3.x,\nMiniMax, Gemma 4) on SambaNova's RDU-accelerated cloud\n\nOverview\n\nSambaNova Cloud serves open-weight models on its Reconfigurable Dataflow\nUnits. NeuroLink wraps api.sambanova.ai/v1 (OpenAI-compatible,\nzero-quirk Tier 2 catalog entry) so the standard generate / stream\ncontract applies.\n\nRoster verified against a live authenticated /v1/models on 2026-08-27:\nMeta-Llama-3.3-70B-Instruct (default) — production, 128K context\ngpt-oss-120b — production, 128K context\nDeepSeek-V3.1 — production reasoning model, 128K context\nDeepSeek-V3.2 — vendor preview, 32K context\nMiniMax-M2.7 — production, 192K context\nMiniMax-M3 — vision-capable per the vendor dashboard\ngemma-4-31B-it — vendor preview; vision (text + image + video)\n\nKey Facts\nProtocol: OpenAI-compatible (/v1/chat/completions)\nDefault base URL: https://api.sambanova.ai/v1\nDefault model: Meta-Llama-3.3-70B-Instruct\nVision: gemma-4-31B-it (image + video) and MiniMax-M3\nStreaming / tool calling: per the OpenAI-compatible contract\n⚠️ Billing (probed live 2026-08-27): new accounts have no free\n  allowance — every call returns 402 PAYMENT_METHOD_REQUIRED\n  (balance_units: 0) until a payment method is added and credits are\n  purchased at cloud.sambanova.ai/plans/billing.\n  The onboarding wizard's payment step may show \"temporarily\n  unavailable\" — use the Billing page instead.\nPricing (per million tokens, vendor pricing page 2026-08-27):\n  Llama-3.3-70B $0.60/$1.20 · gpt-oss-120b $0.22/$0.59 ·\n  DeepSeek-V3.x $3.00/$4.50 · MiniMax $0.60/$2.40 ·\n  gemma-4-31B-it $0.38/$1.15\nAPI keys are bare UUIDs (no sk--style prefix) — keep them out of\n  logs; NeuroLink's Authorization-header redaction covers them.\n\nQuick Start\nGet an API Key\n\nSign up at https://cloud.sambanova.ai\n(Google/Microsoft OAuth), complete the profile step, add a payment\nmethod + credits under Plans → Billing, and create a key under\nAPI Keys.\nConfigure Environment\nGenerate Your First Response\n\nCLI Usage\n\nConfiguration Reference\n\n| Environment Variable | Required | Default                       | Description       |\n| -------------------- | -------- | ----------------------------- | ----------------- |\n| SAMBANOVA_API_KEY  | Yes      | —                             | SambaNova API key |\n| SAMBANOVA_MODEL    | No       | Meta-Llama-3.3-70B-Instruct | Default model     |\n| SAMBANOVA_BASE_URL | No       | https://api.sambanova.ai/v1 | Base URL          |\n\nTroubleshooting\n\n402 on every call / \"PAYMENTMETHODREQUIRED\"\n\nThe account has no credits — new accounts have no free allowance.\nAdd a payment method and purchase credits at\ncloud.sambanova.ai/plans/billing.\n\n\"Invalid SambaNova API key\"\n\nRotate at cloud.sambanova.ai/apis. A\nbad key returns an OpenAI-shaped 401 with \"code\": \"invalid_api_key\".\n\n404 for a model that used to exist\n\nPreview models (DeepSeek-V3.2, gemma-4-31B-it) \"may be removed at\nshort notice\" per the vendor. Verify with an authenticated\nGET https://api.sambanova.ai/v1/models.\n\nSee Also\nCerebras Provider — sibling wafer-scale speed provider\nGroq Provider — sibling LPU speed provider\nTier 2 catalog entry guide — internal wiring\n\nNeed Help? Open a GitHub Discussion or issue.","hierarchy":{"lvl0":"Getting Started","lvl1":"SambaNova Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"afb11b7e78791febba1752f0315138e0323159b838468f4d5b291f5d4646a7ac","title":"SambaNova Provider Guide","url":"/docs/getting-started/providers/sambanova#sambanova-provider-guide","content":"Open-weight flagships (Llama 3.3 70B, GPT-OSS 120B, DeepSeek V3.x,\nMiniMax, Gemma 4) on SambaNova's RDU-accelerated cloud","hierarchy":{"lvl0":"Getting Started","lvl1":"SambaNova Provider Guide","lvl2":"SambaNova Provider Guide","lvl3":""}},
 {"objectID":"32d8042b72d676ef0f4f025a61c7f62d2a0aa2289c6971e318919545188931de","title":"Overview","url":"/docs/getting-started/providers/sambanova#overview","content":"SambaNova Cloud serves open-weight models on its Reconfigurable Dataflow\nUnits. NeuroLink wraps api.sambanova.ai/v1 (OpenAI-compatible,\nzero-quirk Tier 2 catalog entry) so the standard generate / stream\ncontract applies.\n\nRoster verified against a live authenticated /v1/models on 2026-08-27:\nMeta-Llama-3.3-70B-Instruct (default) — production, 128K context\ngpt-oss-120b — production, 128K context\nDeepSeek-V3.1 — production reasoning model, 128K context\nDeepSeek-V3.2 — vendor preview, 32K context\nMiniMax-M2.7 — production, 192K context\nMiniMax-M3 — vision-capable per the vendor dashboard\ngemma-4-31B-it — vendor preview; vision (text + image + video)","hierarchy":{"lvl0":"Getting Started","lvl1":"SambaNova Provider Guide","lvl2":"Overview","lvl3":""}},
@@ -6925,6 +7089,17 @@
 {"objectID":"bd256729471a6ae227bef035d51cf425ded61c9a4145c59e13d3b719f852331d","title":"\"Stability AI returned no image\"","url":"/docs/getting-started/providers/stability#stability-ai-returned-no-image","content":"The upstream returned finish_reason: ERROR without an image. Check\nthe prompt for malformed Unicode or excessive length (>2000 chars).","hierarchy":{"lvl0":"Getting Started","lvl1":"Stability AI Provider Guide","lvl2":"\"Stability AI returned no image\"","lvl3":""}},
 {"objectID":"1fd8be6678a7d6a015a5f79c9c42456826928baa9cd68a5ce04aa90b23377005","title":"\"Model not found\"","url":"/docs/getting-started/providers/stability#model-not-found","content":"Use one of the documented model IDs: stable-image-ultra,\nstable-image-core, sd3.5-large, sd3.5-large-turbo, sd3.5-medium.\nNote: some older Stability models (SDXL 1.0, Stable Diffusion 1.5) are\ndeprecated on the hosted API — use Replicate to access them.","hierarchy":{"lvl0":"Getting Started","lvl1":"Stability AI Provider Guide","lvl2":"\"Model not found\"","lvl3":""}},
 {"objectID":"5b8749a23300892944984a006ceeaf7f3749c9cc330e70ec111e4dfa2303e9d2","title":"See Also","url":"/docs/getting-started/providers/stability#see-also","content":"Ideogram — sibling image-gen with strong typography (no setup doc yet; see src/lib/providers/ideogram.ts)\nRecraft — sibling image-gen with vector / illustration focus (no setup doc yet; see src/lib/providers/recraft.ts)\nReplicate Provider — image-gen via FLUX, SDXL variants, etc.\nAdding an image-gen provider — internal reference\n\nNeed Help? Open a GitHub Discussion or issue.","hierarchy":{"lvl0":"Getting Started","lvl1":"Stability AI Provider Guide","lvl2":"See Also","lvl3":""}},
+{"objectID":"8334c0b197bc2c3a43c0c92b36f1227639337423dbc20127ea54cccc9bc28bfe","title":"STACKIT Provider Guide","url":"/docs/getting-started/providers/stackit","content":"STACKIT Provider Guide\n\nSTACKIT is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/stackit.json) rather than hand-written code.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. STACKIT's GET /models needs a key (an unauthenticated\nGET /v1/models on 2026-09-29 answered HTTP 403), so the model ids come from\nSTACKIT's public documentation and the roster has not been checked. No\naccount was created and no API key was used to build it.\nevidence.liveMatrix is null until someone runs the live capability\nmatrix with a real key (see Verification status\nbelow).\n\nKey Facts\nProvider id: stackit\nProtocol: OpenAI-compatible (/chat/completions) — the model rows on\n  the Available Shared Models\n  page show Specification \"OpenAI-compatible\" and the endpoints\n  POST /chat/completions, POST /completions and GET /models. The sample\n  reply shown under the POST /v1/chat/completions curl request on the\n  Getting started\n  page reads \"object\":\"text_completion\" and \"choices\":[{\"index\":0,\"text\":;\n  no POST request was sent while building this entry\nBase URL: https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1\nDefault model: Qwen/Qwen3-VL-235B-A22B-Instruct-FP8\nModels in catalog: 6 chat models, taken from the \"Full Name:\" headings\n  of the Available Shared Models page (retrieved 2026-09-29)\nStreaming: not declared (false); no streaming request was sent\nTool calling: model-dependent. The Features cell reads \"Tool calling\n  enabled\" on the Qwen3-VL 235B and Llama 3.3 70B rows and \"Tool calling &\n  Reasoning enabled\" on the other four catalogued rows. The\n  tool-calling how-to\n  is a LangChain example that prints tool_call_response.tool_calls\nTools while streaming: not declared (false)\nStructured output: not declared (false). The release note of Dec 10,\n  2025 says of openai/gpt-oss-120b: \"The model provides full\n  chain-of-thought (CoT) and support Structured Outputs.\" The catalog's\n  structuredOutput flag applies to the provider as a whole, so it stays\n  false\nStructured output + tools together: not declared (false) — no\n  combined probe was run without credentials\nEmbeddings: not declared on this catalog entry. STACKIT does list two\n  embedding models with a POST /embeddings endpoint\n  (intfloat/e5-mistral-7b-instruct, Qwen/Qwen3-VL-Embedding-8B), but\n  NeuroLink's generic ConfiguredOpenAICompatProvider does not implement\n  embed()/embedMany(), so this flag tracks that, not the vendor's own API\n  surface\nThinking: not declared (false); the per-model Features text is\n  recorded in the table below\nBilling: no-free-tier — see Billing below\nKey format: none declared\n\nQuick Start\nGet an API key\nVisit: https://portal.stackit.cloud and log in to the customer portal — the Getting started page says \"To enable AI Model Serving login to the Customer portal and click at the sidebar on the left on AI Model Serving.\" and lists a STACKIT customer account, a STACKIT user account and a STACKIT project as prerequisites\nEnable AI Model Serving, click Create token, enter a token name and optionally a lifetime in days, and confirm with \"Order fee-based\" (\"To confirm click on Order fee-based.\"); the same page says \"You can not retrieve the token again after closing the pane\", so copy it when it is shown\nBilling as the vendor states it: the May 6, 2025 release note says \"STACKIT AI Model Serving offers you easy pay-as-you-go access to proven GenAI models\"; the product page offers \"Register for a free trial access\" — see Billing\nSet STACKIT_API_KEY in your .env file (the docs' examples read STACKIT_MODEL_SERVING_AUTH_TOKEN and STACKIT_MODEL_SERVING_API_KEY, which NeuroLink does not read)\nConfigure\nUse it\n\nPer-request credentials:\n\nBilling\n\nWhat the vendor's pages state, quoted as they appear:\nGetting started, token creation: \"To confirm click on Order fee-based.\" The\n  Manage auth tokens page's token-creation steps say \"Click on Order\n  fee-based.\"\nRelease note, May 6, 2025: \"STACKIT AI Model Serving offers you easy\n  pay-as-you-go access to proven GenAI models\"\nProduct page,\n  advantages list: \"Operate GenAI applications cost-effectively with our\n  token-based billing.\"\nProduct page, heading \"Register for a free trial access\": \"All registrations\n  are manually checked by us. If you qualify, you will receive your personal\n  token to use STACKIT AI Model Serving within 24 hours. The trial period ends\n  automatically after 30 days.\"\n\nThe product page's \"STACKIT AI Model Serving price table\" (Region cell\n\"Germany South\") shows these text-model rows, quoted as the cells read:\n\n| SKU                                      | Billing          | \"Price per hour\" cell |\n| ---------------------------------------- | ---------------- | --------------------- |\n| Model Serving-llm-standard-input-EU01  | mio input token  | 0.15000000000 €       |\n| Model Serving-llm-standard-output-EU01 | mio output token | 0.25000000000 €       |\n| Model Serving-llm-plus-input-EU01      | mio input token  | 0","hierarchy":{"lvl0":"Getting Started","lvl1":"STACKIT Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"d38ef6729b2b32860b1efc87cc28fbb29a45279dabacb94e328725ad6468b98f","title":"STACKIT Provider Guide","url":"/docs/getting-started/providers/stackit#stackit-provider-guide","content":"STACKIT is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/stackit.json) rather than hand-written code.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. STACKIT's GET /models needs a key (an unauthenticated\nGET /v1/models on 2026-09-29 answered HTTP 403), so the model ids come from\nSTACKIT's public documentation and the roster has not been checked. No\naccount was created and no API key was used to build it.\nevidence.liveMatrix is null until someone runs the live capability\nmatrix with a real key (see Verification status\nbelow).","hierarchy":{"lvl0":"Getting Started","lvl1":"STACKIT Provider Guide","lvl2":"STACKIT Provider Guide","lvl3":""}},
+{"objectID":"92da5f2d9215b695a1041528ce1f37565c3e5b67fff20abfb7bfe6b8323f09b2","title":"Key Facts","url":"/docs/getting-started/providers/stackit#key-facts","content":"Provider id: stackit\nProtocol: OpenAI-compatible (/chat/completions) — the model rows on\n  the Available Shared Models\n  page show Specification \"OpenAI-compatible\" and the endpoints\n  POST /chat/completions, POST /completions and GET /models. The sample\n  reply shown under the POST /v1/chat/completions curl request on the\n  Getting started\n  page reads \"object\":\"text_completion\" and \"choices\":[{\"index\":0,\"text\":;\n  no POST request was sent while building this entry\nBase URL: https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1\nDefault model: Qwen/Qwen3-VL-235B-A22B-Instruct-FP8\nModels in catalog: 6 chat models, taken from the \"Full Name:\" headings\n  of the Available Shared Models page (retrieved 2026-09-29)\nStreaming: not declared (false); no streaming request was sent\nTool calling: model-dependent. The Features cell reads \"Tool calling\n  enabled\" on the Qwen3-VL 235B and Llama 3.3 70B rows and \"Tool calling &\n  Reasoning enabled\" on the other four catalogued rows. The\n  tool-calling how-to\n  is a LangChain example that prints tool_call_response.tool_calls\nTools while streaming: not declared (false)\nStructured output: not declared (false). The release note of Dec 10,\n  2025 says of openai/gpt-oss-120b: \"The model provides full\n  chain-of-thought (CoT) and support Structured Outputs.\" The catalog's\n  structuredOutput flag applies to the provider as a whole, so it stays\n  false\nStructured output + tools together: not declared (false) — no\n  combined probe was run without credentials\nEmbeddings: not declared on this catalog entry. STACKIT does list two\n  embedding models with a POST /embeddings endpoint\n  (intfloat/e5-mistral-7b-instruct, Qwen/Qwen3-VL-Embedding-8B), but\n  NeuroLink's generic ConfiguredOpenAICompatProvider does not implement\n  embed()/embedMany(), so this flag tracks that, not the vendor's own API\n  surface\nThinking: not declared (false); the per-model Features text is\n  recorded in the table below\nBilling: no-free-tier — see Billing below\n","hierarchy":{"lvl0":"Getting Started","lvl1":"STACKIT Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"5295d30055f6828923c94b598c19629b49a25f96cb94049a4047f65a22e1de92","title":"1. Get an API key","url":"/docs/getting-started/providers/stackit#1-get-an-api-key","content":"Visit: https://portal.stackit.cloud and log in to the customer portal — the Getting started page says \"To enable AI Model Serving login to the Customer portal and click at the sidebar on the left on AI Model Serving.\" and lists a STACKIT customer account, a STACKIT user account and a STACKIT project as prerequisites\nEnable AI Model Serving, click Create token, enter a token name and optionally a lifetime in days, and confirm with \"Order fee-based\" (\"To confirm click on Order fee-based.\"); the same page says \"You can not retrieve the token again after closing the pane\", so copy it when it is shown\nBilling as the vendor states it: the May 6, 2025 release note says \"STACKIT AI Model Serving offers you easy pay-as-you-go access to proven GenAI models\"; the product page offers \"Register for a free trial access\" — see Billing\nSet STACKIT_API_KEY in your .env file (the docs' examples read STACKIT_MODEL_SERVING_AUTH_TOKEN and STACKIT_MODEL_SERVING_API_KEY, which NeuroLink does not read)","hierarchy":{"lvl0":"Getting Started","lvl1":"STACKIT Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"3fc43578f705713ac3b3ecbe7b46aed90695f8458029438f9b28c35085773501","title":"3. Use it","url":"/docs/getting-started/providers/stackit#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"STACKIT Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"deff752327b7958981733893105a739bb4ce973ed4d69cd4f65e12904b8b05c1","title":"CLI","url":"/docs/getting-started/providers/stackit#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider stackit\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"stackit\",\n  credentials: { stackit: { apiKey: process.env.STACKITAPIKEY } },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"STACKIT Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"ac5e2fda929bb3802dcf5af9a6623421a5fc1b58839ef6a9a52784802f3c44b0","title":"Billing","url":"/docs/getting-started/providers/stackit#billing","content":"What the vendor's pages state, quoted as they appear:\nGetting started, token creation: \"To confirm click on Order fee-based.\" The\n  Manage auth tokens page's token-creation steps say \"Click on Order\n  fee-based.\"\nRelease note, May 6, 2025: \"STACKIT AI Model Serving offers you easy\n  pay-as-you-go access to proven GenAI models\"\nProduct page,\n  advantages list: \"Operate GenAI applications cost-effectively with our\n  token-based billing.\"\nProduct page, heading \"Register for a free trial access\": \"All registrations\n  are manually checked by us. If you qualify, you will receive your personal\n  token to use STACKIT AI Model Serving within 24 hours. The trial period ends\n  automatically after 30 days.\"\n\nThe product page's \"STACKIT AI Model Serving price table\" (Region cell\n\"Germany South\") shows these text-model rows, quoted as the cells read:\n\n| SKU                                      | Billing          | \"Price per hour\" cell |\n| ---------------------------------------- | ---------------- | --------------------- |\n| Model Serving-llm-standard-input-EU01  | mio input token  | 0.15000000000 €       |\n| Model Serving-llm-standard-output-EU01 | mio output token | 0.25000000000 €       |\n| Model Serving-llm-plus-input-EU01      | mio input token  | 0.45000000000 €       |\n| Model Serving-llm-plus-output-EU01     | mio output token | 0.65000000000 €       |\n| Model Serving-llm-premium-input-EU01   | mio input token  | 1.50000000000 €       |\n| Model Serving-llm-premium-output-EU01  | mio output token | 1.75000000000 €       |\n\nThe Available Shared Models page gives each chat model a Category cell\n(LLM-Premium, LLM-Plus or LLM-Standard), shown in the table below.\n\nThe entry records billingPolicy: no-free-tier because the catalog schema\ntakes one of three values and the token-creation step says \"To confirm click\non Order fee-based.\"; the free trial above is a separate, manually checked\nregistration. The entry leaves pricingPerMTok empty: the vendor's prices are\nin euro and are ","hierarchy":{"lvl0":"Getting Started","lvl1":"STACKIT Provider Guide","lvl2":"Billing","lvl3":""}},
+{"objectID":"bd4d6266e4412714c606d420cdddd95a55c91e7c5bc14d5f7d6d28eeeaed09ab","title":"Models","url":"/docs/getting-started/providers/stackit#models","content":"| Model                                        | Category       | Context | Max output | Vision          | RPM / TPM   | Notes                                                                                                                                                     |\n| -------------------------------------------- | -------------- | ------- | ---------- | --------------- | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Qwen/Qwen3-VL-235B-A22B-Instruct-FP8 ⭐    | LLM-Premium  | 200K    | 16384      | yes (10 images) | 30 / 350000 | NeuroLink default. Features \"Tool calling enabled\". The row's text: \"Meet Qwen3-VL – the most powerful vision-language model in the Qwen series to date.\" |\n| cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic | LLM-Plus     | 128K    | 4096       | no              | 80 / 200000 | Fallback. Features \"Tool calling enabled\". The model in the Getting started curl example (\"In this guide we use Llama 3.3 70B.\").                         |\n| openai/gpt-oss-120b                        | LLM-Plus     | 131K    | 8192       | no              | 30 / 200000 | Fallback. Features \"Tool calling & Reasoning enabled\".                                                                                                    |\n| Qwen/Qwen3.8-27B                           | LLM-Plus     | 262K    | 16384      | yes (10 images) | 45 / 350000 | Fallback. Features \"Tool calling & Reasoning enabled\"; Thinking budget \"8192 Token\".                                                                      |\n| google/gemma-4-31B-it                      | LLM-Plus     | 256K    | 4096       | yes (10 images) | 80 / 200000 | Fallback. Features \"Tool calling & Reasoning enabled\".                                                                                                    |\n| openai/gpt-oss-20b                         | LLM-Standard | 131K    | 8192      ","hierarchy":{"lvl0":"Getting Started","lvl1":"STACKIT Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"aa34292f420bc029974a92b782903cc8b1ba2ce55c1e9d24e356760a7ee6c253","title":"Verification status","url":"/docs/getting-started/providers/stackit#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog currently records for STACKIT — docs-verified only, not\nlive-verified:\n\n| Probe                     | Result                                                                                                                                                                                                                                                                                               |\n| ------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                    | unauthenticated GET /v1/models answered HTTP 403 (content-length 0, no body) on 2026-09-29, so the roster was not read; the six ids come from the Available Shared Models page, retrieved 2026-09-29 — no key used                                                                                 |\n| Billing                   | vendor pages quoted in Billing, 2026-09-29 — no signup performed                                                                                                                                                                                                                         |\n| Auth-failure shape        | unauthenticated GETs of /v1/models, /v1/chat/completions and /v1 each answered HTTP 403 with content-length 0 and no body on 2026-09-29, so no error code was observable; no POST was sent. errorRules carry the two statuses the vendor's pages state: 404 (FAQ) and 429 (rate-limits page) |\n| Chat response shape       | The sample reply shown under the Getting started page's POST /v1/chat/completions curl request reads \"object\":\"text_completion\" and \"choices\":[{\"in","hierarchy":{"lvl0":"Getting Started","lvl1":"STACKIT Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"358c85fe32cf3134b1b1242649ba700c34cbc074b863eb4af000ef99fc58c894","title":"Troubleshooting","url":"/docs/getting-started/providers/stackit#troubleshooting","content":"Each row is what a STACKIT page says, with the page named.\n\n| Symptom                                          | What the vendor's page says                                                                                                                                                                                                                                     | Page                                                                                                                                            |\n| ------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- |\n| HTTP 404                                         | \"Most likely this is due to an incorrect “model” parameter in the request body.\" and \"This means a chat model cannot be used to compute embeddings, or vice versa.\"                                                                                             | FAQ                                                                    |\n| HTTP 429                                         | \"Once you hit a rate limit (RPM or TPM)\" the API responds with 429 Too Many Requests; a heading on the page reads \"Implement exponential backoff with jitter\"; the page lists the headers x-ratelimit-remaining-requests and x-ratelimit-remaining-tokens | Rate limits |\n| Token does not work                              | Under \"Why does my authentication token (aka API-key) not work?\": \"API base URL: https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1\" and \"API key / Authentication token / Secret key: STACKIT AI Model Serving Auth Token\"                        | FAQ         ","hierarchy":{"lvl0":"Getting Started","lvl1":"STACKIT Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
+{"objectID":"4d23492b8c3c4edd1e26412cdd145ef78f6e966f774da21de48cc825019796e3","title":"See also","url":"/docs/getting-started/providers/stackit#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"STACKIT Provider Guide","lvl2":"See also","lvl3":""}},
 {"objectID":"53668dcbe102b05c8715cd40f4160a0ba947cd979c7bcf7f49b67d7284a71448","title":"StepFun Provider Guide","url":"/docs/getting-started/providers/stepfun","content":"StepFun Provider Guide\n\nStepFun is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/stepfun.json) rather than hand-written code.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. StepFun's GET https://api.stepfun.ai/v1/models needs a key\n(it answers HTTP 401 without one), so the five model ids come from the\nvendor's public\npricing page\nand the roster has not been checked. No account was created and no API key\nwas used to build this entry. evidence.liveMatrix is null until someone\nruns the live capability matrix with a real key (see\nVerification status below).\n\nKey Facts\nProvider id: stepfun\nProtocol: OpenAI-compatible (/chat/completions) — the vendor's\n  migration page\n  says \"Stepfun models are compatible with the OpenAI API spec.\"\nBase URL: https://api.stepfun.ai/v1\nStep Plan: the vendor's\n  Step Plan overview\n  lists a separate OpenAI SDK base URL, https://api.stepfun.ai/step_plan/v1;\n  this entry's default is the standard endpoint above\nDefault model: step-5-preview\nModels in catalog: 5 (ids taken from the vendor's pricing page; roster\n  not checked)\nStreaming: supported — the\n  Chat Completions page\n  documents stream and chat.completion.chunk events ending in\n  data: [DONE]\nTool calling: model-dependent — the\n  Tool Call page\n  lists step-5-preview, step-3.7-flash, step-3.5-flash and\n  step-3.5-flash-2603 among the models that support Toolcall requests\nTools while streaming: supported — the streaming chunk format on the\n  Chat Completions page includes a tool_calls field in delta\nStructured output: supported — the Chat Completions page documents\n  response_format { \"type\": \"json_object\" }, and the\n  JSON Mode page\n  says the json_schema approach applies to step-5-preview,\n  step-3.7-flash, step-3.5-flash and step-3.5-flash-2603\nStructured output + tools together: not declared (false) — no\n  combined probe was possible without credentials\nEmbeddings: not declared\nThinking: declared (true) — the Chat Completions page documents a\n  reasoning_effort request parameter and a reasoning response field\nBilling: recorded as no-free-tier because the catalog schema has no\n  unknown value; that is not a vendor statement. The vendor's own billing\n  wording is quoted under Billing below\nKey format: none declared\n\nQuick Start\nGet an API key\nVisit: https://platform.stepfun.ai/interface-key and sign in - the Quickstart (https://platform.stepfun.ai/docs/en/quickstart/overview.md) says \"Sign in to the StepFun Open Platform and create and copy an API key on the Interface Keys page.\"\nBilling as the vendor states it: the pricing overview (https://platform.stepfun.ai/docs/en/guides/pricing/intro.md) says fees are deducted \"drawing from free credit first, then paid balance\", and the Error Codes page (https://platform.stepfun.ai/docs/en/api-reference/error-codes.md) lists HTTP 402 as \"Insufficient balance\" with the resolution \"Add funds to your account.\"\nSet STEPFUN_API_KEY in your .env file\nConfigure\nUse it\n\nPer-request credentials are passed the same way as for the other catalog providers:\n\nBilling\n\nThe pricing overview\n(pricing/intro)\nsays fees are deducted \"drawing from free credit first, then paid balance\". The\nError Codes page\nlists HTTP 402 as \"Insufficient balance\" with the resolution \"Add funds to\nyour account.\" The\npricing details page\nsays pay-as-you-go calls to the standard Open Platform API \"are rate limited by\ntier according to the cumulative top-up amount on your account\", and for\nindividual accounts states \"Individual accounts must complete identity\nverification first.\" Its individual-account tiers:\n\n| User tier | Cumulative top-up amount | Concurrency | RPM   | TPM        |\n| --------- | ------------------------ | ----------- | ----- | ---------- |\n| V0        | Under $15                | 5           | 100   | 500,000    |\n| V1        | $15 to $69               | 20          | 400   | 2,000,000  |\n| V2        | $70 to $299              | 30          | 600   | 3,000,000  |\n| V3        | $300 to $1,499           | 40          | 800   | 4,000,000  |\n| V4        | $1,500 and above         | 130         | 2,600 | 13,000,000 |\n\nThe entry records no-free-tier because the catalog schema requires one of\nfree-tier, free-with-card or no-free-tier; the vendor pages quoted above\nare the billing statement.\n\nModels\n\n| Model                  | Context | Max output | Vision | $/M in · out (cache hit) | Notes                                                                                                                                                                    |\n| ---------------------- | ------- | ---------- | ------ | ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| step-5-preview ⭐    | 1M      | 64k        | yes    | $1.00 / $2.70 ($0.05)    | NeuroLink default. \"Step 5 Preview is StepFun's flagship m","hierarchy":{"lvl0":"Getting Started","lvl1":"StepFun Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"135256f907a216712790b8be064fbc1bf8bb510aca75e4c14864712caf117469","title":"StepFun Provider Guide","url":"/docs/getting-started/providers/stepfun#stepfun-provider-guide","content":"StepFun is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/stepfun.json) rather than hand-written code.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. StepFun's GET https://api.stepfun.ai/v1/models needs a key\n(it answers HTTP 401 without one), so the five model ids come from the\nvendor's public\npricing page\nand the roster has not been checked. No account was created and no API key\nwas used to build this entry. evidence.liveMatrix is null until someone\nruns the live capability matrix with a real key (see\nVerification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"StepFun Provider Guide","lvl2":"StepFun Provider Guide","lvl3":""}},
 {"objectID":"3f99c4222df11da103cc22dc9c667f2db8637699e6de2e525a23c5d6500e0a03","title":"Key Facts","url":"/docs/getting-started/providers/stepfun#key-facts","content":"Provider id: stepfun\nProtocol: OpenAI-compatible (/chat/completions) — the vendor's\n  migration page\n  says \"Stepfun models are compatible with the OpenAI API spec.\"\nBase URL: https://api.stepfun.ai/v1\nStep Plan: the vendor's\n  Step Plan overview\n  lists a separate OpenAI SDK base URL, https://api.stepfun.ai/step_plan/v1;\n  this entry's default is the standard endpoint above\nDefault model: step-5-preview\nModels in catalog: 5 (ids taken from the vendor's pricing page; roster\n  not checked)\nStreaming: supported — the\n  Chat Completions page\n  documents stream and chat.completion.chunk events ending in\n  data: [DONE]\nTool calling: model-dependent — the\n  Tool Call page\n  lists step-5-preview, step-3.7-flash, step-3.5-flash and\n  step-3.5-flash-2603 among the models that support Toolcall requests\nTools while streaming: supported — the streaming chunk format on the\n  Chat Completions page includes a tool_calls field in delta\nStructured output: supported — the Chat Completions page documents\n  response_format { \"type\": \"json_object\" }, and the\n  JSON Mode page\n  says the json_schema approach applies to step-5-preview,\n  step-3.7-flash, step-3.5-flash and step-3.5-flash-2603\nStructured output + tools together: not declared (false) — no\n  combined probe was possible without credentials\nEmbeddings: not declared\nThinking: declared (true) — the Chat Completions page documents a\n  reasoning_effort request parameter and a reasoning response field\nBilling: recorded as no-free-tier because the catalog schema has no\n  unknown value; that is not a vendor statement. The vendor's own billing\n  wording is quoted under Billing below\nKey format: none declared","hierarchy":{"lvl0":"Getting Started","lvl1":"StepFun Provider Guide","lvl2":"Key Facts","lvl3":""}},
@@ -6956,6 +7131,29 @@
 {"objectID":"1b321e95b49cf8c2e2e15b3e5b1292363d492fd984294d3c5a329e11a33765f2","title":"Verification status","url":"/docs/getting-started/providers/synthetic#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog records for Synthetic — all credential-free:\n\n| Probe                  | Result                                                                                                                                                                                                                                  |\n| ---------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                 | unauthenticated GET /openai/v1/models, HTTP 200, 11 models, 2026-09-28. No API key used or required for this endpoint.                                                                                                                |\n| Billing                | unauthenticated GET https://synthetic.new/pricing, HTTP 200, 2026-09-28 — no free tier; $1/day or $30/month subscription pack (500 req/5hr), or enterprise usage-based pricing.                                                       |\n| Third-party wire check | LiteLLM's Synthetic provider page confirms base URL https://api.synthetic.new/openai/v1, env var SYNTHETIC_API_KEY, and /chat/completions as the only supported operation.                                                        |\n| Live capability sweep  | Not yet run. evidence.liveMatrix is null. Tool calling, structured output, streaming and the tools+schema combination are documented by the vendor's own supported_features roster field, not wire-proven against a real key. |\n\nBecause no live key was used, capabilities.structuredOutputWithTools is\nfalse per Tier-2 policy — a documented individual capability is not\nevidence for the combined one. A future pass with a real\nSYNTHETIC_API_KEY should run the live matrix\n(npx tsx test/con","hierarchy":{"lvl0":"Getting Started","lvl1":"Synthetic Provider Guide","lvl2":"Verification status","lvl3":""}},
 {"objectID":"4db386b896f3e19c66e5564b8719cb8bddca88d0d596ccdea459ee60cf27f825","title":"Troubleshooting","url":"/docs/getting-started/providers/synthetic#troubleshooting","content":"| Symptom                                  | Cause                                                                                                | Fix                                                                                      |\n| ---------------------------------------- | ---------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |\n| Auth error on first request              | No documented auth-error shape yet (no live probe)                                                   | Check SYNTHETIC_API_KEY is set and valid; see https://synthetic.new for key management |\n| Model not found                          | The roster changed since 2026-09-28                                                                  | Pick a current id from the unauthenticated GET /openai/v1/models roster                |\n| No free tier                             | Synthetic requires a paid Pack or usage-based billing                                                | Subscribe at https://synthetic.new before making live calls                              |\n| Structured output + tools together fails | Not yet probed combined; declared unsupported (structuredOutputWithTools: false) until proven live | Send tools and response_format in separate requests until this is live-verified        |","hierarchy":{"lvl0":"Getting Started","lvl1":"Synthetic Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
 {"objectID":"452f3970d27c44897602d26d618f2d1f808aae1c21ceba07acf57e2c84c34a02","title":"See also","url":"/docs/getting-started/providers/synthetic#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Synthetic Provider Guide","lvl2":"See also","lvl3":""}},
+{"objectID":"072e186cf310a05c6cbfe1c00fe2900a3e93ebb2e86d53a93a5b4aa8bfbc3c71","title":"Telnyx Provider Guide","url":"/docs/getting-started/providers/telnyx","content":"Telnyx Provider Guide\n\nTelnyx is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/telnyx.json) rather than hand-written code.\nThat file is the source of truth for this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. Telnyx's GET /v2/ai/openai/models needs a key (it answers\nHTTP 401 without one), so the model ids come from Telnyx's public models page\nand the roster has not been checked. No account was created and no API key\nwas used to build this entry. evidence.liveMatrix is null until someone\nruns the live capability matrix with a real key (see\nVerification status below).\n\nKey Facts\nProvider id: telnyx\nProtocol: OpenAI-compatible (/chat/completions) — the\n  Quickstart\n  says \"The Inference API is OpenAI-compatible.\"\nBase URL: https://api.telnyx.com/v2/ai/openai\nDefault model: zai-org/GLM-5.3-Flash — NeuroLink default. The\n  models page tags it\n  \"(Recommended)\", and the Quickstart's first chat-completions example uses it\nModels in catalog: 9 — the nine chat models the models page lists on\n  2026-09-29\nStreaming: supported — the Quickstart's Streaming section says\n  \"Server-sent events, same as OpenAI.\"\nTool calling: true — the\n  Function Calling page\n  says \"While we recommend you start with this model, every model in our API\n  supports the tools interface.\"\nTools while streaming: true — the\n  Streaming and Parallel Calls page\n  shows a streamed chat completion with tools on zai-org/GLM-5.3-Flash\nStructured output: true — the\n  JSON Mode page\n  documents response_format with json_schema and with json_object\nStructured output + tools together: not declared (false) — no combined\n  probe was run without credentials\nEmbeddings: not declared on this catalog entry. The models page lists\n  three embedding models on POST /v2/ai/openai/embeddings, but NeuroLink's\n  generic ConfiguredOpenAICompatProvider (which every Tier-2 catalog entry\n  uses) does not implement embed()/embedMany(), so this flag tracks that,\n  not the vendor's own API surface\nThinking: not declared — the\n  Chat Completions reference\n  documents reasoning_effort and the Quickstart documents a reasoning_content\n  response field, but this entry sets no reasoning request parameter\nMax output tokens: models.defaultMaxOutputTokens is 8192, the\n  max_tokens default the Chat Completions reference states. The reference also\n  says \"Reasoning models consume this budget across reasoning and answer tokens\n  combined.\"\nVision: each model's vision field is false, a placeholder for a\n  boolean the catalog schema requires; it is not a vendor statement\nBilling: see Billing below\nKey format: none declared\n\nQuick Start\nGet an API key\nVisit: https://telnyx.com/sign-up and create a Telnyx account — the Inference API Quickstart (https://developers.telnyx.com/docs/inference/getting-started) lists a \"Telnyx account\" and an \"API Key\" under Prerequisites\nCreate an API key at https://portal.telnyx.com/#/app/auth/v2, the link the Quickstart gives for the API Key\nAuthentication is HTTP Bearer: the Service tiers page (https://developers.telnyx.com/docs/inference/service-tiers) shows a curl request to https://api.telnyx.com/v2/ai/openai/models with the header Authorization: Bearer $TELNYXAPIKEY\nBilling as the vendor states it: see Billing below\nSet TELNYX_API_KEY in your .env file (the docs' examples read TELNYX_API_KEY)\nConfigure\nUse it\n\nPer-request credentials work as they do for every provider:\n\nBilling\n\nbillingPolicy in the catalog file is recorded as unknown in the growth queue;\nthe catalog schema has no unknown value, so the file holds no-free-tier as a\nplaceholder. It is not a vendor statement of signup terms.\n\nWhat the vendor's pages say:\nThe Inference pricing page shows\n  a plan named PAY AS YOU GO described as \"Standard rates. Card on file.\n  Automatic tier discounts as usage crosses thresholds, no contract needed.\"\nThe docs pricing page\n  says \"Pay-per-token. No minimums, no commitments.\" and points to\n  telnyx.com/pricing/inference-api for current per-model pricing.\n\nModels\n\n| Model                                | Context | Vision            | $/M in · out (cached)            | Notes                                                                                                                                    |\n| ------------------------------------ | ------- | ----------------- | -------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- |\n| zai-org/GLM-5.3-Flash ⭐           | 1M      | false placeholder | $0.135 / $0.450 (cached $0.027)  | NeuroLink default. Best For \"Efficient multimodal coding and agentic workflows\", tagged \"(Recommended)\"; the Quickstart's example model. |\n| zai-org/GLM-5.3                    | 1M      | false placeholder | $1.250 / $4.000 (cached $0.240)  | Fallback. Best For \"Complex coding and long-horizon agent tasks\"; pricing row \"GLM-5.3 — Flagship f","hierarchy":{"lvl0":"Getting Started","lvl1":"Telnyx Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"2045f8976971b0c3b654fdccf085704516ae3fc240255cc23b96e63687a27c53","title":"Telnyx Provider Guide","url":"/docs/getting-started/providers/telnyx#telnyx-provider-guide","content":"Telnyx is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/telnyx.json) rather than hand-written code.\nThat file is the source of truth for this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. Telnyx's GET /v2/ai/openai/models needs a key (it answers\nHTTP 401 without one), so the model ids come from Telnyx's public models page\nand the roster has not been checked. No account was created and no API key\nwas used to build this entry. evidence.liveMatrix is null until someone\nruns the live capability matrix with a real key (see\nVerification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"Telnyx Provider Guide","lvl2":"Telnyx Provider Guide","lvl3":""}},
+{"objectID":"a92e959d3465234bc896cd925ce67f19f84cd5e3b96eb65b8a25b10ed56a9e1c","title":"Key Facts","url":"/docs/getting-started/providers/telnyx#key-facts","content":"Provider id: telnyx\nProtocol: OpenAI-compatible (/chat/completions) — the\n  Quickstart\n  says \"The Inference API is OpenAI-compatible.\"\nBase URL: https://api.telnyx.com/v2/ai/openai\nDefault model: zai-org/GLM-5.3-Flash — NeuroLink default. The\n  models page tags it\n  \"(Recommended)\", and the Quickstart's first chat-completions example uses it\nModels in catalog: 9 — the nine chat models the models page lists on\n  2026-09-29\nStreaming: supported — the Quickstart's Streaming section says\n  \"Server-sent events, same as OpenAI.\"\nTool calling: true — the\n  Function Calling page\n  says \"While we recommend you start with this model, every model in our API\n  supports the tools interface.\"\nTools while streaming: true — the\n  Streaming and Parallel Calls page\n  shows a streamed chat completion with tools on zai-org/GLM-5.3-Flash\nStructured output: true — the\n  JSON Mode page\n  documents response_format with json_schema and with json_object\nStructured output + tools together: not declared (false) — no combined\n  probe was run without credentials\nEmbeddings: not declared on this catalog entry. The models page lists\n  three embedding models on POST /v2/ai/openai/embeddings, but NeuroLink's\n  generic ConfiguredOpenAICompatProvider (which every Tier-2 catalog entry\n  uses) does not implement embed()/embedMany(), so this flag tracks that,\n  not the vendor's own API surface\nThinking: not declared — the\n  Chat Completions reference\n  documents reasoning_effort and the Quickstart documents a reasoning_content\n  response field, but this entry sets no reasoning request parameter\nMax output tokens: models.defaultMaxOutputTokens is 8192, the\n  max_tokens default the Chat Completions reference states. The reference also\n  says \"Reasoning models consume this budget across reasoning and answer tokens\n  combined.\"\nVision: each model's vision field is false, a placeholder for a\n  boolean the catalog schema requires; it is not a vendor statement\nBilling: see Billing below\nKey format: none declar","hierarchy":{"lvl0":"Getting Started","lvl1":"Telnyx Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"6d63ef9dd34304f9672431ad4e381853fd33b34a945d6885be49691f41ccc1f4","title":"1. Get an API key","url":"/docs/getting-started/providers/telnyx#1-get-an-api-key","content":"Visit: https://telnyx.com/sign-up and create a Telnyx account — the Inference API Quickstart (https://developers.telnyx.com/docs/inference/getting-started) lists a \"Telnyx account\" and an \"API Key\" under Prerequisites\nCreate an API key at https://portal.telnyx.com/#/app/auth/v2, the link the Quickstart gives for the API Key\nAuthentication is HTTP Bearer: the Service tiers page (https://developers.telnyx.com/docs/inference/service-tiers) shows a curl request to https://api.telnyx.com/v2/ai/openai/models with the header Authorization: Bearer $TELNYXAPIKEY\nBilling as the vendor states it: see Billing below\nSet TELNYX_API_KEY in your .env file (the docs' examples read TELNYX_API_KEY)","hierarchy":{"lvl0":"Getting Started","lvl1":"Telnyx Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"456ef8325b76a46baf8298e328deeea262fff2e201efde3b7623ff5fece4ba6d","title":"3. Use it","url":"/docs/getting-started/providers/telnyx#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Telnyx Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"04171986a3126dc4ef57b90aa17403cd3e3cf5ab1986bc2ce252f93e9100b432","title":"CLI","url":"/docs/getting-started/providers/telnyx#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider telnyx\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"telnyx\",\n  credentials: { telnyx: { apiKey: process.env.TELNYXAPIKEY } },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"Telnyx Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"5d538d5574bcf7709655425807ee2cdf19460cbceb53f5099bf22c9891b03d57","title":"Billing","url":"/docs/getting-started/providers/telnyx#billing","content":"billingPolicy in the catalog file is recorded as unknown in the growth queue;\nthe catalog schema has no unknown value, so the file holds no-free-tier as a\nplaceholder. It is not a vendor statement of signup terms.\n\nWhat the vendor's pages say:\nThe Inference pricing page shows\n  a plan named PAY AS YOU GO described as \"Standard rates. Card on file.\n  Automatic tier discounts as usage crosses thresholds, no contract needed.\"\nThe docs pricing page\n  says \"Pay-per-token. No minimums, no commitments.\" and points to\n  telnyx.com/pricing/inference-api for current per-model pricing.","hierarchy":{"lvl0":"Getting Started","lvl1":"Telnyx Provider Guide","lvl2":"Billing","lvl3":""}},
+{"objectID":"aa70ca5fbc1b24a500d421c03836b4dd856b0307e81903227a9f814b15da57f9","title":"Models","url":"/docs/getting-started/providers/telnyx#models","content":"| Model                                | Context | Vision            | $/M in · out (cached)            | Notes                                                                                                                                    |\n| ------------------------------------ | ------- | ----------------- | -------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- |\n| zai-org/GLM-5.3-Flash ⭐           | 1M      | false placeholder | $0.135 / $0.450 (cached $0.027)  | NeuroLink default. Best For \"Efficient multimodal coding and agentic workflows\", tagged \"(Recommended)\"; the Quickstart's example model. |\n| zai-org/GLM-5.3                    | 1M      | false placeholder | $1.250 / $4.000 (cached $0.240)  | Fallback. Best For \"Complex coding and long-horizon agent tasks\"; pricing row \"GLM-5.3 — Flagship frontier intelligence\".                |\n| deepseek-ai/DeepSeek-V4.1-Flash    | 1M      | false placeholder | $0.300 / $1.200 (cached $0.006)  | Fallback. Best For \"Low-latency multimodal inference\"; the Service tiers page's Flex example model.                                      |\n| moonshotai/Kimi-K3                 | 1M      | false placeholder | $2.700 / $13.500 (cached $0.270) | Fallback. Best For \"State-of-the-art open-weight intelligence for coding, reasoning, and multimodal work\".                               |\n| moonshotai/Kimi-K2.6               | 256K    | false placeholder | $0.665 / $4.000 (cached $0.080)  | Fallback. Best For \"Voice AI\"; Voice AI column \"Verified — default\".                                                                     |\n| zai-org/GLM-5.2                    | 1M      | false placeholder | $1.000 / $4.000 (cached $0.200)  | Fallback. Best For \"Coding, reasoning, 1M context window\"; Voice AI column \"Verified\".                                                   |\n| MiniMaxAI/MiniMax-M3-MXFP8         | 1M      | fals","hierarchy":{"lvl0":"Getting Started","lvl1":"Telnyx Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"9e77dc1ef1b51ccf04d1e12bc2e7b0f16c1096e7d911a5721ef4840bb9204603","title":"Verification status","url":"/docs/getting-started/providers/telnyx#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the catalog\ncurrently records for Telnyx — docs-verified only, not live-verified:\n\n| Probe                                 | Result                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |\n| ------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                                | unauthenticated GET https://api.telnyx.com/v2/ai/openai/models answers HTTP 401 without a key, 2026-09-29; model ids come from the models page and the roster has not been checked                                                                                                                                                                                                                                                                                            |\n| Auth-failure shape                    | unauthenticated GET /models: HTTP 401, header www-authenticate: Bearer resource_metadata=\"https://api.telnyx.com/.well-known/oauth-protected-resource\", JSON body errors[0] code 10009, title \"Authentication failed\", de","hierarchy":{"lvl0":"Getting Started","lvl1":"Telnyx Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"187152fc0334489ad01d53fd30b301f5299221b59baaf65f6a6252e46199f5c7","title":"Troubleshooting","url":"/docs/getting-started/providers/telnyx#troubleshooting","content":"| Symptom                                       | Cause                                                                                                                                                                                                             | Fix                                                                                        |\n| --------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------ |\n| HTTP 401, code 10009                        | Telnyx's error catalog describes 10009 \"Authentication failed\" as \"The required authentication headers were either invalid or not included in the request.\" | Set TELNYX_API_KEY; the docs' examples read the same variable                            |\n| Structured output ignored with tools attached | structuredOutputWithTools is false on this entry — untested combination                                                                                                                                       | NeuroLink omits response_format automatically whenever tools are present, before sending |","hierarchy":{"lvl0":"Getting Started","lvl1":"Telnyx Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
+{"objectID":"b9ba1cd5a30c554c43b28f72773e3f5f2c3050d8f0843d29db257388f9d074a3","title":"See also","url":"/docs/getting-started/providers/telnyx#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Telnyx Provider Guide","lvl2":"See also","lvl3":""}},
+{"objectID":"615902293f44b0c3e4f6cf153b2c2b02fc4d6a158fa2c002cd289ac8cad1754f","title":"Thinking Machines Provider Guide","url":"/docs/getting-started/providers/thinking-machines","content":"Thinking Machines Provider Guide\n\nThinking Machines is a Tier-2 catalog provider: OpenAI-wire-compatible with\nno behavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/thinking-machines.json) rather than hand-written\ncode. That file is the source of truth for everything on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's GET /models needs a key (an unauthenticated\nGET answered HTTP 401), so the model ids come from the vendor's public\nModels & Pricing page\nand the roster has not been checked. No API key was created or used to build\nthis entry. evidence.liveMatrix is null until someone runs the live\ncapability matrix with a real key (see\nVerification status below).\n\nKey Facts\nProvider id: thinking-machines (alias tinker)\nProtocol: OpenAI-compatible (/chat/completions). The vendor's\n  OpenAI-compatible page\n  is titled \"OpenAI API Compatible Inference (in beta)\" and says \"We support\n  both /completions and /chat/completions endpoints.\"\nBase URL: https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1\nDefault model: moonshotai/Kimi-K2.6\nModels in catalog: 12 rows of the Training table on the\n  Models & Pricing page,\n  listed under Models\nVendor scope statement: \"Currently, OpenAI-compatible inference is meant\n  for testing and internal use with low internal traffic, rather than large,\n  high-throughput, user-facing deployments.\" (OpenAI-compatible page)\nStreaming: true — the OpenAI-compatible page says \"In streaming mode,\n  reasoning_content and content arrive on separate SSE events\"\nThinking: true — the OpenAI-compatible page documents a separate_reasoning\n  flag and a reasoning_effort parameter on /chat/completions, and says of\n  the latter \"Not all models support this parameter.\"\nTool calling: not declared (false). With false, the provider's\n  supportsTools() answers false, so no tools array is sent\nStructured output: not declared (false)\nStructured output + tools together: not declared (false) — no POST\n  request was sent\nEmbeddings: not declared (false)\nBilling: the catalog field holds no-free-tier, a schema placeholder (the\n  schema has no unknown value), not a vendor statement; see\n  Billing for what the vendor says\nKey format: none declared, so NeuroLink applies no key-format check\n\nQuick Start\nGet an API key\nVisit: https://tinker.thinkingmachines.ai/keys — the Quickstart says \"Or create an API key in the Tinker Console and set it as the TINKERAPIKEY environment variable.\" An unauthenticated GET of that URL redirects to a page titled \"Sign in\" (sign-in was not attempted while building this entry)\nAuthentication as the vendor states it: the OpenAI-compatible page says \"Authenticate with your Tinker API key, by passing the same key used for Tinker as the API key to the OpenAI client.\" Its code example reads the key from TINKER_API_KEY\nBilling as the vendor states it: see Billing\nSet THINKING_MACHINES_API_KEY in your .env file (the vendor's examples read TINKER_API_KEY, which NeuroLink accepts as a fallback)\nConfigure\nUse it\n\nPer-request credentials work as they do for every provider:\n\nSampler checkpoints\n\nThe OpenAI-compatible page says \"Use a Tinker sampler weight path as the model\nname.\" and shows a path that begins with tinker://. A tinker:// path passed\nas model is an id outside the catalog, so it uses models.defaultContextWindow\n(32768) and models.defaultMaxOutputTokens (8192).\n\nBilling\n\nThe vendor's Quickstart says: \"Set up payment info in Billing, and see Models &\nPricing for current training and sampling rates.\" The Billing link goes to\nhttps://tinker.thinkingmachines.ai/billing/; an unauthenticated GET of it\nredirects to the same \"Sign in\" page as the keys URL. The Models & Pricing page\nsays \"All prices are per million tokens.\" The catalog's billingPolicy field\nholds no-free-tier only because the schema requires one of three values; it is\nnot a vendor statement.\n\nModels\n\n| Model                                           | Context | Vision       | $/M in · out (cached in) | Vendor type     | Notes                                                                                                     |\n| ----------------------------------------------- | ------- | ------------ | ------------------------ | --------------- | --------------------------------------------------------------------------------------------------------- |\n| moonshotai/Kimi-K2.6 ⭐                       | 32,768  | not declared | $2.205 / $5.49 ($0.441)  | Hybrid + Vision | NeuroLink default. Named in the OpenCode tutorial's \"Using a base model (no fine-tuning)\" section.        |\n| Qwen/Qwen3.8-27B                              | 65,536  | not declared | $1.86 / $5.595 ($0.372)  | Hybrid + Vision | Fallback. Listed under \"Recommended replacement\" for Qwen3.6-27B.                                         |\n| Qwen/Qwen3.6-35B-A3B                          | 65,536  | not declared | $0.54 / $1.335 ($0.108)  | Hybrid + Vision | Listed unde","hierarchy":{"lvl0":"Getting Started","lvl1":"Thinking Machines Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"6d59bfa41822835f383ed2f1ed3d1dd299e6385816b3945d59736671204f4d53","title":"Thinking Machines Provider Guide","url":"/docs/getting-started/providers/thinking-machines#thinking-machines-provider-guide","content":"Thinking Machines is a Tier-2 catalog provider: OpenAI-wire-compatible with\nno behavioural quirks, so its entire integration is one JSON file\n(src/lib/providers/catalog/thinking-machines.json) rather than hand-written\ncode. That file is the source of truth for everything on this page.\n\nVerification status: this entry is docs-verified only, not yet\nlive-verified. The vendor's GET /models needs a key (an unauthenticated\nGET answered HTTP 401), so the model ids come from the vendor's public\nModels & Pricing page\nand the roster has not been checked. No API key was created or used to build\nthis entry. evidence.liveMatrix is null until someone runs the live\ncapability matrix with a real key (see\nVerification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"Thinking Machines Provider Guide","lvl2":"Thinking Machines Provider Guide","lvl3":""}},
+{"objectID":"7b4679c9d473ec51dd9dbd783af3a55769da6816099c1fb1eb1fc39291327741","title":"Key Facts","url":"/docs/getting-started/providers/thinking-machines#key-facts","content":"Provider id: thinking-machines (alias tinker)\nProtocol: OpenAI-compatible (/chat/completions). The vendor's\n  OpenAI-compatible page\n  is titled \"OpenAI API Compatible Inference (in beta)\" and says \"We support\n  both /completions and /chat/completions endpoints.\"\nBase URL: https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1\nDefault model: moonshotai/Kimi-K2.6\nModels in catalog: 12 rows of the Training table on the\n  Models & Pricing page,\n  listed under Models\nVendor scope statement: \"Currently, OpenAI-compatible inference is meant\n  for testing and internal use with low internal traffic, rather than large,\n  high-throughput, user-facing deployments.\" (OpenAI-compatible page)\nStreaming: true — the OpenAI-compatible page says \"In streaming mode,\n  reasoning_content and content arrive on separate SSE events\"\nThinking: true — the OpenAI-compatible page documents a separate_reasoning\n  flag and a reasoning_effort parameter on /chat/completions, and says of\n  the latter \"Not all models support this parameter.\"\nTool calling: not declared (false). With false, the provider's\n  supportsTools() answers false, so no tools array is sent\nStructured output: not declared (false)\nStructured output + tools together: not declared (false) — no POST\n  request was sent\nEmbeddings: not declared (false)\nBilling: the catalog field holds no-free-tier, a schema placeholder (the\n  schema has no unknown value), not a vendor statement; see\n  Billing for what the vendor says\nKey format: none declared, so NeuroLink applies no key-format check","hierarchy":{"lvl0":"Getting Started","lvl1":"Thinking Machines Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"cb6b793f646bed3982640d587e2f087a400d2bae90dbf500a4216a879dc8f685","title":"1. Get an API key","url":"/docs/getting-started/providers/thinking-machines#1-get-an-api-key","content":"Visit: https://tinker.thinkingmachines.ai/keys — the Quickstart says \"Or create an API key in the Tinker Console and set it as the TINKERAPIKEY environment variable.\" An unauthenticated GET of that URL redirects to a page titled \"Sign in\" (sign-in was not attempted while building this entry)\nAuthentication as the vendor states it: the OpenAI-compatible page says \"Authenticate with your Tinker API key, by passing the same key used for Tinker as the API key to the OpenAI client.\" Its code example reads the key from TINKER_API_KEY\nBilling as the vendor states it: see Billing\nSet THINKING_MACHINES_API_KEY in your .env file (the vendor's examples read TINKER_API_KEY, which NeuroLink accepts as a fallback)","hierarchy":{"lvl0":"Getting Started","lvl1":"Thinking Machines Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"081c89917e6dab39380a1a8ed7231f2f232f81ca6136dc3329ee37ed3ccc9dbf","title":"3. Use it","url":"/docs/getting-started/providers/thinking-machines#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Thinking Machines Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"9859787d27cddb6e6ec6a4a0dba1a9d0f2a475dcdff9d601fd7f3898ca303bb0","title":"CLI","url":"/docs/getting-started/providers/thinking-machines#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider thinking-machines\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"thinking-machines\",\n  credentials: {\n    thinkingMachines: { apiKey: process.env.THINKINGMACHINESAPI_KEY },\n  },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"Thinking Machines Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"7c9d836127ef604489927114abdfc9f7d66ec38438ef41167f72336b954edd6b","title":"Sampler checkpoints","url":"/docs/getting-started/providers/thinking-machines#sampler-checkpoints","content":"The OpenAI-compatible page says \"Use a Tinker sampler weight path as the model\nname.\" and shows a path that begins with tinker://. A tinker:// path passed\nas model is an id outside the catalog, so it uses models.defaultContextWindow\n(32768) and models.defaultMaxOutputTokens (8192).","hierarchy":{"lvl0":"Getting Started","lvl1":"Thinking Machines Provider Guide","lvl2":"Sampler checkpoints","lvl3":""}},
+{"objectID":"39ebb2ae60d1cd2dc0b7357a07437d3b7817873a32b4051a58dfec291151cf1d","title":"Billing","url":"/docs/getting-started/providers/thinking-machines#billing","content":"The vendor's Quickstart says: \"Set up payment info in Billing, and see Models &\nPricing for current training and sampling rates.\" The Billing link goes to\nhttps://tinker.thinkingmachines.ai/billing/; an unauthenticated GET of it\nredirects to the same \"Sign in\" page as the keys URL. The Models & Pricing page\nsays \"All prices are per million tokens.\" The catalog's billingPolicy field\nholds no-free-tier only because the schema requires one of three values; it is\nnot a vendor statement.","hierarchy":{"lvl0":"Getting Started","lvl1":"Thinking Machines Provider Guide","lvl2":"Billing","lvl3":""}},
+{"objectID":"55ad4b561d814e4434fd41786043bedecf6e742e008c330e2653da64432b7e98","title":"Models","url":"/docs/getting-started/providers/thinking-machines#models","content":"| Model                                           | Context | Vision       | $/M in · out (cached in) | Vendor type     | Notes                                                                                                     |\n| ----------------------------------------------- | ------- | ------------ | ------------------------ | --------------- | --------------------------------------------------------------------------------------------------------- |\n| moonshotai/Kimi-K2.6 ⭐                       | 32,768  | not declared | $2.205 / $5.49 ($0.441)  | Hybrid + Vision | NeuroLink default. Named in the OpenCode tutorial's \"Using a base model (no fine-tuning)\" section.        |\n| Qwen/Qwen3.8-27B                              | 65,536  | not declared | $1.86 / $5.595 ($0.372)  | Hybrid + Vision | Fallback. Listed under \"Recommended replacement\" for Qwen3.6-27B.                                         |\n| Qwen/Qwen3.6-35B-A3B                          | 65,536  | not declared | $0.54 / $1.335 ($0.108)  | Hybrid + Vision | Listed under \"Recommended replacement\" for Qwen3.5-35B-A3B and Qwen3-30B-A3B.                             |\n| Qwen/Qwen3.5-397B-A17B                        | 65,536  | not declared | $3.00 / $7.50 ($0.60)    | Hybrid + Vision | Listed under \"Recommended replacement\" for Qwen3-235B-A22B-Instruct-2507 and Qwen3-VL-235B-A22B-Instruct. |\n| Qwen/Qwen3.5-9B                               | 65,536  | not declared | $0.66 / $1.995 ($0.132)  | Hybrid + Vision | Listed under \"Recommended replacement\" for Llama-3.1-8B-Instruct.                                         |\n| Qwen/Qwen3.5-4B                               | 65,536  | not declared | $0.33 / $1.005 ($0.066)  | Hybrid + Vision | Listed under \"Recommended replacement\" for Qwen3-4B-Instruct-2507.                                        |\n| Qwen/Qwen3-8B                                 | 32,768  | not declared | $0.195 / $0.60 ($0.039)  | Hybrid          | Fallback. Named on the Anthropic-Compatible API page,","hierarchy":{"lvl0":"Getting Started","lvl1":"Thinking Machines Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"c58fa10816d9a9f4b7c94d1a8b876b284a6b87833b72b2588cd643568676c371","title":"Verification status","url":"/docs/getting-started/providers/thinking-machines#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog currently records for Thinking Machines — docs-verified only, not\nlive-verified:\n\n| Probe                     | Result                                                                                                                                                                                                                               |\n| ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| Roster                    | unauthenticated GET /models answers HTTP 401 without a key (2026-09-29), so the twelve model ids are taken from the Models & Pricing page and the roster has not been checked                                                      |\n| Endpoint shape            | unauthenticated GET /chat/completions answered HTTP 405 with header allow: POST and body {\"detail\":\"Method Not Allowed\"}; the base URL itself answered HTTP 404 with body {\"detail\":\"Not Found\"}; no POST request was sent   |\n| Auth-failure shape        | unauthenticated GET /models answered HTTP 401, content-type application/json, body {\"detail\":\"X-Api-Key token is empty\"}; the body has no code field, so no code is recorded and errorRules holds one rule, for status 401 |\n| Billing                   | the Quickstart's Billing section, quoted under Billing; no signup was performed                                                                                                                                          |\n| Tools / structured output | not declared; no POST request was sent — structuredOutputWithTools stays false                                                                                                                                ","hierarchy":{"lvl0":"Getting Started","lvl1":"Thinking Machines Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"a333dba919b426ab885447d39bbb6fbaaec6a51acaa5778c9866b3c753ae7914","title":"Troubleshooting","url":"/docs/getting-started/providers/thinking-machines#troubleshooting","content":"Each row below is a statement from the vendor's own pages.\n\n| Symptom                                         | What the vendor says                                                                                                                                                                                                      | Source                                                                                           |\n| ----------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------ |\n| HTTP 400 when a request sets reasoning_effort | \"Not all models support this parameter. Requests against a model that doesn't support it return HTTP 400.\"                                                                                                                | OpenAI-compatible page |\n| Reasoning trace missing from content          | \"separate_reasoning defaults to true; set it to false to keep the reasoning trace inlined in content.\"                                                                                                                    | OpenAI-compatible page |\n| Prompt formatting differs from the checkpoint   | On /chat/completions \"the server renders them with the model’s default Hugging Face chat template\"; \"If your checkpoint expects a different renderer, render the prompt to token IDs yourself\"                          | OpenAI-compatible page |\n| Latency or throughput varies                    | \"Latency and throughput may vary by model and may change without notice during the beta.\" and \"If you need higher or more stable throughput, contact the Tinker team in our Discord for guidance on larger-scale setups.\" | OpenAI-compatible page |\n| A model id is ","hierarchy":{"lvl0":"Getting Started","lvl1":"Thinking Machines Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
+{"objectID":"08dc3a265ca7fd4eefbfc00ba41e61832e547e173b87b05534ab249df374611d","title":"See also","url":"/docs/getting-started/providers/thinking-machines#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Thinking Machines Provider Guide","lvl2":"See also","lvl3":""}},
 {"objectID":"823f5e16f43c75de89ea1f12d99dd4ca0e84299fe2372730cbc3d17169a00417","title":"Tinfoil Provider Guide","url":"/docs/getting-started/providers/tinfoil","content":"Tinfoil Provider Guide\n\nTinfoil is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/tinfoil.json) rather than hand-written code.\nThat file is the source of truth for this page.\n\nVerification status: this entry is docs- and roster-verified, not yet\nlive-verified. The fields below come from Tinfoil's own public pages and\ntwo unauthenticated GET requests (/v1/models and /v1/chat/completions) —\nno account was created and no API key was used to build it.\nevidence.liveMatrix is null until someone runs the live capability matrix\nwith a real key (see Verification status below).\n\nKey Facts\nProvider id: tinfoil (no alias)\nProtocol: OpenAI-compatible (/chat/completions). The homepage says\n  \"Our API is OpenAI-compatible, open-source, and fully verifiable.\"\n  (tinfoil.sh) and the chat models page says \"Chat models\n  use the OpenAI chat completions API.\"\n  (docs)\nBase URL: https://inference.tinfoil.sh/v1\nDefault model: kimi-k3\nModels in catalog: 7 (the seven entries whose roster type is chat,\n  taken from a 17-entry roster)\nStreaming: supported — the structured outputs guide shows a request with\n  stream=True that reads chunk.choices[0].delta.content, under the heading\n  \"Enable Streaming for Large Responses\"\n  (docs)\nTool calling: supported (true) — the tool-calling guide documents\n  function calling (docs), and\n  the roster's tool_calling field is true on the seven catalog models\nTools while streaming: not declared (false) — no combined\n  tools-and-streaming request was sent (no credentials were used)\nStructured output: supported — the structured outputs guide documents a\n  response_format of type json_schema\n  (docs), and the seven\n  chat model cards carry a \"Structured Outputs\" line\n  (docs)\nStructured output + tools together: not declared (false) — no\n  combined probe was run without credentials\nEmbeddings: not declared (false) on this catalog entry. The roster lists\n  nomic-embed-text with type embedding\n  (docs); it is not one of the seven\n  catalog models\nThinking: declared (true) — the reasoning guide documents a\n  reasoning_effort request parameter and says the model's thinking is returned\n  in the reasoning field of the response message\n  (docs); the accepted values differ\n  by model (see Reasoning effort)\nVision: four catalog models (kimi-k3, gemma4-31b, glm-5-3-flash,\n  deepseek-v4-1-flash) — see Models\nBilling: free-with-card — see Billing below\nKey format: none validated (apiKeyFormat is null)\nConnection security: NeuroLink calls the endpoint directly over HTTPS —\n  see Direct HTTPS access\n\nQuick Start\nGet an API key\nVisit: https://dash.tinfoil.sh?tab=api-keys and sign in or sign up — https://docs.tinfoil.sh/get-api-key says \"Create an account with your email or one of the social connections.\"\nOn the dashboard Products page, click Activate on the Private Inference card. Per https://docs.tinfoil.sh/get-api-key, if no payment method is on file you are redirected to a checkout page to enter your card details, and \"You’re only charged based on usage.\"\nThe activation dialog creates a \"Default API key\" and, per the same page, \"adds $1 in API credits to your account\"; additional keys are created from API Keys in the sidebar\nSet TINFOIL_API_KEY in your .env file (the examples on https://docs.tinfoil.sh/quickstart read TINFOILAPIKEY)\nNeuroLink sends requests straight to https://inference.tinfoil.sh/v1. https://docs.tinfoil.sh/sdk/direct-api-access says \"but this is not recommended in production\" and \"Direct access skips the automatic attestation verification our SDKs perform\". https://docs.tinfoil.sh/local-proxy/cli documents a local proxy that verifies enclave attestations and serves http://127.0.0.1:3301/v1 for OpenAI-compatible clients (not exercised with NeuroLink)\nConfigure\nUse it\n\nPer-request credentials work as they do for the other catalog providers:\n\nDirect HTTPS access\n\nThe catalog's base URL, https://inference.tinfoil.sh/v1, is the endpoint the\nTinfoil docs call \"direct\" access. The docs page for it\n(Direct API Access) says \"but\nthis is not recommended in production\" and \"Direct access skips the automatic\nattestation verification our SDKs perform, so you have no cryptographic proof\nyour data is processed in a secure enclave and no protection against\nman-in-the-middle attacks.\" It also says \"We maintain direct HTTPS\ncompatibility for debugging and simple testing (e.g., inference requests via\ncURL).\"\n\nThe coding-agents tutorial says \"OpenAI-compatible clients don’t perform\nconnection-time attestation themselves.\"\n(docs) and the\nTinfoil Proxy CLI page describes a\nlocal proxy that listens on http://127.0.0.1:3301, verifies the enclave's\nattestation, and takes that address as the base URL for any OpenAI-compatible\nclient. Pointing TINFOIL_BASE_URL at it follows those docs; NeuroLink through\nthat proxy was not exercised.\n\nBilling\n\nTinfoil's key guide (docs) describes the\nflow: sign up, click Activate on the Private Inference card, enter card details\nat checkout when no pa","hierarchy":{"lvl0":"Getting Started","lvl1":"Tinfoil Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"553cdc414eaa87c755098d10deaaadad4af926e106a7330741e0c44d7352308d","title":"Tinfoil Provider Guide","url":"/docs/getting-started/providers/tinfoil#tinfoil-provider-guide","content":"Tinfoil is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/tinfoil.json) rather than hand-written code.\nThat file is the source of truth for this page.\n\nVerification status: this entry is docs- and roster-verified, not yet\nlive-verified. The fields below come from Tinfoil's own public pages and\ntwo unauthenticated GET requests (/v1/models and /v1/chat/completions) —\nno account was created and no API key was used to build it.\nevidence.liveMatrix is null until someone runs the live capability matrix\nwith a real key (see Verification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"Tinfoil Provider Guide","lvl2":"Tinfoil Provider Guide","lvl3":""}},
 {"objectID":"59d2d8b0523c0312969cc9fd6bae755b259f60fdfdad2912f120e07be9818836","title":"Key Facts","url":"/docs/getting-started/providers/tinfoil#key-facts","content":"Provider id: tinfoil (no alias)\nProtocol: OpenAI-compatible (/chat/completions). The homepage says\n  \"Our API is OpenAI-compatible, open-source, and fully verifiable.\"\n  (tinfoil.sh) and the chat models page says \"Chat models\n  use the OpenAI chat completions API.\"\n  (docs)\nBase URL: https://inference.tinfoil.sh/v1\nDefault model: kimi-k3\nModels in catalog: 7 (the seven entries whose roster type is chat,\n  taken from a 17-entry roster)\nStreaming: supported — the structured outputs guide shows a request with\n  stream=True that reads chunk.choices[0].delta.content, under the heading\n  \"Enable Streaming for Large Responses\"\n  (docs)\nTool calling: supported (true) — the tool-calling guide documents\n  function calling (docs), and\n  the roster's tool_calling field is true on the seven catalog models\nTools while streaming: not declared (false) — no combined\n  tools-and-streaming request was sent (no credentials were used)\nStructured output: supported — the structured outputs guide documents a\n  response_format of type json_schema\n  (docs), and the seven\n  chat model cards carry a \"Structured Outputs\" line\n  (docs)\nStructured output + tools together: not declared (false) — no\n  combined probe was run without credentials\nEmbeddings: not declared (false) on this catalog entry. The roster lists\n  nomic-embed-text with type embedding\n  (docs); it is not one of the seven\n  catalog models\nThinking: declared (true) — the reasoning guide documents a\n  reasoning_effort request parameter and says the model's thinking is returned\n  in the reasoning field of the response message\n  (docs); the accepted values differ\n  by model (see Reasoning effort)\nVision: four catalog models (kimi-k3, gemma4-31b, glm-5-3-flash,\n  deepseek-v4-1-flash) — see Models\nBilling: free-with-card — see Billing below\nKey format: none validated (apiKeyFormat is null)\nConnection security: NeuroLink calls the endpoint directly over HTTPS —\n  see Direct HTTPS access","hierarchy":{"lvl0":"Getting Started","lvl1":"Tinfoil Provider Guide","lvl2":"Key Facts","lvl3":""}},
@@ -7024,6 +7222,17 @@
 {"objectID":"5e9e6668f1675d4256502fb8630f9bf1df48b4047dd465f774ea0590ea22e90d","title":"Verification status","url":"/docs/getting-started/providers/venice-ai#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog currently records for Venice AI — docs- and roster-verified, not\nlive-verified:\n\n| Probe                     | Result                                                                                                                                                                                                                                                                                                                                                                                               |\n| ------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                    | unauthenticated GET /models, HTTP 200, 126 text models, 2026-09-29 — no key used                                                                                                                                                                                                                                                                                                                   |\n| Default model             | unauthenticated GET /models/traits, HTTP 200, 2026-09-29 — returned \"default\":\"zai-org-glm-5-2\"                                                                                                                                                                                                                                                                                                  |\n| Billing                   | public pages quoted in Billing above, 2026-09-29 — recorded as ","hierarchy":{"lvl0":"Getting Started","lvl1":"Venice AI Provider Guide","lvl2":"Verification status","lvl3":""}},
 {"objectID":"f22e358b5c6033ae66d4fe4f1e34d99f0ee243e821d695933209d5ca584f9830","title":"Troubleshooting","url":"/docs/getting-started/providers/venice-ai#troubleshooting","content":"Each row is what a Venice page states; none was reproduced live.\n\n| Symptom                                       | Cause                                                                                                                                                                                                                                                                                           | Fix                                                                                                                                                                                                                           |\n| --------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| HTTP 401                                      | The API key guide says a 401 with AUTHENTICATION_FAILED means the key itself was rejected, and lists a partial copy, a Bearer prefix or quotes captured into the value, or a stray space or newline as the usual causes | The quick-start page says to paste the key exactly as Venice issued it, with no Bearer prefix, on a single line with no quotes                                        |\n| HTTP 402                                      | The error-codes page lists INSUFFICIENT_BALANCE and two per-key spend-limit codes under 402; the API key guide says that with a spend-limit code \"the cause is the key's own limit rather than your account balance\"                      | For INSUFFICIENT_BALANCE the error-codes page points to https://venice.ai/settings/a","hierarchy":{"lvl0":"Getting Started","lvl1":"Venice AI Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
 {"objectID":"47b9d2873035ce5df7122eda69ae954cde0cadb9cecd4e9978ae2d6b4080f07e","title":"See also","url":"/docs/getting-started/providers/venice-ai#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Venice AI Provider Guide","lvl2":"See also","lvl3":""}},
+{"objectID":"4d57bb4076cc1ea55086e17053d2784d81d777b2e0a8934f463aea2df3cfbe21","title":"Vispark Provider Guide","url":"/docs/getting-started/providers/vispark","content":"Vispark Provider Guide\n\nVispark is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/vispark.json) rather than hand-written code.\nThe catalog values on this page come from that file.\n\nVerification status: this entry is docs- and roster-verified, not yet\nlive-verified. The fields below come from the text of Vispark's public\nsite (https://lab.vispark.in/) and unauthenticated GET requests to\nhttps://api.lab.vispark.in/v1 — no account was created and no API key was\nused to build it. evidence.liveMatrix is null until someone runs the live\ncapability matrix with a real key (see\nVerification status below).\n\nKey Facts\nProvider id: vispark\nProtocol: OpenAI-compatible (/chat/completions) — the site's OpenAI\n  Compatibility panel says \"This model is compatible with OpenAI-compatible\n  clients.\"\nBase URL: https://api.lab.vispark.in/v1 — that panel gives the Base URL\n  https://api.lab.vispark.in. Unauthenticated GETs made 2026-09-29:\n  https://api.lab.vispark.in/v1/models and https://api.lab.vispark.in/models\n  returned the same 3-model body; https://api.lab.vispark.in/v1/chat/completions\n  and https://api.lab.vispark.in/chat/completions both answered HTTP 405\nDefault model: vispark/vision-large (NeuroLink default)\nModels in catalog: 3 — the roster returned 3 models on 2026-09-29\nStreaming: true — the Vision entry on the site reads \"Supports up to 1\n  million tokens per request with real-time streaming capabilities.\"\nTool calling: true — the Vision entry reads \"Supports Tool Calling and\n  Continual Learning; updates weights in real-time.\", and the roster lists\n  tools in supported_features for the three models. No POST request was sent\nTools while streaming: false in the catalog — the site's \"Tool Calling\n  Guide\" has a \"Streaming with Tool Calls\" section whose sample chunk shows\n  \"type\": \"tool_calls\" and \"finished\": true. No POST request was sent\nStructured output: false in the catalog — the roster lists json_mode\n  and structured_outputs in supported_features. No POST request was sent\nStructured output + tools together: false in the catalog. No POST request\n  was sent\nEmbeddings: false in the catalog — the roster's output_modalities for\n  the three models is text\nThinking: false in the catalog — the roster lists reasoning in\n  supported_features. No POST request was sent\nBilling policy field: no-free-tier is a schema placeholder (the schema\n  has no unknown value), not a vendor statement; the unit strings the site\n  shows are quoted under Billing\nKey format: apiKeyFormat is null in the catalog\n\nQuick Start\nGet an API key\nVisit: https://lab.vispark.in/profile and sign in — the playground text reads \"Sign in to run this model.\", and the site links the Vispark account system at https://account.vispark.in\nOpen API Keys in the profile sidebar (the panel is titled \"API Keys\" with the subtitle \"Manage your API keys\"), choose \"Add Key\" and complete the \"Create New API Key\" dialog\nAuthentication is HTTP Bearer: the OpenAI Compatibility panel says \"Use your standard API Key as a Bearer Token.\" and shows Authorization: Bearer <your_api_key>. The site's developer-guide text for the Vision model also lists \"Endpoint: /model/text/vision\" and \"Authentication: X-API-Key: yourapikey_here\", and the ephemeral-key panel \"Using on Model Endpoints\" shows an X-API-Key header and lists \"POST /chat/completions\" under \"Supported endpoints:\". Neither header scheme was exercised: no POST request was sent\nBilling as the site shows it: the Account tab of the profile page has a \"Buy More Units\" panel with the strings \"₹1 (INR) = 1 unit\" and \"$1 (USD) = ~95 units\"\nSet VISPARK_API_KEY in your .env file\nConfigure\nUse it\n\nPer-request credentials are passed like this:\n\nBilling\n\nThe Account tab of https://lab.vispark.in/profile has a \"Buy More Units\" panel\nwith the strings \"₹1 (INR) = 1 unit\" and \"$1 (USD) = ~95 units\", and the\nInsufficient Units dialog carries the text \"~$0.01 = ₹1 = 1 unit.\" The Vision model's price text\nis quoted in Models. The no-free-tier value in the catalog is a\nschema placeholder, not a vendor statement.\n\nModels\n\n| Model                     | Context   | Max output | Vision | $/M in · out   | Notes                                                                                                                                                                                                       |\n| ------------------------- | --------- | ---------- | ------ | -------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| vispark/vision-large ⭐ | 1,000,000 | 65,536     | yes    | $7.37 / $22.11 | NeuroLink default. Roster description: \"Vision Large: India's most advanced foundational intelligence.\" The site's size entry reads \"Slowest processing but highest intelligence and accuracy\".             |\n| vispark/vision-medium   | 1,000,000 ","hierarchy":{"lvl0":"Getting Started","lvl1":"Vispark Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"058095deb707ccac0ce5ef385d9f7b90e47fdb58ea3c24d1f9906ad654721d3b","title":"Vispark Provider Guide","url":"/docs/getting-started/providers/vispark#vispark-provider-guide","content":"Vispark is a Tier-2 catalog provider: its integration is one JSON file\n(src/lib/providers/catalog/vispark.json) rather than hand-written code.\nThe catalog values on this page come from that file.\n\nVerification status: this entry is docs- and roster-verified, not yet\nlive-verified. The fields below come from the text of Vispark's public\nsite (https://lab.vispark.in/) and unauthenticated GET requests to\nhttps://api.lab.vispark.in/v1 — no account was created and no API key was\nused to build it. evidence.liveMatrix is null until someone runs the live\ncapability matrix with a real key (see\nVerification status below).","hierarchy":{"lvl0":"Getting Started","lvl1":"Vispark Provider Guide","lvl2":"Vispark Provider Guide","lvl3":""}},
+{"objectID":"81b81d8850b95a64740c6a1716e877b8095b6d9ad856e2eaaf756af7c4a9cc51","title":"Key Facts","url":"/docs/getting-started/providers/vispark#key-facts","content":"Provider id: vispark\nProtocol: OpenAI-compatible (/chat/completions) — the site's OpenAI\n  Compatibility panel says \"This model is compatible with OpenAI-compatible\n  clients.\"\nBase URL: https://api.lab.vispark.in/v1 — that panel gives the Base URL\n  https://api.lab.vispark.in. Unauthenticated GETs made 2026-09-29:\n  https://api.lab.vispark.in/v1/models and https://api.lab.vispark.in/models\n  returned the same 3-model body; https://api.lab.vispark.in/v1/chat/completions\n  and https://api.lab.vispark.in/chat/completions both answered HTTP 405\nDefault model: vispark/vision-large (NeuroLink default)\nModels in catalog: 3 — the roster returned 3 models on 2026-09-29\nStreaming: true — the Vision entry on the site reads \"Supports up to 1\n  million tokens per request with real-time streaming capabilities.\"\nTool calling: true — the Vision entry reads \"Supports Tool Calling and\n  Continual Learning; updates weights in real-time.\", and the roster lists\n  tools in supported_features for the three models. No POST request was sent\nTools while streaming: false in the catalog — the site's \"Tool Calling\n  Guide\" has a \"Streaming with Tool Calls\" section whose sample chunk shows\n  \"type\": \"tool_calls\" and \"finished\": true. No POST request was sent\nStructured output: false in the catalog — the roster lists json_mode\n  and structured_outputs in supported_features. No POST request was sent\nStructured output + tools together: false in the catalog. No POST request\n  was sent\nEmbeddings: false in the catalog — the roster's output_modalities for\n  the three models is text\nThinking: false in the catalog — the roster lists reasoning in\n  supported_features. No POST request was sent\nBilling policy field: no-free-tier is a schema placeholder (the schema\n  has no unknown value), not a vendor statement; the unit strings the site\n  shows are quoted under Billing\nKey format: apiKeyFormat is null in the catalog","hierarchy":{"lvl0":"Getting Started","lvl1":"Vispark Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"c293b1a7209ba40dd45d264dfdeb30c74adac5ceafa614d073e5310dd3047c8f","title":"1. Get an API key","url":"/docs/getting-started/providers/vispark#1-get-an-api-key","content":"Visit: https://lab.vispark.in/profile and sign in — the playground text reads \"Sign in to run this model.\", and the site links the Vispark account system at https://account.vispark.in\nOpen API Keys in the profile sidebar (the panel is titled \"API Keys\" with the subtitle \"Manage your API keys\"), choose \"Add Key\" and complete the \"Create New API Key\" dialog\nAuthentication is HTTP Bearer: the OpenAI Compatibility panel says \"Use your standard API Key as a Bearer Token.\" and shows Authorization: Bearer <your_api_key>. The site's developer-guide text for the Vision model also lists \"Endpoint: /model/text/vision\" and \"Authentication: X-API-Key: yourapikey_here\", and the ephemeral-key panel \"Using on Model Endpoints\" shows an X-API-Key header and lists \"POST /chat/completions\" under \"Supported endpoints:\". Neither header scheme was exercised: no POST request was sent\nBilling as the site shows it: the Account tab of the profile page has a \"Buy More Units\" panel with the strings \"₹1 (INR) = 1 unit\" and \"$1 (USD) = ~95 units\"\nSet VISPARK_API_KEY in your .env file","hierarchy":{"lvl0":"Getting Started","lvl1":"Vispark Provider Guide","lvl2":"1. Get an API key","lvl3":""}},
+{"objectID":"db6688b3a02a56f1bbfa9d81388e5c51e2a54cda4dd6a44cb18cf5f2439b92fc","title":"3. Use it","url":"/docs/getting-started/providers/vispark#3-use-it","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Vispark Provider Guide","lvl2":"3. Use it","lvl3":""}},
+{"objectID":"c9dc4830e2b38d170687117e9ce0a99dfcdc4746c643267dccf6a275ffabf6dd","title":"CLI","url":"/docs/getting-started/providers/vispark#cli","content":"npx @juspay/neurolink generate \"Hello\" --provider vispark\ntypescript\nawait neurolink.generate({\n  input: { text: \"Hello\" },\n  provider: \"vispark\",\n  credentials: { vispark: { apiKey: process.env.VISPARKAPIKEY } },\n});\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"Vispark Provider Guide","lvl2":"CLI","lvl3":""}},
+{"objectID":"8600718c64918cd42149d5c287105367581e242511d81edc02ade1c711e4225a","title":"Billing","url":"/docs/getting-started/providers/vispark#billing","content":"The Account tab of https://lab.vispark.in/profile has a \"Buy More Units\" panel\nwith the strings \"₹1 (INR) = 1 unit\" and \"$1 (USD) = ~95 units\", and the\nInsufficient Units dialog carries the text \"~$0.01 = ₹1 = 1 unit.\" The Vision model's price text\nis quoted in Models. The no-free-tier value in the catalog is a\nschema placeholder, not a vendor statement.","hierarchy":{"lvl0":"Getting Started","lvl1":"Vispark Provider Guide","lvl2":"Billing","lvl3":""}},
+{"objectID":"3091dae1618c61c3b6c5ba6b6f6656da4056c25caed3526e0499c3d176dd2bbc","title":"Models","url":"/docs/getting-started/providers/vispark#models","content":"| Model                     | Context   | Max output | Vision | $/M in · out   | Notes                                                                                                                                                                                                       |\n| ------------------------- | --------- | ---------- | ------ | -------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| vispark/vision-large ⭐ | 1,000,000 | 65,536     | yes    | $7.37 / $22.11 | NeuroLink default. Roster description: \"Vision Large: India's most advanced foundational intelligence.\" The site's size entry reads \"Slowest processing but highest intelligence and accuracy\".             |\n| vispark/vision-medium   | 1,000,000 | 65,536     | yes    | $4.21 / $12.63 | Fallback. Roster description: \"Vision Medium: A versatile foundational model built for the world on Indian infrastructure.\" The site's size entry reads \"Balanced processing speed with good intelligence\". |\n| vispark/vision-small    | 1,000,000 | 65,536     | yes    | $1.05 / $3.16  | Fallback. Roster description: \"Vision Small: India's fast and efficient foundational AI.\" The site's size entry reads \"Fastest processing speed with basic intelligence\".                                   |\n\nContext, max output, prices and modalities come from an unauthenticated\nGET https://api.lab.vispark.in/v1/models call made 2026-09-29 (3 models; 3 in\nthis catalog): context_length 1000000, max_output_length 65536, and\ninput_modalities text, image, audio, video, file for the three\nmodels. The $/M figures are the roster's pricing.prompt and\npricing.completion strings times 1,000,000 (\"0.00000737\" and\n\"0.00002211\" for vispark/vision-large, \"0.00000421\" and \"0.00001263\"\nfor vispark/vision-medium, \"0.00000105\" and \"0.00000316\" for\nvispark/vision-small).\n\nThe site's pric","hierarchy":{"lvl0":"Getting Started","lvl1":"Vispark Provider Guide","lvl2":"Models","lvl3":""}},
+{"objectID":"e4ade222d9dd9ddf6c39293e1110999d1af487bd9d036a002c7bac30b2576559","title":"Vendor-stated error handling","url":"/docs/getting-started/providers/vispark#vendor-stated-error-handling","content":"These lines are quoted from the Vision model's Limitations text on the site\n(script https://lab.vispark.in/assets/index-WmfFPhvJ.js, retrieved 2026-09-29).\nThey are the vendor's wording, not NeuroLink behaviour, and the catalog's\nerrorRules (401, 402, 429) carry them:\n\"Check HTTP status codes (200, 400, 401, 402, 429)\"\n\"Handle rate limiting with exponential backoff\"\n\"Validate API keys and sufficient units\"\n\"API rate limit: 240 requests/minute\"\n\nThe site's script also uses \"Insufficient units for this operation\" as the\nfallback message for HTTP 402.","hierarchy":{"lvl0":"Getting Started","lvl1":"Vispark Provider Guide","lvl2":"Vendor-stated error handling","lvl3":""}},
+{"objectID":"5ca724dc8e534794bc5f296a62cb8f16d6ab66820149dfcbbd8158e9715c3bea","title":"Verification status","url":"/docs/getting-started/providers/vispark#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog currently records for Vispark — docs- and roster-verified, not\nlive-verified:\n\n| Probe                     | Result                                                                                                                                                                                                                                                                                                          |\n| ------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Roster                    | unauthenticated GET /v1/models, HTTP 200, 3 models, 2026-09-29 — no key used; GET https://api.lab.vispark.in/models returned the same body                                                                                                                                                                  |\n| Billing                   | public script strings \"₹1 (INR) = 1 unit\" and \"$1 (USD) = ~95 units\" from the Buy More Units panel, 2026-09-29                                                                                                                                                                                                  |\n| Auth-failure shape        | unauthenticated GET https://api.lab.vispark.in/v1/chat/completions returned HTTP 405 with an HTML body titled \"405 Method Not Allowed\"; no authProbe is recorded, and errorRules carry the status codes and sentences of the site's Limitations text                                                      |\n| Tools / structured output | the roster lists tools, json_mode and structured_outputs in supported_fea","hierarchy":{"lvl0":"Getting Started","lvl1":"Vispark Provider Guide","lvl2":"Verification status","lvl3":""}},
+{"objectID":"63bacfbbc9e2a5c03913f476a9d338eae6e74d9327173facaaad42accae7744a","title":"See also","url":"/docs/getting-started/providers/vispark#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding — how this provider's JSON becomes a working integration\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Vispark Provider Guide","lvl2":"See also","lvl3":""}},
 {"objectID":"f336420da8773b8ccbfbb545df2bfb3a8201804c4d38fa8408ac119ad21d8317","title":"Voyage AI Provider Guide","url":"/docs/getting-started/providers/voyage","content":"Voyage AI Provider Guide\n\nTop-tier RAG embeddings — text-only provider exposing embed() and\nembedMany() (chat / streaming intentionally not supported)\n\nOverview\n\nVoyage AI provides some of the highest-accuracy text embeddings available\ntoday, particularly strong on retrieval and reranking benchmarks. NeuroLink\nwraps api.voyageai.com/v1/embeddings so the same embed() / embedMany()\ncontract used by every other embedding-capable provider works for Voyage.\nvoyage-4 — newest general-purpose flagship (not yet the default)\nvoyage-4-large — largest / highest accuracy in the 4.x line\nvoyage-4-lite — smaller / cheaper 4.x variant\nvoyage-code-4 — code-tuned (best for code retrieval), 4.x line\nvoyage-3.5 — general-purpose (default)\nvoyage-3-large — flagship; highest accuracy\nvoyage-3.5-lite — smaller / cheaper\nvoyage-code-3 — code-tuned (best for code retrieval)\nvoyage-finance-2, voyage-law-2 — domain-tuned\nvoyage-multilingual-2 — non-English / cross-lingual\n\nKey Facts\nProtocol: Native REST API (/embeddings only — not OpenAI-compat\n  for chat)\nDefault base URL: https://api.voyageai.com/v1\nDefault model: voyage-3.5\nMax input tokens: 32K (16K on voyage-law-2)\nStreaming / chat / tool calling: NOT supported (embedding-only;\n  executeStream and getAISDKModel throw a friendly error)\nPricing: Per-million input tokens; output dimension is the\n  embedding vector, not generated tokens\n\nQuick Start\nGet an API Key\n\nSign up at https://www.voyageai.com/ and\ncreate an API key at\nhttps://dash.voyageai.com/api-keys.\nConfigure Environment\nGenerate Your First Embedding\n\nSDK Usage\n\nSingle Embedding\n\nBatch Embeddings\n\nCode Embeddings\n\nPer-Call Credentials\n\nUse with NeuroLink RAG\n\nVoyage embeddings plug into NeuroLink's RAG pipeline. Configure the RAG\nembedder to use Voyage:\n\nCLI Usage\n\nVoyage is embedding-only — there is no cli generate flow because\ngenerate is a chat-completion path. Use the SDK directly, or use Voyage\nas the embedder behind a RAG-enabled cli generate:\n\nProvider Aliases\n\n| Alias       | Example                |\n| ----------- | ---------------------- |\n| voyage    | --provider voyage    |\n| voyage-ai | --provider voyage-ai |\n\n(Note: aliases are mostly relevant for RAG embedder routing; standalone\nchat use is not supported.)\n\nConfiguration Reference\n\n| Environment Variable | Required | Default                       | Description             |\n| -------------------- | -------- | ----------------------------- | ----------------------- |\n| VOYAGE_API_KEY     | Yes      | —                             | Voyage AI API key       |\n| VOYAGE_MODEL       | No       | voyage-3.5                  | Default embedding model |\n| VOYAGE_BASE_URL    | No       | https://api.voyageai.com/v1 | Base URL                |\n\nModel Reference\n\nPer the Voyage embeddings docs:\n\n| Model                   | Default dim | Tokens | Best For                        |\n| ----------------------- | ----------- | ------ | ------------------------------- |\n| voyage-4              | 1024        | 32K    | General-purpose, 4.x line       |\n| voyage-4-large        | 1024        | 32K    | Flagship, highest quality (4.x) |\n| voyage-4-lite         | 1024        | 32K    | Smaller / cheaper (4.x)         |\n| voyage-code-4         | 1024        | 32K    | Code retrieval (4.x)            |\n| voyage-3.5            | 1024        | 32K    | General-purpose (default)       |\n| voyage-3.5-lite       | 1024        | 32K    | Smaller / cheaper               |\n| voyage-3-large        | 1024        | 32K    | Flagship; highest accuracy      |\n| voyage-code-3         | 1024        | 32K    | Code retrieval                  |\n| voyage-finance-2      | 1024        | 32K    | Finance domain                  |\n| voyage-law-2          | 1024        | 16K    | Legal domain                    |\n| voyage-multilingual-2 | unspecified | 32K    | Cross-lingual                   |\n\nMatryoshka flexible dimensions: voyage-4, voyage-4-large,\nvoyage-4-lite, voyage-code-4, voyage-3.5, voyage-3.5-lite,\nvoyage-3-large, and voyage-code-3 all support flexible output dimensions\nof 256 / 512 / 1024 / 2048 via the output_dimension parameter on the\nVoyage API. The default (and what NeuroLink currently returns) is 1024.\nvoyage-finance-2, voyage-law-2, and voyage-multilingual-2 only emit\nthe default dimension. See the FAQ below for how to request a smaller\ndimension explicitly.\n\nFeature Support Matrix\n\n| Feature         | voyage-3.5           | voyage-3-large | voyage-code-3 |\n| --------------- | -------------------- | -------------- | ------------- |\n| Embeddings      | Yes                  | Yes            | Yes           |\n| Single embed    | Yes                  | Yes            | Yes           |\n| Batch embed     | Yes (128 inputs/req) | Yes            | Yes           |\n| Text generation | No                   | No             | No            |\n| Streaming       | No                   | No             | No            |\n| Tool calling    | No                   | No             | No            |\n| Visio","hierarchy":{"lvl0":"Getting Started","lvl1":"Voyage AI Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"31d0a4981c0396028c8536380313b4d38511b6fe67e0f49e8e81c35a49bc48f8","title":"Voyage AI Provider Guide","url":"/docs/getting-started/providers/voyage#voyage-ai-provider-guide","content":"Top-tier RAG embeddings — text-only provider exposing embed() and\nembedMany() (chat / streaming intentionally not supported)","hierarchy":{"lvl0":"Getting Started","lvl1":"Voyage AI Provider Guide","lvl2":"Voyage AI Provider Guide","lvl3":""}},
 {"objectID":"15e3c23ac4bbda64e2a47a5490232b7076df375e991209c644e9fade69a3db62","title":"Overview","url":"/docs/getting-started/providers/voyage#overview","content":"Voyage AI provides some of the highest-accuracy text embeddings available\ntoday, particularly strong on retrieval and reranking benchmarks. NeuroLink\nwraps api.voyageai.com/v1/embeddings so the same embed() / embedMany()\ncontract used by every other embedding-capable provider works for Voyage.\nvoyage-4 — newest general-purpose flagship (not yet the default)\nvoyage-4-large — largest / highest accuracy in the 4.x line\nvoyage-4-lite — smaller / cheaper 4.x variant\nvoyage-code-4 — code-tuned (best for code retrieval), 4.x line\nvoyage-3.5 — general-purpose (default)\nvoyage-3-large — flagship; highest accuracy\nvoyage-3.5-lite — smaller / cheaper\nvoyage-code-3 — code-tuned (best for code retrieval)\nvoyage-finance-2, voyage-law-2 — domain-tuned\nvoyage-multilingual-2 — non-English / cross-lingual","hierarchy":{"lvl0":"Getting Started","lvl1":"Voyage AI Provider Guide","lvl2":"Overview","lvl3":""}},
@@ -9412,8 +9621,8 @@
 {"objectID":"da986710e206bdfe9e761b9941c084a698a400e499994510b53989e7685fd3a6","title":"Must remain class (14)","url":"/docs/provider-integration/migration-ledger#must-remain-class-14","content":"| Provider     | Why                                                                                                                                                                                                                                                                                                                                                                        |\n| ------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| bedrock    | AWS SigV4/Converse protocol, custom loop, not OpenAI-compatible. Tier 4.                                                                                                                                                                                                                                                                                                   |\n| openai     | Chat portion is catalog-shaped, but embeddings, image generation, and OpenAI-specific telemetry/errors are executable behavior.                                                                                                                                                                                                                                            |\n| vertex     | Two native protocols (Google GenAI + Anthropic-on-Vertex) and multiple modality pipelines behind one provider identity.                                                                                                                                                                                                                                                    |\n| anthropic  | Native Messages API auth/message/tool semantics are executable protocol behavior.","hierarchy":{"lvl0":"Provider Integration","lvl1":"Provider Descriptor Migration Ledger","lvl2":"Must remain class (14)","lvl3":""}},
 {"objectID":"a4f69e09308f075830f2efa7c1b0126236c5ec0fc12bfe08be21764a627e47a5","title":"Must remain core class (1)","url":"/docs/provider-integration/migration-ledger#must-remain-core-class-1","content":"| Provider            | Why                                                                                                                                                                                                                                                                           |\n| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| openai-compatible | This is the generic protocol surface itself, not a direct vendor. It should consume shared descriptor/config primitives but must never become a fixed-vendor JSON row — collapsing it into the catalog would conflate \"the adapter\" with \"an entry in the adapter's catalog.\" |","hierarchy":{"lvl0":"Provider Integration","lvl1":"Provider Descriptor Migration Ledger","lvl2":"Must remain core class (1)","lvl3":""}},
 {"objectID":"235850085d9102413140920b9d5e5e2ff6113d007c865f5d78012af80fbf1843","title":"Suggested execution order","url":"/docs/provider-integration/migration-ledger#suggested-execution-order","content":"The former steps 1–2 below (mistral; huggingface, deepseek) are complete — see Migrated above. What remains:\nThree shared adapters (local-runtime, embedding-only, image-generation) — each unlocks 3 providers at once; build once, migrate three.\ngoogle-ai descriptor-only JSON metadata — proof of concept for moving static descriptor data out of a \"must remain class\" provider without touching its execution.\nDirect-vendor \"must remain class\" providers (bedrock, openai, vertex, anthropic, azure, sagemaker, nvidia-nim) get descriptor-only JSON metadata migrations, execution untouched — lower priority, cosmetic consolidation only.\nAggregators (litellm, openrouter), the core adapter (openai-compatible), and the decision-only providers (typesafe, laya, xor) are excluded from the first-class-count migration priority entirely — the first three add no direct-vendor coverage however they're implemented, and typesafe/laya/xor are decide-only providers with no generate/stream surface to migrate at all.","hierarchy":{"lvl0":"Provider Integration","lvl1":"Provider Descriptor Migration Ledger","lvl2":"Suggested execution order","lvl3":""}},
-{"objectID":"6122b2e83358a45c64da87c1ca80a2d579cdfb087a6d9dc58b1e02805296b14a","title":"OpenAI-Compatible Provider Catalog","url":"/docs/provider-integration/openai-compat-catalog","content":"OpenAI-Compatible Provider Catalog\n\nEvery OpenAI-compatible provider in the catalog (61 as of 2026-09-29; the\ndirectory is the list) is registered from one JSON file each, under\nsrc/lib/providers/catalog/<id>.json, and served by one generic class,\nConfiguredOpenAICompatProvider\n(src/lib/providers/configuredOpenAICompat.ts). Adding another provider to\nthis family means adding one JSON file — no subclass, no registry edit, no\nhand-written enum member, no test edit.\n\nThe JSON is the source of truth\n\nOPENAI_COMPAT_CATALOG still exists and keeps its name and element type,\nbut it is now built by the loader (src/lib/providers/catalog/loader.ts)\nfrom the JSON files rather than hand-written. Two consumers read the JSON:\nCodegen (pnpm run codegen:catalog) writes the compile-time\n  artifacts into marked regions — the AIProviderName member, the\n  <Name>Models enum, the NeurolinkCredentials key — plus the generated\n  index. Pre-commit and CI fail on stale output.\nThe loader builds the runtime entry; the descriptor, config options,\n  context windows, pricing, vision map and model-choice tables all derive\n  from it, as do the provider test suites' rows and counts.\n\nEach file is validated by a zod schema (src/lib/providers/catalog/schema.ts)\nwith a mirrored provider-catalog.schema.json for editor squiggles.\nProbe evidence (roster/auth/billing dates, live-matrix result, PR URL)\nlives in the file's evidence block — the old\ndocs/provider-integration/manifests/<id>.json files were folded into it.\n\nField-by-field reference and the escape hatches:\ntiers/tier-2-catalog-entry.md. Design rationale and the approved rulings:\ndocs/superpowers/plans/2026-08-28-provider-json-catalog-spec.md.\n\nWhen a provider belongs in the catalog\n\nA provider belongs in the JSON catalog if it needs only:\na credential (API key, optionally an extra field like Cloudflare's account id)\na base URL (static default + optional env override, or computed from an\n  extra credential field)\na default/fallback model\nerror-message classification (auth / rate-limit / invalid-model / generic)\na named, closed catalog quirk. DeepSeek is the worked example: it 400s on\n  json_schema structured-output requests, so deepseek.json sets\n  quirks.responseFormatDowngrade: \"json-schema-to-json-object\" and the\n  generic ConfiguredOpenAICompatProvider downgrades to json_object before\n  sending — no subclass. It also sets quirks.replayReasoningContent: true:\n  DeepSeek documents that each assistant turn's reasoning_content must go\n  back on later requests once tools are in play, so the shared message\n  converter and the streaming tool loop send it — for this quirk only, since\n  strict OpenAI-compatible backends reject the unknown field.\na wire-proven capability such as\n  capabilities.structuredOutputWithTools. The generic provider suppresses\n  response_format when tools are attached by default; an explicit true\n  keeps it on the same generate() or stream() request. Set this only after\n  a combined tools-plus-schema request returned successfully. Separate tool\n  and structured-output probes are not evidence for the combined capability.\n  A stale opt-in is still protected by the runtime conflict retry, which drops\n  structured output and retries rather than losing the turn.\n\nThe currently opted-in providers are Baseten, DeepSeek, Fireworks AI, GMI\nCloud, Inception Labs, io.net Intelligence, Novita AI, Together AI, Upstage and\nxAI. API Route remains opted out because its evidence verifies the features\nseparately, not together in one request. Mistral remains opted out because its\ncombined probes returned 429 twice, not a successful capability response.\n\nWhen a provider needs a dedicated subclass instead\n\nAzure OpenAI is deliberately not in the catalog because it overrides real\nrequest-shaping behavior that no named catalog quirk expresses:\nAzure OpenAI (src/lib/providers/azureOpenai.ts) overrides four hooks:\n  getChatCompletionsURL (deployment-name URL routing across two Azure\n  endpoint schemes), getAuthHeaders (Azure's api-key header instead of\n  Authorization: Bearer), adjustRequestBody (renames max_tokens to\n  max_completion_tokens for o-series/gpt-5+ deployments), and\n  suppressResponseFormatWithTools (Azure supports both at once).\n\nIf a future provider needs any hook beyond the 3 mandatory ones\n(getProviderName, getDefaultModel, formatProviderError) or the 2\npurely-declarative optional ones (getFallbackModelName,\ngetFallbackModels) and that hook is not already a named catalog quirk, it\nneeds either a new closed quirk (the DeepSeek route) or a dedicated subclass\n(the Azure OpenAI route).\n\nError-message fidelity\n\nEach entry's errorRules is a direct, order-preserving translation of its\noriginal subclass's formatProviderError if/else ladder into rule data\n(status code and/or case-insensitive pattern), classified via\nclassifyProviderError()\n(src/lib/utils/errorClassifier.ts). Every bespoke message string is\npreserved verbatim — including xAI's \"top up your account\" quota URL and\nGroq's d","hierarchy":{"lvl0":"Provider Integration","lvl1":"OpenAI-Compatible Provider Catalog","lvl2":"","lvl3":""}},
-{"objectID":"9a91a5b4a32a9f1e89c6a28f762c3594c4a39d96d32cc9e6e1fa0f5cb3f609e4","title":"OpenAI-Compatible Provider Catalog","url":"/docs/provider-integration/openai-compat-catalog#openai-compatible-provider-catalog","content":"Every OpenAI-compatible provider in the catalog (61 as of 2026-09-29; the\ndirectory is the list) is registered from one JSON file each, under\nsrc/lib/providers/catalog/<id>.json, and served by one generic class,\nConfiguredOpenAICompatProvider\n(src/lib/providers/configuredOpenAICompat.ts). Adding another provider to\nthis family means adding one JSON file — no subclass, no registry edit, no\nhand-written enum member, no test edit.","hierarchy":{"lvl0":"Provider Integration","lvl1":"OpenAI-Compatible Provider Catalog","lvl2":"OpenAI-Compatible Provider Catalog","lvl3":""}},
+{"objectID":"6122b2e83358a45c64da87c1ca80a2d579cdfb087a6d9dc58b1e02805296b14a","title":"OpenAI-Compatible Provider Catalog","url":"/docs/provider-integration/openai-compat-catalog","content":"OpenAI-Compatible Provider Catalog\n\nEvery OpenAI-compatible provider in the catalog (80 as of 2026-09-29; the\ndirectory is the list) is registered from one JSON file each, under\nsrc/lib/providers/catalog/<id>.json, and served by one generic class,\nConfiguredOpenAICompatProvider\n(src/lib/providers/configuredOpenAICompat.ts). Adding another provider to\nthis family means adding one JSON file — no subclass, no registry edit, no\nhand-written enum member, no test edit.\n\nThe JSON is the source of truth\n\nOPENAI_COMPAT_CATALOG still exists and keeps its name and element type,\nbut it is now built by the loader (src/lib/providers/catalog/loader.ts)\nfrom the JSON files rather than hand-written. Two consumers read the JSON:\nCodegen (pnpm run codegen:catalog) writes the compile-time\n  artifacts into marked regions — the AIProviderName member, the\n  <Name>Models enum, the NeurolinkCredentials key — plus the generated\n  index. Pre-commit and CI fail on stale output.\nThe loader builds the runtime entry; the descriptor, config options,\n  context windows, pricing, vision map and model-choice tables all derive\n  from it, as do the provider test suites' rows and counts.\n\nEach file is validated by a zod schema (src/lib/providers/catalog/schema.ts)\nwith a mirrored provider-catalog.schema.json for editor squiggles.\nProbe evidence (roster/auth/billing dates, live-matrix result, PR URL)\nlives in the file's evidence block — the old\ndocs/provider-integration/manifests/<id>.json files were folded into it.\n\nField-by-field reference and the escape hatches:\ntiers/tier-2-catalog-entry.md. Design rationale and the approved rulings:\ndocs/superpowers/plans/2026-08-28-provider-json-catalog-spec.md.\n\nWhen a provider belongs in the catalog\n\nA provider belongs in the JSON catalog if it needs only:\na credential (API key, optionally an extra field like Cloudflare's account id)\na base URL (static default + optional env override, or computed from an\n  extra credential field)\na default/fallback model\nerror-message classification (auth / rate-limit / invalid-model / generic)\na named, closed catalog quirk. DeepSeek is the worked example: it 400s on\n  json_schema structured-output requests, so deepseek.json sets\n  quirks.responseFormatDowngrade: \"json-schema-to-json-object\" and the\n  generic ConfiguredOpenAICompatProvider downgrades to json_object before\n  sending — no subclass. It also sets quirks.replayReasoningContent: true:\n  DeepSeek documents that each assistant turn's reasoning_content must go\n  back on later requests once tools are in play, so the shared message\n  converter and the streaming tool loop send it — for this quirk only, since\n  strict OpenAI-compatible backends reject the unknown field.\na wire-proven capability such as\n  capabilities.structuredOutputWithTools. The generic provider suppresses\n  response_format when tools are attached by default; an explicit true\n  keeps it on the same generate() or stream() request. Set this only after\n  a combined tools-plus-schema request returned successfully. Separate tool\n  and structured-output probes are not evidence for the combined capability.\n  A stale opt-in is still protected by the runtime conflict retry, which drops\n  structured output and retries rather than losing the turn.\n\nThe currently opted-in providers are Baseten, DeepSeek, Fireworks AI, GMI\nCloud, Inception Labs, io.net Intelligence, Novita AI, Together AI, Upstage and\nxAI. API Route remains opted out because its evidence verifies the features\nseparately, not together in one request. Mistral remains opted out because its\ncombined probes returned 429 twice, not a successful capability response.\n\nWhen a provider needs a dedicated subclass instead\n\nAzure OpenAI is deliberately not in the catalog because it overrides real\nrequest-shaping behavior that no named catalog quirk expresses:\nAzure OpenAI (src/lib/providers/azureOpenai.ts) overrides four hooks:\n  getChatCompletionsURL (deployment-name URL routing across two Azure\n  endpoint schemes), getAuthHeaders (Azure's api-key header instead of\n  Authorization: Bearer), adjustRequestBody (renames max_tokens to\n  max_completion_tokens for o-series/gpt-5+ deployments), and\n  suppressResponseFormatWithTools (Azure supports both at once).\n\nIf a future provider needs any hook beyond the 3 mandatory ones\n(getProviderName, getDefaultModel, formatProviderError) or the 2\npurely-declarative optional ones (getFallbackModelName,\ngetFallbackModels) and that hook is not already a named catalog quirk, it\nneeds either a new closed quirk (the DeepSeek route) or a dedicated subclass\n(the Azure OpenAI route).\n\nError-message fidelity\n\nEach entry's errorRules is a direct, order-preserving translation of its\noriginal subclass's formatProviderError if/else ladder into rule data\n(status code and/or case-insensitive pattern), classified via\nclassifyProviderError()\n(src/lib/utils/errorClassifier.ts). Every bespoke message string is\npreserved verbatim — including xAI's \"top up your account\" quota URL and\nGroq's d","hierarchy":{"lvl0":"Provider Integration","lvl1":"OpenAI-Compatible Provider Catalog","lvl2":"","lvl3":""}},
+{"objectID":"9a91a5b4a32a9f1e89c6a28f762c3594c4a39d96d32cc9e6e1fa0f5cb3f609e4","title":"OpenAI-Compatible Provider Catalog","url":"/docs/provider-integration/openai-compat-catalog#openai-compatible-provider-catalog","content":"Every OpenAI-compatible provider in the catalog (80 as of 2026-09-29; the\ndirectory is the list) is registered from one JSON file each, under\nsrc/lib/providers/catalog/<id>.json, and served by one generic class,\nConfiguredOpenAICompatProvider\n(src/lib/providers/configuredOpenAICompat.ts). Adding another provider to\nthis family means adding one JSON file — no subclass, no registry edit, no\nhand-written enum member, no test edit.","hierarchy":{"lvl0":"Provider Integration","lvl1":"OpenAI-Compatible Provider Catalog","lvl2":"OpenAI-Compatible Provider Catalog","lvl3":""}},
 {"objectID":"16e60ee66171009a6638b5110cc8693f90c1a2cfde796c6932c3512d7f7421fb","title":"The JSON is the source of truth","url":"/docs/provider-integration/openai-compat-catalog#the-json-is-the-source-of-truth","content":"OPENAI_COMPAT_CATALOG still exists and keeps its name and element type,\nbut it is now built by the loader (src/lib/providers/catalog/loader.ts)\nfrom the JSON files rather than hand-written. Two consumers read the JSON:\nCodegen (pnpm run codegen:catalog) writes the compile-time\n  artifacts into marked regions — the AIProviderName member, the\n  <Name>Models enum, the NeurolinkCredentials key — plus the generated\n  index. Pre-commit and CI fail on stale output.\nThe loader builds the runtime entry; the descriptor, config options,\n  context windows, pricing, vision map and model-choice tables all derive\n  from it, as do the provider test suites' rows and counts.\n\nEach file is validated by a zod schema (src/lib/providers/catalog/schema.ts)\nwith a mirrored provider-catalog.schema.json for editor squiggles.\nProbe evidence (roster/auth/billing dates, live-matrix result, PR URL)\nlives in the file's evidence block — the old\ndocs/provider-integration/manifests/<id>.json files were folded into it.\n\nField-by-field reference and the escape hatches:\ntiers/tier-2-catalog-entry.md. Design rationale and the approved rulings:\ndocs/superpowers/plans/2026-08-28-provider-json-catalog-spec.md.","hierarchy":{"lvl0":"Provider Integration","lvl1":"OpenAI-Compatible Provider Catalog","lvl2":"The JSON is the source of truth","lvl3":""}},
 {"objectID":"00a7366eb480e85f5377e0cb8575403e7fd9b33cc028bf95cf0fe48cc94fcea9","title":"When a provider belongs in the catalog","url":"/docs/provider-integration/openai-compat-catalog#when-a-provider-belongs-in-the-catalog","content":"A provider belongs in the JSON catalog if it needs only:\na credential (API key, optionally an extra field like Cloudflare's account id)\na base URL (static default + optional env override, or computed from an\n  extra credential field)\na default/fallback model\nerror-message classification (auth / rate-limit / invalid-model / generic)\na named, closed catalog quirk. DeepSeek is the worked example: it 400s on\n  json_schema structured-output requests, so deepseek.json sets\n  quirks.responseFormatDowngrade: \"json-schema-to-json-object\" and the\n  generic ConfiguredOpenAICompatProvider downgrades to json_object before\n  sending — no subclass. It also sets quirks.replayReasoningContent: true:\n  DeepSeek documents that each assistant turn's reasoning_content must go\n  back on later requests once tools are in play, so the shared message\n  converter and the streaming tool loop send it — for this quirk only, since\n  strict OpenAI-compatible backends reject the unknown field.\na wire-proven capability such as\n  capabilities.structuredOutputWithTools. The generic provider suppresses\n  response_format when tools are attached by default; an explicit true\n  keeps it on the same generate() or stream() request. Set this only after\n  a combined tools-plus-schema request returned successfully. Separate tool\n  and structured-output probes are not evidence for the combined capability.\n  A stale opt-in is still protected by the runtime conflict retry, which drops\n  structured output and retries rather than losing the turn.\n\nThe currently opted-in providers are Baseten, DeepSeek, Fireworks AI, GMI\nCloud, Inception Labs, io.net Intelligence, Novita AI, Together AI, Upstage and\nxAI. API Route remains opted out because its evidence verifies the features\nseparately, not together in one request. Mistral remains opted out because its\ncombined probes returned 429 twice, not a successful capability response.","hierarchy":{"lvl0":"Provider Integration","lvl1":"OpenAI-Compatible Provider Catalog","lvl2":"When a provider belongs in the catalog","lvl3":""}},
 {"objectID":"c2a9e3425a4cecb520467f900df8b5fa78fc4178514eba6385040bb9506e48ee","title":"When a provider needs a dedicated subclass instead","url":"/docs/provider-integration/openai-compat-catalog#when-a-provider-needs-a-dedicated-subclass-instead","content":"Azure OpenAI is deliberately not in the catalog because it overrides real\nrequest-shaping behavior that no named catalog quirk expresses:\nAzure OpenAI (src/lib/providers/azureOpenai.ts) overrides four hooks:\n  getChatCompletionsURL (deployment-name URL routing across two Azure\n  endpoint schemes), getAuthHeaders (Azure's api-key header instead of\n  Authorization: Bearer), adjustRequestBody (renames max_tokens to\n  max_completion_tokens for o-series/gpt-5+ deployments), and\n  suppressResponseFormatWithTools (Azure supports both at once).\n\nIf a future provider needs any hook beyond the 3 mandatory ones\n(getProviderName, getDefaultModel, formatProviderError) or the 2\npurely-declarative optional ones (getFallbackModelName,\ngetFallbackModels) and that hook is not already a named catalog quirk, it\nneeds either a new closed quirk (the DeepSeek route) or a dedicated subclass\n(the Azure OpenAI route).","hierarchy":{"lvl0":"Provider Integration","lvl1":"OpenAI-Compatible Provider Catalog","lvl2":"When a provider needs a dedicated subclass instead","lvl3":""}},