@juspay/neurolink 12.39.0 → 12.40.0

package/dist/providers/catalog/nebius.json

@@ -0,0 +1,165 @@
+{
+    "$schema": "./provider-catalog.schema.json",
+    "id": "nebius",
+    "displayName": "Nebius Token Factory",
+    "aliases": [],
+    "tier": 2,
+    "wire": {
+        "baseURL": "https://api.tokenfactory.nebius.com/v1"
+    },
+    "models": {
+        "default": "Qwen/Qwen3-235B-A22B-Instruct-2507",
+        "fallbacks": [
+            "deepseek-ai/DeepSeek-V4-Flash-0731",
+            "openai/gpt-oss-120b",
+            "Qwen/Qwen3-30B-A3B-Instruct-2507",
+            "NousResearch/Hermes-4-405B"
+        ],
+        "defaultContextWindow": 32000,
+        "defaultMaxOutputTokens": 8192,
+        "catalog": {
+            "Qwen/Qwen3-235B-A22B-Instruct-2507": {
+                "contextWindow": 262144,
+                "pricingPerMTok": {
+                    "input": 0.2,
+                    "output": 0.6
+                },
+                "vision": false,
+                "status": "production",
+                "description": "NeuroLink default. Public model catalog (https://tokenfactory.nebius.com/api/public/models_info, retrieved 2026-09-29): name \"Qwen3-235B-A22B-Instruct-2507\"; type text2text; status active; description \"Balanced Qwen3 flagship tuned for strong general reasoning, chat quality, and tool use.\"; tags \"262K context\", \"code\", \"math\", \"JSON mode\"; use_cases text, code, function_calling, context_and_rag, fine_tune, responses_api; context_window_k 262; max_model_len 262144; input_price_per_million_tokens 0.2; output_price_per_million_tokens 0.6. vision false: catalog type text2text."
+            },
+            "deepseek-ai/DeepSeek-V4-Flash-0731": {
+                "contextWindow": 1024000,
+                "pricingPerMTok": {
+                    "input": 0.14,
+                    "output": 0.28
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Fallback. Public model catalog (https://tokenfactory.nebius.com/api/public/models_info, retrieved 2026-09-29): name \"DeepSeek-V4-Flash-0731\"; type text2text; status active; description \"DeepSeek V4 Flash 0731 is a 1M-context reasoning model designed for coding and agentic workloads.\"; tags \"1M context\", \"reasoning\", \"JSON mode\", \"code\", \"math\"; use_cases text, reasoning, function_calling, code, context_and_rag, responses_api, fine_tune; context_window_k 1024; max_model_len 1024000; input_price_per_million_tokens 0.14; output_price_per_million_tokens 0.28. vision false: catalog type text2text. The August 2026 deprecation notice (https://docs.tokenfactory.nebius.com/august-2026-deprecation-notice) lists this id in its \"Recommended Replacement\" column."
+            },
+            "openai/gpt-oss-120b": {
+                "contextWindow": 131072,
+                "pricingPerMTok": {
+                    "input": 0.15,
+                    "output": 0.6
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Fallback. Public model catalog (https://tokenfactory.nebius.com/api/public/models_info, retrieved 2026-09-29): name \"gpt-oss-120b\"; type text2text; status active; description \"Open-weight agentic model with configurable reasoning, full CoT visibility, strong tool use, and fine-tuning support.\"; tags \"131K context\", \"code\", \"JSON mode\", \"math\", \"reasoning\"; use_cases text, code, fine_tune, function_calling, reasoning; context_window_k 131; max_model_len 131072; input_price_per_million_tokens 0.15; output_price_per_million_tokens 0.6. vision false: catalog type text2text. The Structured output & JSON page (https://docs.tokenfactory.nebius.com/ai-models-inference/json) uses this id in its JavaScript example."
+            },
+            "Qwen/Qwen3-30B-A3B-Instruct-2507": {
+                "contextWindow": 262144,
+                "pricingPerMTok": {
+                    "input": 0.1,
+                    "output": 0.3
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Fallback. Public model catalog (https://tokenfactory.nebius.com/api/public/models_info, retrieved 2026-09-29): name \"Qwen3-30B-A3B-Instruct-2507\"; type text2text; status active; description \"Versatile 30B instruct model optimized for high-quality chat, reasoning, and coding.\"; tags \"262K context\", \"code\", \"math\", \"JSON mode\"; use_cases text, code, function_calling, context_and_rag, fine_tune, responses_api; context_window_k 262; max_model_len 262144; input_price_per_million_tokens 0.1; output_price_per_million_tokens 0.3. vision false: catalog type text2text."
+            },
+            "NousResearch/Hermes-4-405B": {
+                "contextWindow": 131072,
+                "pricingPerMTok": {
+                    "input": 1,
+                    "output": 3
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Fallback. Public model catalog (https://tokenfactory.nebius.com/api/public/models_info, retrieved 2026-09-29): name \"Hermes-4-405B\"; type text2text; status active; description \"Hybrid-reasoning model trained on verified CoT traces for strong math, coding, and step-by-step reliability.\"; tags \"128K context\", \"JSON mode\"; use_cases text, code, complex_writing, context_and_rag, function_calling, reasoning, summarization, responses_api; context_window_k 128; max_model_len 131072; input_price_per_million_tokens 1; output_price_per_million_tokens 3. vision false: catalog type text2text."
+            },
+            "nvidia/Nemotron-3_5-Lightning": {
+                "contextWindow": 1048576,
+                "pricingPerMTok": {
+                    "input": 0.06,
+                    "output": 0.24
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Public model catalog (https://tokenfactory.nebius.com/api/public/models_info, retrieved 2026-09-29): name \"Nemotron-3.5-Lightning\"; type text2text; status active; description \"NVIDIA's 30B-parameter hybrid MoE model with 3B active parameters per token, designed for efficient agentic reasoning, tool use, coding, and long-context workflows.\"; tags \"1M context\", \"reasoning\", \"code\", \"function calling\", \"MTP\"; use_cases text, reasoning, function_calling, code, context_and_rag, responses_api; context_window_k 1024; max_model_len 1048576; input_price_per_million_tokens 0.06; output_price_per_million_tokens 0.24. vision false: catalog type text2text. The August 2026 deprecation notice (https://docs.tokenfactory.nebius.com/august-2026-deprecation-notice) lists this id in its \"Recommended Replacement\" column."
+            },
+            "openbmb/MiniCPM-V-4_5": {
+                "contextWindow": 32000,
+                "pricingPerMTok": {
+                    "input": 0.658,
+                    "output": 1.11
+                },
+                "vision": true,
+                "status": "production",
+                "description": "Public model catalog (https://tokenfactory.nebius.com/api/public/models_info, retrieved 2026-09-29): name \"openbmb/MiniCPM-V-4_5\"; type image2text; status active; description \"MiniCPM-V-4.5 – Compact multimodal model for image, multi-image, high-FPS/long-video, OCR/PDF understanding, with switchable fast/deep thinking.\"; tags \"JSON mode\"; use_cases text, image, summarization, context_and_rag; context_window_k 32; max_model_len 32000; input_price_per_million_tokens 0.658; output_price_per_million_tokens 1.11. vision true: catalog type image2text with image in use_cases."
+            }
+        },
+        "topModels": [
+            "Qwen/Qwen3-235B-A22B-Instruct-2507",
+            "deepseek-ai/DeepSeek-V4-Flash-0731",
+            "openai/gpt-oss-120b",
+            "Qwen/Qwen3-30B-A3B-Instruct-2507",
+            "NousResearch/Hermes-4-405B",
+            "nvidia/Nemotron-3_5-Lightning",
+            "openbmb/MiniCPM-V-4_5"
+        ],
+        "visionModel": "openbmb/MiniCPM-V-4_5"
+    },
+    "capabilities": {
+        "text": true,
+        "streaming": true,
+        "tools": "model-dependent",
+        "toolsWithStreaming": true,
+        "structuredOutput": true,
+        "structuredOutputWithTools": false,
+        "embeddings": false,
+        "thinking": false
+    },
+    "errorRules": [
+        {
+            "status": 401,
+            "class": "authentication",
+            "message": "Nebius Token Factory returned HTTP 401. Check {apiKeyEnvVar}. Get one at {setupUrl}"
+        },
+        {
+            "status": 402,
+            "class": "provider",
+            "message": "Nebius Token Factory returned HTTP 402 (Payment Required): the account budget is exhausted. Billing details: https://docs.tokenfactory.nebius.com/other-capabilities/billing-new"
+        },
+        {
+            "status": 404,
+            "class": "invalid-model",
+            "message": "Nebius Token Factory returned HTTP 404: the model '{model}' does not exist. Model ids are listed at https://tokenfactory.nebius.com/model-catalog.md"
+        },
+        {
+            "status": 429,
+            "class": "rate-limit",
+            "message": "Nebius Token Factory returned HTTP 429 (rate limit exceeded). The Retry-After response header gives the time in seconds to wait before making another request (https://docs.tokenfactory.nebius.com/ai-models-inference/rate-limits)"
+        }
+    ],
+    "setup": {
+        "url": "https://tokenfactory.nebius.com/",
+        "apiKeyFormat": null,
+        "billingPolicy": "free-with-card",
+        "instructions": [
+            "1. Visit: https://tokenfactory.nebius.com/ and create an account; the quickstart (https://docs.tokenfactory.nebius.com/quickstart) says: \"Log in using your Google or GitHub account\"",
+            "2. Create an API key (https://docs.tokenfactory.nebius.com/api-reference/introduction#authentication): go to the API keys section, click Create API key, enter the key name, click Create, and save the displayed key — \"Save the displayed API key. You cannot open it later in Nebius Token Factory.\"",
+            "3. Billing (https://docs.tokenfactory.nebius.com/other-capabilities/billing-new): \"Billing setup is mandatory—you cannot complete onboarding without it.\" \"Setting up a billing account requires a bank card.\" \"Upon first sign-up, you receive $1 in trial credit, valid for 30 days.\"",
+            "4. Set {apiKeyEnvVar} in your .env file (the vendor's docs read NEBIUS_API_KEY)"
+        ],
+        "description": "OpenAI-compatible endpoint at https://api.tokenfactory.nebius.com/v1 (https://docs.tokenfactory.nebius.com/api-reference/introduction: \"Nebius Token Factory offers an OpenAI-compatible API for inference and fine-tuning.\"). Docs-verified, not live-verified: an unauthenticated GET of https://api.tokenfactory.nebius.com/v1/models answers HTTP 401 without a key, so the model ids come from the vendor's public model catalog (https://tokenfactory.nebius.com/api/public/models_info, retrieved 2026-09-29) and the roster has not been checked against the API. errorRules follow the statuses and example bodies in https://docs.tokenfactory.nebius.com/api-reference/inference/create-chat-completion (401, 402, 404, 429). models.defaultMaxOutputTokens (8192) is the value that reference gives for an omitted max_tokens (\"If omitted or set to null, defaults to 8192 tokens.\"); models.defaultContextWindow (32000) is a placeholder the vendor does not publish."
+    },
+    "evidence": {
+        "rosterVerified": {
+            "date": "2026-09-29",
+            "status": 401,
+            "method": "docs-only — unauthenticated GET https://api.tokenfactory.nebius.com/v1/models answers 401 without a key, so model ids are taken from https://tokenfactory.nebius.com/api/public/models_info (retrieved 2026-09-29); roster not verified"
+        },
+        "authProbe": {
+            "date": "2026-09-29",
+            "status": 401,
+            "method": "unauthenticated GET https://api.tokenfactory.nebius.com/v1/models — body {\"detail\":\"Couldn't authenticate. Reason: token is not present\"}; credential-free, no key used"
+        },
+        "billingProbe": {
+            "date": "2026-09-29",
+            "method": "public page https://docs.tokenfactory.nebius.com/other-capabilities/billing-new — \"Setting up a billing account requires a bank card.\" and \"Upon first sign-up, you receive $1 in trial credit, valid for 30 days.\"; credential-free"
+        },
+        "liveMatrix": null,
+        "addedInPR": "https://github.com/juspay/neurolink/pull/1860"
+    }
+}

package/dist/providers/catalog/prime-intellect.json

@@ -0,0 +1,217 @@
+{
+    "$schema": "./provider-catalog.schema.json",
+    "id": "prime-intellect",
+    "displayName": "Prime Intellect",
+    "aliases": [],
+    "tier": 2,
+    "wire": {
+        "baseURL": "https://api.pinference.ai/api/v1",
+        "apiKeyFallbackEnvVars": ["PRIME_API_KEY"]
+    },
+    "models": {
+        "default": "openai/gpt-4.1-mini",
+        "fallbacks": [
+            "openai/gpt-4.1",
+            "anthropic/claude-sonnet-4.5",
+            "meta-llama/llama-3.3-70b-instruct"
+        ],
+        "defaultContextWindow": 131072,
+        "defaultMaxOutputTokens": 16384,
+        "catalog": {
+            "openai/gpt-4.1-mini": {
+                "contextWindow": 1047576,
+                "maxOutputTokens": 32768,
+                "pricingPerMTok": {
+                    "input": 0.4,
+                    "output": 1.6
+                },
+                "vision": true,
+                "status": "production",
+                "description": "Recommended default. Prime Intellect's own Evaluating Environments guide (docs.primeintellect.ai/tutorials-environments/evaluating) lists this model as \"Fast, cost-effective (default)\" and uses it as the default model of its inference-backed evaluation command. No Prime-trained model appears on this roster (119 of 125 entries are gateway-routed and the other 6 are third-party models served on Prime infrastructure), so this is the model its docs designate as the default, not a Prime-trained flagship. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 1,047,576, max_output_tokens 32,768, $0.4/$1.6 per MTok input/output; input modalities image/text/file; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. vision: true follows the roster's image input modality (no image request was sent)."
+            },
+            "openai/gpt-4.1": {
+                "contextWindow": 1047576,
+                "maxOutputTokens": 32768,
+                "pricingPerMTok": {
+                    "input": 2,
+                    "output": 8
+                },
+                "vision": true,
+                "status": "production",
+                "description": "Listed in the Evaluating Environments guide (docs.primeintellect.ai/tutorials-environments/evaluating) as \"Higher quality\" than the default. Fallback. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 1,047,576, max_output_tokens 32,768, $2/$8 per MTok input/output; input modalities image/text/file; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. vision: true follows the roster's image input modality (no image request was sent)."
+            },
+            "anthropic/claude-sonnet-4.5": {
+                "contextWindow": 1000000,
+                "maxOutputTokens": 64000,
+                "pricingPerMTok": {
+                    "input": 3,
+                    "output": 15
+                },
+                "vision": true,
+                "status": "production",
+                "description": "Listed in the Evaluating Environments guide (docs.primeintellect.ai/tutorials-environments/evaluating) as \"Strong reasoning\". Fallback. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 1,000,000, max_output_tokens 64,000, $3/$15 per MTok input/output; input modalities text/image/file; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. vision: true follows the roster's image input modality (no image request was sent)."
+            },
+            "meta-llama/llama-3.3-70b-instruct": {
+                "contextWindow": 131072,
+                "maxOutputTokens": 16384,
+                "pricingPerMTok": {
+                    "input": 1.04,
+                    "output": 2.253
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Listed in the Evaluating Environments guide (docs.primeintellect.ai/tutorials-environments/evaluating) as \"Open-weight, balanced\". Fallback. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 131,072, max_output_tokens 16,384, $1.04/$2.253 per MTok input/output; input modalities text; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. No image input modality on the roster, so vision is false."
+            },
+            "google/gemini-2.5-flash": {
+                "contextWindow": 1048576,
+                "maxOutputTokens": 65535,
+                "pricingPerMTok": {
+                    "input": 0.3,
+                    "output": 2.5
+                },
+                "vision": true,
+                "status": "production",
+                "description": "Listed in the Evaluating Environments guide (docs.primeintellect.ai/tutorials-environments/evaluating) as \"Fast multimodal\". Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 1,048,576, max_output_tokens 65,535, $0.3/$2.5 per MTok input/output; input modalities file/image/text/audio/video; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. vision: true follows the roster's image input modality (no image request was sent)."
+            },
+            "Qwen/Qwen3-235B-A22B-Instruct-2507": {
+                "contextWindow": 262144,
+                "maxOutputTokens": 235929,
+                "pricingPerMTok": {
+                    "input": 0.25,
+                    "output": 1
+                },
+                "vision": false,
+                "status": "production",
+                "description": "The Evaluating Environments guide (docs.primeintellect.ai/tutorials-environments/evaluating) lists a lowercase id, qwen/qwen3-235b-a22b-instruct-2507, as \"Large MoE model\"; that lowercase id is not on today's roster, so the id here is copied character for character from the roster's differently cased entry. The roster's max_output_tokens figure is reported as served. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 262,144, max_output_tokens 235,929, $0.25/$1 per MTok input/output; input modalities text; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. No image input modality on the roster, so vision is false."
+            },
+            "z-ai/glm-5.3": {
+                "contextWindow": 1048576,
+                "maxOutputTokens": 131072,
+                "pricingPerMTok": {
+                    "input": 1.4,
+                    "output": 4.4,
+                    "cachedInput": 0.26
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Serving \"hosted\" on today's roster — the vendor's OpenAPI spec (https://api.pinference.ai/openapi.json) defines that value as models served on Prime infrastructure. Roster display_name \"GLM 5.3\"; reasoning is marked mandatory with default effort \"max\". Its supported_parameters list tools and tool_choice but not response_format or structured_outputs. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 1,048,576, max_output_tokens 131,072, $1.4/$4.4 per MTok input/output ($0.26 cached-input read); input modalities text; supported_parameters include tools, tool_choice; serving hosted. No image input modality on the roster, so vision is false."
+            },
+            "openai/gpt-5.4-mini": {
+                "contextWindow": 400000,
+                "maxOutputTokens": 128000,
+                "pricingPerMTok": {
+                    "input": 0.75,
+                    "output": 4.5
+                },
+                "vision": true,
+                "status": "production",
+                "description": "Named in the Troubleshooting page's direct-API examples (docs.primeintellect.ai/inference/troubleshooting). Roster reasoning efforts: xhigh/high/medium/low/none, not mandatory. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 400,000, max_output_tokens 128,000, $0.75/$4.5 per MTok input/output; input modalities file/image/text; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. vision: true follows the roster's image input modality (no image request was sent)."
+            },
+            "openai/gpt-oss-120b": {
+                "contextWindow": 131072,
+                "maxOutputTokens": 65536,
+                "pricingPerMTok": {
+                    "input": 0.35,
+                    "output": 0.75
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Roster-listed only. Reasoning is marked mandatory (default effort \"medium\"). Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 131,072, max_output_tokens 65,536, $0.35/$0.75 per MTok input/output; input modalities text; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. No image input modality on the roster, so vision is false."
+            },
+            "deepseek/deepseek-v4-flash": {
+                "contextWindow": 1048576,
+                "maxOutputTokens": 131072,
+                "pricingPerMTok": {
+                    "input": 0.44,
+                    "output": 1.32
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Roster-listed only. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 1,048,576, max_output_tokens 131,072, $0.44/$1.32 per MTok input/output; input modalities text; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. No image input modality on the roster, so vision is false."
+            },
+            "anthropic/claude-haiku-4.5": {
+                "contextWindow": 200000,
+                "maxOutputTokens": 64000,
+                "pricingPerMTok": {
+                    "input": 1,
+                    "output": 5
+                },
+                "vision": true,
+                "status": "production",
+                "description": "Roster-listed only. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 200,000, max_output_tokens 64,000, $1/$5 per MTok input/output; input modalities text/image/file; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. vision: true follows the roster's image input modality (no image request was sent)."
+            },
+            "Qwen/Qwen3.5-122B-A10B": {
+                "pricingPerMTok": {
+                    "input": 0.3,
+                    "output": 0.9,
+                    "cachedInput": 0.27
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Serving \"hosted\" (Prime infrastructure) on today's roster. The roster gives it no context_window, max_output_tokens, modalities or supported_parameters, so none are declared here; vision false is the schema's required default, not a vendor statement about image input. Roster-listed only. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): $0.3/$0.9 per MTok input/output ($0.27 cached-input read); serving hosted."
+            }
+        },
+        "topModels": [
+            "openai/gpt-4.1-mini",
+            "openai/gpt-4.1",
+            "anthropic/claude-sonnet-4.5",
+            "meta-llama/llama-3.3-70b-instruct",
+            "google/gemini-2.5-flash",
+            "Qwen/Qwen3-235B-A22B-Instruct-2507",
+            "z-ai/glm-5.3",
+            "openai/gpt-5.4-mini",
+            "openai/gpt-oss-120b",
+            "deepseek/deepseek-v4-flash",
+            "anthropic/claude-haiku-4.5",
+            "Qwen/Qwen3.5-122B-A10B"
+        ]
+    },
+    "capabilities": {
+        "text": true,
+        "streaming": true,
+        "tools": "model-dependent",
+        "toolsWithStreaming": false,
+        "structuredOutput": true,
+        "structuredOutputWithTools": false,
+        "embeddings": false,
+        "thinking": false
+    },
+    "errorRules": [
+        {
+            "status": 401,
+            "pattern": "Authorization header or x-api-key missing|invalid_api_key|Invalid API key",
+            "class": "authentication",
+            "message": "Invalid or missing Prime Intellect API key. Check {apiKeyEnvVar}. Create a key with the Inference permission enabled at {setupUrl}"
+        }
+    ],
+    "setup": {
+        "url": "https://app.primeintellect.ai/dashboard/tokens",
+        "apiKeyFormat": null,
+        "billingPolicy": "no-free-tier",
+        "instructions": [
+            "1. Visit: https://app.primeintellect.ai/dashboard/tokens (Settings -> API Keys) and sign in",
+            "2. Click 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)",
+            "3. Billing 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",
+            "4. Set {apiKeyEnvVar} in your .env file (PRIME_API_KEY, the variable Prime's own docs use, is also read)"
+        ],
+        "description": "OpenAI-compatible endpoint at https://api.pinference.ai/api/v1 (docs.primeintellect.ai/inference/overview), a gateway that routes to upstream model providers plus a few models served on Prime infrastructure. The inference host (pinference.ai) differs from the docs and dashboard host (primeintellect.ai); both are confirmed on the vendor's own pages. The catalog schema has no 'unknown' billing value, so no-free-tier here means no free tier is documented, not that the vendor confirmed there is none."
+    },
+    "evidence": {
+        "rosterVerified": {
+            "date": "2026-09-29",
+            "method": "unauthenticated GET https://api.pinference.ai/api/v1/models — 125 models; credential-free, no key used",
+            "status": 200
+        },
+        "authProbe": {
+            "date": "2026-09-29",
+            "method": "unauthenticated GET https://api.pinference.ai/api/v1/models/openai/gpt-4.1-mini with no credentials — 401 {\"detail\":\"Authorization header or x-api-key missing\", ...}; only the missing-credential shape was observed, the invalid-key shape (error.code invalid_api_key) is from docs.primeintellect.ai/api-reference/inference-models and was not probed; credential-free, no key used",
+            "status": 401
+        },
+        "billingProbe": {
+            "date": "2026-09-29",
+            "method": "public page https://docs.primeintellect.ai/inference/overview — \"Automatic deduction from your Prime Intellect account balance\"; https://docs.primeintellect.ai/inference/troubleshooting documents an insufficient_funds error; no free tier stated; credential-free"
+        },
+        "liveMatrix": null,
+        "addedInPR": "https://github.com/juspay/neurolink/pull/1860"
+    }
+}

package/dist/providers/catalog/scaleway.json

@@ -0,0 +1,177 @@
+{
+    "$schema": "./provider-catalog.schema.json",
+    "id": "scaleway",
+    "displayName": "Scaleway",
+    "aliases": [],
+    "tier": 2,
+    "wire": {
+        "baseURL": "https://api.scaleway.ai/v1"
+    },
+    "models": {
+        "default": "mistral-small-3.2-24b-instruct-2506",
+        "fallbacks": [
+            "llama-3.3-70b-instruct",
+            "qwen3-235b-a22b-instruct-2507",
+            "gemma-4-26b-a4b-it",
+            "qwen3.6-35b-a3b"
+        ],
+        "defaultContextWindow": 100000,
+        "defaultMaxOutputTokens": 16000,
+        "catalog": {
+            "mistral-small-3.2-24b-instruct-2506": {
+                "contextWindow": 128000,
+                "maxOutputTokens": 32000,
+                "vision": true,
+                "status": "production",
+                "description": "NeuroLink default. The id appears in the Model field description of the Chat Completions API reference (https://www.scaleway.com/en/developers/api/generative-apis/chat-completions/: \"Unique identifier of the model, such as llama-3.3-70b-instruct or mistral-small-3.2-24b-instruct-2506.\") and in the /chat/completions curl example on the rate-limits page (https://www.scaleway.com/en/docs/generative-apis/reference-content/rate-limits/). From the supported-models page (https://www.scaleway.com/en/docs/generative-apis/reference-content/supported-models/, retrieved 2026-09-29) and pricing page (https://www.scaleway.com/en/pricing/model-as-a-service/, retrieved 2026-09-29, region Paris): Available in Serverless is Yes, modalities are Text and Vision, maximum context window is 128k, maximum output (Serverless) is 32k; the attribute rows for structured output, function calling and parallel tool-calling are Yes; supported image formats are PNG, JPEG, WEBP, and non-animated GIFs. The pricing page lists it as Chat and Vision at 0.15 EUR per million input tokens and 0.35 EUR per million output tokens; pricingPerMTok is left out because the pricing page states euro prices and the schema has no currency field. Vision is true because the modalities entry lists Vision (not probed with an image request)."
+            },
+            "llama-3.3-70b-instruct": {
+                "contextWindow": 100000,
+                "maxOutputTokens": 16000,
+                "vision": false,
+                "status": "production",
+                "description": "Fallback. The id appears in the Model field description and the example request of the Chat Completions API reference (https://www.scaleway.com/en/developers/api/generative-apis/chat-completions/). From the supported-models page (https://www.scaleway.com/en/docs/generative-apis/reference-content/supported-models/, retrieved 2026-09-29) and pricing page (https://www.scaleway.com/en/pricing/model-as-a-service/, retrieved 2026-09-29, region Paris): Available in Serverless is Yes, modality is Text, context window is 100k (Serverless), maximum output (Serverless) is 16k; the attribute rows for structured output, function calling and parallel tool-calling are Yes. Vendor text: \"Released in December 2024, Llama 3.3 70b by Meta is a fine-tune of the Llama 3.1 70b model.\" and \"This model is text-only (text in/text out).\" The pricing page lists it as Chat at 0.90 EUR per million input tokens and 0.90 EUR per million output tokens. Vision is false because the modalities entry does not list Vision."
+            },
+            "qwen3-235b-a22b-instruct-2507": {
+                "contextWindow": 250000,
+                "maxOutputTokens": 16000,
+                "vision": false,
+                "status": "production",
+                "description": "Fallback. From the supported-models page (https://www.scaleway.com/en/docs/generative-apis/reference-content/supported-models/, retrieved 2026-09-29) and pricing page (https://www.scaleway.com/en/pricing/model-as-a-service/, retrieved 2026-09-29, region Paris): Available in Serverless is Yes, modality is Text, maximum context window is 250k, maximum output (Serverless) is 16k; the attribute rows for structured output, function calling and parallel tool-calling are Yes. Vendor text: \"Released in July 2025, Qwen 3 235B A22B is an open-weight model\". The pricing page lists it as Chat at 0.75 EUR per million input tokens and 2.25 EUR per million output tokens. Vision is false because the modalities entry does not list Vision."
+            },
+            "gemma-4-26b-a4b-it": {
+                "contextWindow": 256000,
+                "maxOutputTokens": 32000,
+                "vision": true,
+                "status": "production",
+                "description": "Fallback. From the supported-models page (https://www.scaleway.com/en/docs/generative-apis/reference-content/supported-models/, retrieved 2026-09-29) and pricing page (https://www.scaleway.com/en/pricing/model-as-a-service/, retrieved 2026-09-29, region Paris): Available in Serverless is Yes, modalities are Text and Vision, maximum context window is 256k, maximum output (Serverless) is 32k; the attribute rows for structured output, function calling and parallel tool-calling are Yes; supported reasoning efforts are none, low, medium, high; supported image formats are PNG, JPEG, WEBP, and non-animated GIFs. Vendor text: \"Released in April 2026, Gemma-4-26b-a4b-it is a frontier small-sized model to perform agentic and reasoning tasks on many languages.\" The pricing page lists it as Chat, code, and Vision at 0.25 EUR per million input tokens and 0.50 EUR per million output tokens. Vision is true because the modalities entry lists Vision (not probed with an image request)."
+            },
+            "qwen3.6-35b-a3b": {
+                "contextWindow": 256000,
+                "maxOutputTokens": 32000,
+                "vision": true,
+                "status": "production",
+                "description": "From the supported-models page (https://www.scaleway.com/en/docs/generative-apis/reference-content/supported-models/, retrieved 2026-09-29) and pricing page (https://www.scaleway.com/en/pricing/model-as-a-service/, retrieved 2026-09-29, region Paris): Available in Serverless is Yes, modalities are Text, Code and Vision, maximum context window is 256k, maximum output (Serverless) is 32k; the attribute rows for structured output, function calling and parallel tool-calling are Yes; supported reasoning efforts are none, low, medium, high; supported image formats are PNG, JPEG, GIF. Vendor text: \"Released in April 2026, Qwen3.6-35b-a3b is a state-of-the-art small-sized model optimized for agentic tasks and logical reasoning.\" The pricing page lists it as Chat, code, and Vision at 0.25 EUR per million input tokens and 1.50 EUR per million output tokens. Vision is true because the modalities entry lists Vision (not probed with an image request)."
+            },
+            "qwen3.8-27b": {
+                "contextWindow": 256000,
+                "maxOutputTokens": 32000,
+                "vision": true,
+                "status": "production",
+                "description": "From the supported-models page (https://www.scaleway.com/en/docs/generative-apis/reference-content/supported-models/, retrieved 2026-09-29) and pricing page (https://www.scaleway.com/en/pricing/model-as-a-service/, retrieved 2026-09-29, region Paris): Available in Serverless is Yes, modalities are Text, Code and Vision, maximum context window is 256k, maximum output (Serverless) is 32k; the attribute rows for structured output, function calling and parallel tool-calling are Yes; supported reasoning efforts are none, low, medium, xhigh; supported image formats are PNG, JPEG, GIF. Vendor text: \"A state-of-the-art small-sized dense model as of August 2026, optimized for agentic tasks and logical reasoning.\" The pricing page lists it as Chat, code, and Vision at 0.60 EUR per million input tokens (0.12 EUR per million cached) and 3.30 EUR per million output tokens. Vision is true because the modalities entry lists Vision (not probed with an image request)."
+            },
+            "qwen3.5-397b-a17b": {
+                "contextWindow": 250000,
+                "maxOutputTokens": 16000,
+                "vision": true,
+                "status": "production",
+                "description": "From the supported-models page (https://www.scaleway.com/en/docs/generative-apis/reference-content/supported-models/, retrieved 2026-09-29) and pricing page (https://www.scaleway.com/en/pricing/model-as-a-service/, retrieved 2026-09-29, region Paris): Available in Serverless is Yes, modalities are Text, Code and Vision, maximum context window is 250k, maximum output (Serverless) is 16k; the attribute rows for structured output, function calling and parallel tool-calling are Yes; supported reasoning efforts are none, low, medium, high; supported image formats are PNG, JPEG, WEBP, and non-animated GIFs. Vendor text: \"Qwen3.5-397b-a17b is a model developed by Qwen to perform text processing, agentic coding, image, and video analysis in several languages.\" The pricing page lists it as Chat, code, and Vision at 0.60 EUR per million input tokens and 3.60 EUR per million output tokens. Vision is true because the modalities entry lists Vision (not probed with an image request)."
+            },
+            "deepseek-v4-flash-0731": {
+                "contextWindow": 256000,
+                "maxOutputTokens": 32000,
+                "vision": false,
+                "status": "preview",
+                "description": "From the supported-models page (https://www.scaleway.com/en/docs/generative-apis/reference-content/supported-models/, retrieved 2026-09-29) and pricing page (https://www.scaleway.com/en/pricing/model-as-a-service/, retrieved 2026-09-29, region Paris): Available in Serverless is Yes, modalities are Text and Code, maximum context window is 256k, maximum output (Serverless) is 32k; the attribute rows for structured output, function calling and parallel tool-calling are Yes; supported reasoning efforts are none, low, high, max. The context footnote on that page reads: \"GLM 5.2 and DeepSeek-V4-Flash support 1 million context. During the preview stage, the context is limited to 256k to ensure consistent token generation speed.\" Vendor text: \"Released in July 2026, DeepSeek-V4-Flash is the best cost-efficient model for long-horizon and coding tasks at the time of release.\" The pricing page lists it as Chat and code at 0.40 EUR per million input tokens (0.08 EUR per million cached) and 0.80 EUR per million output tokens. Vision is false because the modalities entry does not list Vision."
+            },
+            "glm-5.2": {
+                "contextWindow": 256000,
+                "maxOutputTokens": 16000,
+                "vision": false,
+                "status": "preview",
+                "description": "From the supported-models page (https://www.scaleway.com/en/docs/generative-apis/reference-content/supported-models/, retrieved 2026-09-29) and pricing page (https://www.scaleway.com/en/pricing/model-as-a-service/, retrieved 2026-09-29, region Paris): Available in Serverless is Yes, modalities are Text and Code, maximum context window is 256k, maximum output (Serverless) is 16k; the attribute rows for structured output, function calling and parallel tool-calling are Yes; supported reasoning efforts are none, high, max. The context footnote on that page reads: \"GLM 5.2 and DeepSeek-V4-Flash support 1 million context. During the preview stage, the context is limited to 256k to ensure consistent token generation speed.\" Vendor text: \"Released in June 2026, GLM 5.2 is the best open-weight model for long-horizon and coding tasks at the time of release.\" The pricing page lists it as Chat and code at 1.80 EUR per million input tokens and 5.50 EUR per million output tokens. Vision is false because the modalities entry does not list Vision."
+            },
+            "mistral-medium-3.5-128b": {
+                "contextWindow": 180000,
+                "maxOutputTokens": 16000,
+                "vision": true,
+                "status": "preview",
+                "description": "From the supported-models page (https://www.scaleway.com/en/docs/generative-apis/reference-content/supported-models/, retrieved 2026-09-29) and pricing page (https://www.scaleway.com/en/pricing/model-as-a-service/, retrieved 2026-09-29, region Paris): Available in Serverless is Yes, modalities are Text and Vision, maximum context window is 180k, maximum output (Serverless) is 16k; the attribute rows for structured output, function calling and parallel tool-calling are Yes; supported reasoning efforts are none, high; supported image formats are PNG, JPEG, WEBP, GIF. The context footnote on that page reads: \"Mistral Medium 3.5 supports 1 million context. During the preview stage, the context is limited to 180k to ensure consistent token generation speed.\" Vendor text: \"Mistral-medium-3.5 is a unified model from Mistral with strong performance for instruct, reasoning, and coding tasks.\" The pricing page lists it as Chat, code, and Vision at 1.50 EUR per million input tokens and 7.50 EUR per million output tokens. Vision is true because the modalities entry lists Vision (not probed with an image request)."
+            },
+            "gpt-oss-120b": {
+                "contextWindow": 128000,
+                "maxOutputTokens": 32000,
+                "vision": false,
+                "status": "production",
+                "description": "From the supported-models page (https://www.scaleway.com/en/docs/generative-apis/reference-content/supported-models/, retrieved 2026-09-29) and pricing page (https://www.scaleway.com/en/pricing/model-as-a-service/, retrieved 2026-09-29, region Paris): Available in Serverless is Yes, modality is Text, maximum context window is 128k, maximum output (Serverless) is 32k; the attribute rows for structured output, function calling and parallel tool-calling are Yes; supported reasoning efforts are low, medium, high. Vendor text: \"Released in August 2025, GPT OSS 120B is an open-weight model providing significant throughput performance and reasoning capabilities.\" and \"Currently, this model should be used through the Responses API, because the Chat Completions API does not yet support tool-calling for this model.\" The pricing page lists it as Chat at 0.15 EUR per million input tokens and 0.60 EUR per million output tokens. Vision is false because the modalities entry does not list Vision."
+            }
+        },
+        "topModels": [
+            "mistral-small-3.2-24b-instruct-2506",
+            "llama-3.3-70b-instruct",
+            "qwen3-235b-a22b-instruct-2507",
+            "gemma-4-26b-a4b-it",
+            "qwen3.6-35b-a3b",
+            "qwen3.8-27b",
+            "qwen3.5-397b-a17b",
+            "deepseek-v4-flash-0731",
+            "glm-5.2",
+            "mistral-medium-3.5-128b",
+            "gpt-oss-120b"
+        ],
+        "visionModel": "mistral-small-3.2-24b-instruct-2506"
+    },
+    "capabilities": {
+        "text": true,
+        "streaming": true,
+        "tools": "model-dependent",
+        "toolsWithStreaming": true,
+        "structuredOutput": true,
+        "structuredOutputWithTools": false,
+        "embeddings": false,
+        "thinking": false
+    },
+    "errorRules": [
+        {
+            "status": 401,
+            "class": "authentication",
+            "message": "Scaleway rejected the request with HTTP 401 (the Understanding common errors page lists 401 as \"Unauthorized: The authorization header is missing.\"). Check {apiKeyEnvVar}. Create a key: {setupUrl}"
+        },
+        {
+            "status": 403,
+            "class": "authentication",
+            "message": "Scaleway returned HTTP 403 (the Understanding common errors page lists 403 as \"Forbidden: Your API key does not exist or does not have the necessary permissions to access the requested resource.\"). The Using Generative APIs page lists the permission sets GenerativeApisModelAccess, GenerativeApisFullAccess and AllProductsFullAccess for querying models. Check {apiKeyEnvVar}."
+        },
+        {
+            "status": 422,
+            "class": "invalid-model",
+            "message": "Scaleway returned HTTP 422 for model '{model}' (the Understanding common errors page lists 422 as \"Model Not Found: The model key is present in the request payload, but the corresponding model is not found.\" and \"Missing Model: The model key is missing from the request payload.\"). Supported models: https://www.scaleway.com/en/docs/generative-apis/reference-content/supported-models/"
+        },
+        {
+            "status": 429,
+            "class": "rate-limit",
+            "message": "Scaleway returned HTTP 429 (the Understanding common errors page lists 429 as \"Too Many Requests: You are exceeding your current quota for the requested model, calculated in requests per minute.\" and \"Too Many Tokens: You are exceeding your current quota for the requested model, calculated in tokens per minute.\"). Rate limits: https://www.scaleway.com/en/docs/generative-apis/reference-content/rate-limits/"
+        }
+    ],
+    "setup": {
+        "url": "https://account.scaleway.com/register?service=console",
+        "apiKeyFormat": null,
+        "billingPolicy": "free-with-card",
+        "instructions": [
+            "1. Visit: https://account.scaleway.com/register?service=console and create a Scaleway account; the quickstart (https://www.scaleway.com/en/docs/generative-apis/quickstart/) lists \"A Scaleway account logged into the console\" and \"A valid API key\" as requirements",
+            "2. Create an API key (https://www.scaleway.com/en/docs/iam/credentials/create-api-keys/): click IAM & API keys on the top-right drop-down menu of the Scaleway console, open the API keys tab and click + Generate API key. The page says: \"A screen displays showing the access key and secret key for your new API key and reminding you that this is your only chance to securely save the secret key.\" The quickstart passes the secret key as the OpenAI client's api_key. Querying models requires one of the permission sets GenerativeApisModelAccess, GenerativeApisFullAccess or AllProductsFullAccess (https://www.scaleway.com/en/docs/generative-apis/api-cli/using-generative-apis/)",
+            "3. Billing as the vendor states it: the pricing page (https://www.scaleway.com/en/pricing/model-as-a-service/) says \"Try out new models with our free tier: 1 million tokens and 60 minutes of audio transcription.\"; the FAQ (https://www.scaleway.com/en/docs/generative-apis/faq/) says \"After reaching this limit, you will be charged per million tokens processed and per minutes of audio processed.\"; the create-account page (https://www.scaleway.com/en/docs/account/how-to/create-an-account/) says \"Ordering Scaleway resources requires a valid credit card.\"; the payment-method page (https://www.scaleway.com/en/docs/billing/how-to/add-payment-method/) says \"Before you can order Scaleway resources, you must add a payment method to your account.\"; the rate-limits page (https://www.scaleway.com/en/docs/generative-apis/reference-content/rate-limits/) says \"Base limits apply if you registered a valid payment method, and they are increased automatically if you also verify your identity.\"",
+            "4. Set {apiKeyEnvVar} in your .env file (the vendor's examples read SCW_SECRET_KEY, which NeuroLink does not)"
+        ],
+        "description": "Docs-verified only: the vendor's GET https://api.scaleway.ai/v1/models needs a key (it answers HTTP 401 without one), so the eleven model ids come from the supported-models page https://www.scaleway.com/en/docs/generative-apis/reference-content/supported-models/ (names checked against the pricing page https://www.scaleway.com/en/pricing/model-as-a-service/) and the roster has not been checked; the entry is not yet live-verified. OpenAI-compatible endpoint at https://api.scaleway.ai/v1: the compatibility page (https://www.scaleway.com/en/docs/generative-apis/reference-content/openai-compatibility/) says \"You can use any of the OpenAI official libraries, for example, the OpenAI Python client library to interact with Generative APIs.\", the quickstart (https://www.scaleway.com/en/docs/generative-apis/quickstart/) sets base_url to https://api.scaleway.ai/v1, and the Chat Completions reference (https://www.scaleway.com/en/developers/api/generative-apis/chat-completions/) documents POST /{project_id}/v1/chat/completions with a required model and messages. Unauthenticated GETs made 2026-09-29: /models and /chat/completions both answered HTTP 401 with the body {\"status\":401,\"error\":\"UNAUTHORIZED\",\"message\":\"missing 'Authorization' header\"}; errorRules carry that 401 and the 403, 422 and 429 statuses listed on the Understanding common errors page (https://www.scaleway.com/en/docs/generative-apis/api-cli/understanding-errors/). models.defaultContextWindow (100000) and models.defaultMaxOutputTokens (16000) are placeholders for model ids outside the catalog that the vendor does not publish; they equal the smallest Serverless context and maximum-output figures among the catalog models. Per-model contextWindow and maxOutputTokens values are the decimal forms of the labels the vendor prints (256k, 250k, 180k, 128k, 100k; 32k, 16k). The pricing page states euro prices, so pricingPerMTok is omitted rather than converted and the prices appear in the model descriptions. billingPolicy holds the schema value free-with-card: the pricing page and FAQ describe a Free Tier, and the create-account, payment-method and rate-limits pages carry the payment-method sentences quoted in setup.instructions step 3; the value is NeuroLink's classification, not a Scaleway statement. The status value production is a value the schema requires and is not a Scaleway statement; preview marks the three models whose context the supported-models page ties to the preview stage. No POST request was sent, so the request fields NeuroLink's chat-completions client can add (stream_options on streaming calls, tool_choice on calls with tools, and a json_schema response_format for schema output) have not been exercised against Scaleway."
+    },
+    "evidence": {
+        "rosterVerified": {
+            "date": "2026-09-29",
+            "status": 401,
+            "method": "docs-only — unauthenticated GET https://api.scaleway.ai/v1/models answers 401 without a key, so model ids are taken from https://www.scaleway.com/en/docs/generative-apis/reference-content/supported-models/ (retrieved 2026-09-29); roster not verified"
+        },
+        "authProbe": {
+            "date": "2026-09-29",
+            "status": 401,
+            "code": "UNAUTHORIZED",
+            "method": "unauthenticated GET https://api.scaleway.ai/v1/models and GET https://api.scaleway.ai/v1/chat/completions, no Authorization header — both HTTP 401, JSON body {\"status\":401,\"error\":\"UNAUTHORIZED\",\"message\":\"missing 'Authorization' header\"}; the code recorded here is the body's error value; credential-free, no key used"
+        },
+        "billingProbe": {
+            "date": "2026-09-29",
+            "method": "public pages https://www.scaleway.com/en/pricing/model-as-a-service/ (\"Try out new models with our free tier: 1 million tokens and 60 minutes of audio transcription.\"), https://www.scaleway.com/en/docs/generative-apis/faq/ (\"There is a Free Tier available for Serverless.\"), https://www.scaleway.com/en/docs/account/how-to/create-an-account/ (\"Ordering Scaleway resources requires a valid credit card.\"), https://www.scaleway.com/en/docs/billing/how-to/add-payment-method/ (\"Before you can order Scaleway resources, you must add a payment method to your account.\") and https://www.scaleway.com/en/docs/generative-apis/reference-content/rate-limits/ (\"Base limits apply if you registered a valid payment method, and they are increased automatically if you also verify your identity.\"); credential-free, no signup performed"
+        },
+        "liveMatrix": null,
+        "addedInPR": "https://github.com/juspay/neurolink/pull/1860"
+    }
+}