@juspay/neurolink 12.39.0 → 12.40.0

package/dist/providers/catalog/siliconflow.json

@@ -0,0 +1,242 @@
+{
+    "$schema": "./provider-catalog.schema.json",
+    "id": "siliconflow",
+    "displayName": "SiliconFlow",
+    "aliases": [],
+    "tier": 2,
+    "wire": {
+        "baseURL": "https://api.siliconflow.com/v1"
+    },
+    "models": {
+        "default": "deepseek-ai/DeepSeek-V4-Pro",
+        "fallbacks": [
+            "deepseek-ai/DeepSeek-V4-Flash",
+            "deepseek-ai/DeepSeek-V3.2",
+            "zai-org/GLM-5.1",
+            "moonshotai/Kimi-K2.6",
+            "Qwen/Qwen3-32B"
+        ],
+        "defaultContextWindow": 32768,
+        "defaultMaxOutputTokens": 4096,
+        "catalog": {
+            "deepseek-ai/DeepSeek-V4-Pro": {
+                "contextWindow": 1049000,
+                "maxOutputTokens": 393000,
+                "pricingPerMTok": {
+                    "input": 1.50162,
+                    "output": 3.135,
+                    "cachedInput": 0.135
+                },
+                "vision": false,
+                "status": "production",
+                "description": "NeuroLink default. The model page About text begins \"DeepSeek-V4-Pro is DeepSeek's flagship open-source MoE model\". Listed in the model enum of the chat-completions API reference (https://docs.siliconflow.com/en/api-reference/chat-completions/chat-completions, retrieved 2026-09-29). The model page https://www.siliconflow.com/models/deepseek-v4-pro (retrieved 2026-09-29) shows the id deepseek-ai/DeepSeek-V4-Pro, context length \"1049K\", max tokens \"393K\", input price 1.50162, cache read 0.135, output price 3.135 ($ per M tokens), Support image input \"Not supported\", Tools \"Supported\", JSON Mode \"Supported\", Structured Outputs \"Not supported\". The pricing page (https://www.siliconflow.com/pricing, retrieved 2026-09-29) shows the same context length and prices under the name DeepSeek-V4-Pro."
+            },
+            "deepseek-ai/DeepSeek-V4-Flash": {
+                "contextWindow": 1049000,
+                "maxOutputTokens": 393000,
+                "pricingPerMTok": {
+                    "input": 0.13,
+                    "output": 0.28,
+                    "cachedInput": 0.028
+                },
+                "vision": false,
+                "status": "production",
+                "description": "The model page About text begins \"DeepSeek-V4-Flash is DeepSeek's latest open-source MoE model\". Listed in the model enum of the chat-completions API reference (https://docs.siliconflow.com/en/api-reference/chat-completions/chat-completions, retrieved 2026-09-29). The model page https://www.siliconflow.com/models/deepseek-v4-flash (retrieved 2026-09-29) shows the id deepseek-ai/DeepSeek-V4-Flash, context length \"1049K\", max tokens \"393K\", input price 0.13, cache read 0.028, output price 0.28 ($ per M tokens), Support image input \"Not supported\", Tools \"Supported\", JSON Mode \"Supported\", Structured Outputs \"Not supported\"."
+            },
+            "deepseek-ai/DeepSeek-V3.2": {
+                "contextWindow": 164000,
+                "maxOutputTokens": 164000,
+                "pricingPerMTok": {
+                    "input": 0.27,
+                    "output": 0.42,
+                    "cachedInput": 0.135
+                },
+                "vision": false,
+                "status": "production",
+                "description": "The model page About text begins \"DeepSeek-V3.2 is a model that harmonizes high computational efficiency with superior reasoning and agent performance\". Listed in the model enum of the chat-completions API reference (https://docs.siliconflow.com/en/api-reference/chat-completions/chat-completions, retrieved 2026-09-29). The model page https://www.siliconflow.com/models/deepseek-v3-2 (retrieved 2026-09-29) shows the id deepseek-ai/DeepSeek-V3.2, context length \"164K\", max tokens \"164K\", input price 0.27, cache read 0.135, output price 0.42 ($ per M tokens), Support image input \"Not supported\", Tools \"Supported\", JSON Mode \"Supported\", Structured Outputs \"Not supported\"."
+            },
+            "zai-org/GLM-5.1": {
+                "contextWindow": 205000,
+                "maxOutputTokens": 131000,
+                "pricingPerMTok": {
+                    "input": 1.19,
+                    "output": 3.74,
+                    "cachedInput": 0.6
+                },
+                "vision": false,
+                "status": "production",
+                "description": "The model page About text begins \"GLM-5.1 is Z.ai's next-generation flagship model built for agentic engineering\". Listed in the model enum of the chat-completions API reference (https://docs.siliconflow.com/en/api-reference/chat-completions/chat-completions, retrieved 2026-09-29). The model page https://www.siliconflow.com/models/glm-5-1 (retrieved 2026-09-29) shows the id zai-org/GLM-5.1, context length \"205K\", max tokens \"131K\", input price 1.19, cache read 0.6, output price 3.74 ($ per M tokens), Support image input \"Not supported\", Tools \"Supported\", JSON Mode \"Not supported\", Structured Outputs \"Not supported\". The pricing page (https://www.siliconflow.com/pricing, retrieved 2026-09-29) shows the same context length and prices under the name GLM-5.1."
+            },
+            "zai-org/GLM-5": {
+                "contextWindow": 205000,
+                "maxOutputTokens": 131000,
+                "pricingPerMTok": {
+                    "input": 0.95,
+                    "output": 2.55,
+                    "cachedInput": 0.2
+                },
+                "vision": false,
+                "status": "production",
+                "description": "The model page About text begins \"GLM-5 is a next-generation open-source model for complex systems engineering and long-horizon agentic tasks\". Listed in the model enum of the chat-completions API reference (https://docs.siliconflow.com/en/api-reference/chat-completions/chat-completions, retrieved 2026-09-29). The model page https://www.siliconflow.com/models/glm-5 (retrieved 2026-09-29) shows the id zai-org/GLM-5, context length \"205K\", max tokens \"131K\", input price 0.95, cache read 0.2, output price 2.55 ($ per M tokens), Support image input \"Not supported\", Tools \"Supported\", JSON Mode \"Not supported\", Structured Outputs \"Not supported\". The pricing page (https://www.siliconflow.com/pricing, retrieved 2026-09-29) shows the same context length and prices under the name GLM-5."
+            },
+            "moonshotai/Kimi-K2.6": {
+                "contextWindow": 262000,
+                "maxOutputTokens": 262000,
+                "pricingPerMTok": {
+                    "input": 0.77,
+                    "output": 3.4,
+                    "cachedInput": 0.14
+                },
+                "vision": true,
+                "status": "production",
+                "description": "The model page About text begins \"Kimi K2.6 is an open-source, native multimodal agentic model by Moonshot AI\". Listed in the model enum of the chat-completions API reference (https://docs.siliconflow.com/en/api-reference/chat-completions/chat-completions, retrieved 2026-09-29). The model page https://www.siliconflow.com/models/kimi-k2-6 (retrieved 2026-09-29) shows the id moonshotai/Kimi-K2.6, context length \"262K\", max tokens \"262K\", input price 0.77, cache read 0.14, output price 3.4 ($ per M tokens), Support image input \"Supported\", Tools \"Supported\", JSON Mode \"Supported\", Structured Outputs \"Not supported\". The pricing page (https://www.siliconflow.com/pricing, retrieved 2026-09-29) shows the same context length and prices under the name Kimi-K2.6."
+            },
+            "moonshotai/Kimi-K2.5": {
+                "contextWindow": 262000,
+                "maxOutputTokens": 262000,
+                "pricingPerMTok": {
+                    "input": 0.45,
+                    "output": 2.25,
+                    "cachedInput": 0.07
+                },
+                "vision": true,
+                "status": "production",
+                "description": "The model page About text begins \"Kimi K2.5 is an open-source, native multimodal agentic model\". Listed in the model enum of the chat-completions API reference (https://docs.siliconflow.com/en/api-reference/chat-completions/chat-completions, retrieved 2026-09-29). The model page https://www.siliconflow.com/models/kimi-k2-5 (retrieved 2026-09-29) shows the id moonshotai/Kimi-K2.5, context length \"262K\", max tokens \"262K\", input price 0.45, cache read 0.07, output price 2.25 ($ per M tokens), Support image input \"Supported\", Tools \"Supported\", JSON Mode \"Supported\", Structured Outputs \"Not supported\". The pricing page (https://www.siliconflow.com/pricing, retrieved 2026-09-29) shows the same context length and prices under the name Kimi-K2.5."
+            },
+            "Qwen/Qwen3.6-27B": {
+                "contextWindow": 262000,
+                "maxOutputTokens": 262000,
+                "pricingPerMTok": {
+                    "input": 0.3,
+                    "output": 3.2
+                },
+                "vision": true,
+                "status": "production",
+                "description": "The model page About text begins \"Qwen3.6-27B is the first open-weight small-to-mid-sized dense model in the Qwen3.6 series\". Listed in the model enum of the chat-completions API reference (https://docs.siliconflow.com/en/api-reference/chat-completions/chat-completions, retrieved 2026-09-29). The model page https://www.siliconflow.com/models/qwen3-6-27b (retrieved 2026-09-29) shows the id Qwen/Qwen3.6-27B, context length \"262K\", max tokens \"262K\", input price 0.3, output price 3.2 ($ per M tokens), Support image input \"Supported\", Tools \"Supported\", JSON Mode \"Supported\", Structured Outputs \"Not supported\". The pricing page (https://www.siliconflow.com/pricing, retrieved 2026-09-29) shows the same context length and prices under the name Qwen3.6-27B."
+            },
+            "Qwen/Qwen3.6-35B-A3B": {
+                "contextWindow": 262000,
+                "maxOutputTokens": 262000,
+                "pricingPerMTok": {
+                    "input": 0.24,
+                    "output": 1.8,
+                    "cachedInput": 0.15
+                },
+                "vision": true,
+                "status": "production",
+                "description": "The model page About text begins \"Qwen3.6-35B-A3B is a large language model from Alibaba's Qwen3.6 series\". Listed in the model enum of the chat-completions API reference (https://docs.siliconflow.com/en/api-reference/chat-completions/chat-completions, retrieved 2026-09-29). The model page https://www.siliconflow.com/models/qwen3-6-35b-a3b (retrieved 2026-09-29) shows the id Qwen/Qwen3.6-35B-A3B, context length \"262K\", max tokens \"262K\", input price 0.24, cache read 0.15, output price 1.8 ($ per M tokens), Support image input \"Supported\", Tools \"Supported\", JSON Mode \"Supported\", Structured Outputs \"Not supported\". The pricing page (https://www.siliconflow.com/pricing, retrieved 2026-09-29) shows the same context length and prices under the name Qwen3.6-35B-A3B."
+            },
+            "Qwen/Qwen3-32B": {
+                "contextWindow": 131000,
+                "pricingPerMTok": {
+                    "input": 0.14,
+                    "output": 0.57
+                },
+                "vision": false,
+                "status": "production",
+                "description": "The model page About text begins \"Qwen3-32B is the latest large language model in the Qwen series with 32.8B parameters\". Listed in the model enum of the chat-completions API reference (https://docs.siliconflow.com/en/api-reference/chat-completions/chat-completions, retrieved 2026-09-29). The model page https://www.siliconflow.com/models/qwen3-32b (retrieved 2026-09-29) shows the id Qwen/Qwen3-32B, context length \"131K\", max tokens \"131K\", input price 0.14, output price 0.57 ($ per M tokens), Support image input \"Not supported\", Tools \"Supported\", JSON Mode \"Supported\", Structured Outputs \"Not supported\". The Reasoning page (https://docs.siliconflow.com/en/userguide/capabilities/reasoning, retrieved 2026-09-29) lists the Qwen3 Series with Maximum Response Length 8192, Maximum Reasoning Chain Length 32768 and Maximum Context Length 131072. The two pages give different output figures, so maxOutputTokens is not set for this model."
+            },
+            "Qwen/Qwen3-VL-32B-Instruct": {
+                "contextWindow": 262000,
+                "maxOutputTokens": 262000,
+                "pricingPerMTok": {
+                    "input": 0.2,
+                    "output": 0.6
+                },
+                "vision": true,
+                "status": "production",
+                "description": "The model page About text begins \"Qwen3-VL is the vision-language model in the Qwen3 series\". Listed in the model enum of the VLM request schema in the chat-completions API reference (https://docs.siliconflow.com/en/api-reference/chat-completions/chat-completions, retrieved 2026-09-29). The model page https://www.siliconflow.com/models/qwen3-vl-32b-instruct (retrieved 2026-09-29) shows the id Qwen/Qwen3-VL-32B-Instruct, context length \"262K\", max tokens \"262K\", input price 0.2, output price 0.6 ($ per M tokens), Support image input \"Supported\", Tools \"Supported\", JSON Mode \"Supported\", Structured Outputs \"Not supported\"."
+            },
+            "google/gemma-4-31B-it": {
+                "contextWindow": 262000,
+                "maxOutputTokens": 262000,
+                "pricingPerMTok": {
+                    "input": 0.75,
+                    "output": 1.0,
+                    "cachedInput": 0.25
+                },
+                "vision": true,
+                "status": "production",
+                "description": "The model page About text begins \"Gemma 4 31B is Google DeepMind's latest open-source model\". Listed in the model enum of the chat-completions API reference (https://docs.siliconflow.com/en/api-reference/chat-completions/chat-completions, retrieved 2026-09-29). The model page https://www.siliconflow.com/models/gemma-4-31b-it (retrieved 2026-09-29) shows the id google/gemma-4-31B-it, context length \"262K\", max tokens \"262K\", input price 0.75, cache read 0.25, output price 1.0 ($ per M tokens), Support image input \"Supported\", Tools \"Supported\", JSON Mode \"Supported\", Structured Outputs \"Not supported\". The pricing page (https://www.siliconflow.com/pricing, retrieved 2026-09-29) shows the same context length and prices under the name gemma-4-31B-it."
+            }
+        },
+        "topModels": [
+            "deepseek-ai/DeepSeek-V4-Pro",
+            "deepseek-ai/DeepSeek-V4-Flash",
+            "deepseek-ai/DeepSeek-V3.2",
+            "zai-org/GLM-5.1",
+            "zai-org/GLM-5",
+            "moonshotai/Kimi-K2.6",
+            "moonshotai/Kimi-K2.5",
+            "Qwen/Qwen3.6-27B",
+            "Qwen/Qwen3.6-35B-A3B",
+            "Qwen/Qwen3-32B",
+            "Qwen/Qwen3-VL-32B-Instruct",
+            "google/gemma-4-31B-it"
+        ],
+        "visionModel": "Qwen/Qwen3-VL-32B-Instruct"
+    },
+    "capabilities": {
+        "text": true,
+        "streaming": true,
+        "tools": "model-dependent",
+        "toolsWithStreaming": false,
+        "structuredOutput": false,
+        "structuredOutputWithTools": false,
+        "embeddings": false,
+        "thinking": false
+    },
+    "errorRules": [
+        {
+            "status": 401,
+            "class": "authentication",
+            "message": "SiliconFlow rejected the request as unauthorized (HTTP 401; an unauthenticated GET https://api.siliconflow.com/v1/models returned code 30014 with the message \"Token is invalid.\"). Check {apiKeyEnvVar}. Get one at {setupUrl}"
+        },
+        {
+            "status": 403,
+            "class": "authentication",
+            "message": "SiliconFlow reports insufficient permissions (HTTP 403). Its error-handling page (https://docs.siliconflow.com/en/faqs/error-code) says: \"The most common reason is that the model requires real-name authentication.\""
+        },
+        {
+            "status": 429,
+            "class": "rate-limit",
+            "message": "SiliconFlow rate limit reached (HTTP 429). Its error-handling page (https://docs.siliconflow.com/en/faqs/error-code) says to refer to the error message to determine whether the limit is RPM / RPD / TPM / TPD / IPM / IPD."
+        },
+        {
+            "pattern": "Model does not exist",
+            "class": "invalid-model",
+            "message": "SiliconFlow model '{model}' was not found. Its error-handling page (https://docs.siliconflow.com/en/faqs/error-code) shows the HTTP 400 message \"Model does not exist. Please check it carefully.\" with code 20012."
+        }
+    ],
+    "setup": {
+        "url": "https://cloud.siliconflow.com/account/ak",
+        "apiKeyFormat": null,
+        "billingPolicy": "free-tier",
+        "instructions": [
+            "1. Visit: https://cloud.siliconflow.com/ and create a SiliconFlow account (https://docs.siliconflow.com/en/userguide/quickstart)",
+            "2. Open the API Keys page at https://cloud.siliconflow.com/account/ak, click Create API Key and copy the key (https://docs.siliconflow.com/en/userguide/quickstart)",
+            "3. Billing as the vendor words it on https://www.siliconflow.com/pricing: \"Flexible token pricing, high usage limits, and postpaid billing—plus $1 in free credits to get you started!\"",
+            "4. Set {apiKeyEnvVar} in your .env file"
+        ],
+        "description": "Endpoint https://api.siliconflow.com/v1 (the chat-completions API reference lists the server https://api.siliconflow.com/v1 and POST /chat/completions with bearer auth; the Text Generation page says \"You can make end-to-end API requests using the OpenAI SDK\" and the Quick Start says \"The platform currently supports most OpenAI-related parameters.\"). This entry is docs-verified only: an unauthenticated GET of https://api.siliconflow.com/v1/models answered HTTP 401 without a key, so the model ids come from the vendor's public docs and the roster has not been checked; it is not yet live-verified. That GET returned code 30014 with the message \"Token is invalid.\" (2026-09-29), so errorRules match status 401 and the statuses and messages on the vendor's error-handling page (https://docs.siliconflow.com/en/faqs/error-code). capabilities.structuredOutput is false because the model pages show Structured Outputs \"Not supported\" on the 12 catalog models; the JSON Mode page documents response_format={\"type\": \"json_object\"} and this entry sets no responseFormatDowngrade quirk. vision is true for moonshotai/Kimi-K2.6, moonshotai/Kimi-K2.5, Qwen/Qwen3.6-27B, Qwen/Qwen3.6-35B-A3B and google/gemma-4-31B-it from the model page value Support image input \"Supported\"; image input was not exercised. models.defaultContextWindow (32768) and models.defaultMaxOutputTokens (4096) are placeholders for ids outside the catalog that the vendor does not publish; the status values are ones the schema requires (production), not vendor statements. billingPolicy free-tier follows the pricing page's \"$1 in free credits\" statement."
+    },
+    "evidence": {
+        "rosterVerified": {
+            "date": "2026-09-29",
+            "status": 401,
+            "method": "docs-only — unauthenticated GET https://api.siliconflow.com/v1/models answers 401 without a key, so model ids are taken from https://docs.siliconflow.com/en/api-reference/chat-completions/chat-completions (retrieved 2026-09-29) and cross-checked against the ids shown on the model pages under https://www.siliconflow.com/models/ (retrieved 2026-09-29); roster not verified"
+        },
+        "authProbe": {
+            "date": "2026-09-29",
+            "status": 401,
+            "code": "30014",
+            "method": "unauthenticated GET https://api.siliconflow.com/v1/models — body {\"code\":30014,\"data\":null,\"message\":\"Token is invalid.\"} with header www-authenticate: Bearer realm=\"siliconflow\", error=\"invalid_token\", error_description=\"Token is invalid.\"; credential-free, no key used"
+        },
+        "billingProbe": {
+            "date": "2026-09-29",
+            "method": "public page https://www.siliconflow.com/pricing — \"Flexible token pricing, high usage limits, and postpaid billing—plus $1 in free credits to get you started!\" and the FAQ answer \"No, there are no minimum commitments. You only pay for what you use, and you can start with $1 in free credits.\"; credential-free"
+        },
+        "liveMatrix": null,
+        "addedInPR": "https://github.com/juspay/neurolink/pull/1860"
+    }
+}

package/dist/providers/catalog/stepfun.json

@@ -0,0 +1,155 @@
+{
+    "$schema": "./provider-catalog.schema.json",
+    "id": "stepfun",
+    "displayName": "StepFun",
+    "aliases": [],
+    "tier": 2,
+    "wire": {
+        "baseURL": "https://api.stepfun.ai/v1"
+    },
+    "models": {
+        "default": "step-5-preview",
+        "fallbacks": [
+            "step-3.7-flash",
+            "step-3.5-flash",
+            "step-3.5-flash-2603",
+            "step-1o-turbo-vision"
+        ],
+        "fallbackModelName": "step-3.7-flash",
+        "defaultContextWindow": 32000,
+        "defaultMaxOutputTokens": 16384,
+        "catalog": {
+            "step-5-preview": {
+                "contextWindow": 1000000,
+                "maxOutputTokens": 64000,
+                "pricingPerMTok": {
+                    "input": 1.0,
+                    "output": 2.7,
+                    "cachedInput": 0.05
+                },
+                "vision": true,
+                "status": "preview",
+                "description": "NeuroLink default. Model page https://platform.stepfun.ai/docs/en/guides/models/step-5-preview (retrieved 2026-09-29): \"Step 5 Preview is StepFun's flagship model for agentic work.\" The page's specification table gives Model ID step-5-preview, Context window \"1M tokens\", Input types \"Text, images, and video\", Output type \"Text\" and Maximum output \"64k tokens\"; its features table lists Streaming output, Tool calling, Structured output (\"JSON Mode and JSON Schema supported\"), Reasoning effort (low, medium, high) and Prompt caching. The Chat Completions page https://platform.stepfun.ai/docs/en/api-reference/chat/chat-completion-create.md states \"The examples below use step-5-preview by default.\" Prices per https://platform.stepfun.ai/docs/en/guides/pricing/details.md: $1.00 input (cache miss), $0.05 input (cache hit), $2.70 output per 1M tokens. contextWindow 1000000 and maxOutputTokens 64000 are the decimal forms of \"1M tokens\" and \"64k tokens\"; vision is true because the model page lists images and video as input types; status is preview because the vendor names the model \"Step 5 Preview\"."
+            },
+            "step-3.7-flash": {
+                "contextWindow": 256000,
+                "pricingPerMTok": {
+                    "input": 0.2,
+                    "output": 1.15,
+                    "cachedInput": 0.04
+                },
+                "vision": true,
+                "status": "production",
+                "description": "Fallback. Model page https://platform.stepfun.ai/docs/en/guides/models/step-3.7-flash (retrieved 2026-09-29): \"StepFun's flagship multimodal reasoning model. Powered by a 198B-parameter / 11B-activation sparse MoE architecture, with native support for image and video understanding.\" Its Key facts section states a context length of 256K tokens, and the page lists three reasoning effort levels (low, medium, high) set with reasoning_effort on the Chat Completions API. The Quickstart table (https://platform.stepfun.ai/docs/en/quickstart/overview.md) lists Input capabilities \"Text, images, and video\" for it; the Tool Call page (https://platform.stepfun.ai/docs/en/api-reference/tool-call.md) lists it among the models that support Toolcall requests, and the JSON Mode page (https://platform.stepfun.ai/docs/en/guides/developer/json-mode.md) says the json_schema approach applies to it. Prices per https://platform.stepfun.ai/docs/en/guides/pricing/details.md (the model page shows the same figures): $0.20 input (cache miss), $0.04 input (cache hit), $1.15 output per 1M tokens. contextWindow 256000 is the decimal form of \"256K tokens\"; vision is true because the Quickstart table lists images and video as input capabilities."
+            },
+            "step-3.5-flash": {
+                "contextWindow": 256000,
+                "pricingPerMTok": {
+                    "input": 0.1,
+                    "output": 0.3,
+                    "cachedInput": 0.02
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Fallback. Model page https://platform.stepfun.ai/docs/en/guides/models/step-3.5-flash (retrieved 2026-09-29): the model is \"StepFun's flagship language reasoning model\", \"Built on a 196B-parameter / 11B-activation sparse MoE architecture.\" Its Key facts section states a context length of 256K tokens. The Quickstart table (https://platform.stepfun.ai/docs/en/quickstart/overview.md) lists Input capabilities \"Text only\" for it and says \"Step 3.5 Flash does not support image input\". The Tool Call page (https://platform.stepfun.ai/docs/en/api-reference/tool-call.md) lists it among the models that support Toolcall requests, and the JSON Mode page (https://platform.stepfun.ai/docs/en/guides/developer/json-mode.md) says the json_schema approach applies to it. Prices per https://platform.stepfun.ai/docs/en/guides/pricing/details.md (the model page shows the same figures): $0.10 input (cache miss), $0.02 input (cache hit), $0.30 output per 1M tokens. contextWindow 256000 is the decimal form of \"256K tokens\"."
+            },
+            "step-3.5-flash-2603": {
+                "contextWindow": 256000,
+                "pricingPerMTok": {
+                    "input": 0.1,
+                    "output": 0.3,
+                    "cachedInput": 0.02
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Fallback. The Model variants section of https://platform.stepfun.ai/docs/en/guides/models/step-3.5-flash (retrieved 2026-09-29) describes step-3.5-flash-2603 as \"Agent-optimized version: tuned from step-3.5-flash for high-frequency agent scenarios.\" and says it \"Supports the reasoning_effort field (low / high).\" The Chat Completions page (https://platform.stepfun.ai/docs/en/api-reference/chat/chat-completion-create.md) says step-3.5-flash-2603 accepts low and high for reasoning_effort. The welcome page model overview (https://platform.stepfun.ai/docs/en/welcome.md) has a card titled \"Step 3.5 Flash 2603\" with the category \"Reasoning / text\", the subtitle \"Optimized for agents\" and the metric \"Max context\" (value 256K). The Tool Call page (https://platform.stepfun.ai/docs/en/api-reference/tool-call.md) lists step-3.5-flash-2603 among the models that support Toolcall requests, and the JSON Mode page (https://platform.stepfun.ai/docs/en/guides/developer/json-mode.md) says the json_schema approach applies to it. Prices per https://platform.stepfun.ai/docs/en/guides/pricing/details.md: $0.10 input (cache miss), $0.02 input (cache hit), $0.30 output per 1M tokens. contextWindow 256000 is the decimal form of 256K; vision is false (the welcome card category is \"Reasoning / text\")."
+            },
+            "step-1o-turbo-vision": {
+                "contextWindow": 32000,
+                "pricingPerMTok": {
+                    "input": 0.36,
+                    "output": 1.15,
+                    "cachedInput": 0.07
+                },
+                "vision": true,
+                "status": "production",
+                "description": "Fallback. Listed as step-1o-turbo-vision under \"Pricing for Vision Models\" on https://platform.stepfun.ai/docs/en/guides/pricing/details.md (retrieved 2026-09-29): $0.36 input (cache miss), $0.07 input (cache hit), $1.15 output per 1M tokens; the page adds \"Image input is counted and billed as tokens, just like text input.\" The Model Retirement and Migration page (https://platform.stepfun.ai/docs/en/guides/model-migration.md) lists it in the \"Recommended replacement\" column for step-1-8k, step-1-32k, step-1v-8k, step-1v-32k, step-2-mini, step-1o-vision-32k and step-2-16k. The welcome page model overview (https://platform.stepfun.ai/docs/en/welcome.md) has a card titled \"Step-1o Turbo Vision\" with the metric \"Max context\" (value 32K) and the text \"Designed for social content creation, AI assistants, and image and video understanding.\" contextWindow 32000 is the decimal form of 32K; vision is true because the pricing page groups the model under vision models and the card describes image and video understanding."
+            }
+        },
+        "topModels": [
+            "step-5-preview",
+            "step-3.7-flash",
+            "step-3.5-flash",
+            "step-3.5-flash-2603",
+            "step-1o-turbo-vision"
+        ],
+        "visionModel": "step-5-preview"
+    },
+    "capabilities": {
+        "text": true,
+        "streaming": true,
+        "tools": "model-dependent",
+        "toolsWithStreaming": true,
+        "structuredOutput": true,
+        "structuredOutputWithTools": false,
+        "embeddings": false,
+        "thinking": true
+    },
+    "errorRules": [
+        {
+            "status": 401,
+            "class": "authentication",
+            "message": "StepFun rejected the API key (HTTP 401 invalid_api_key; the Error Codes page lists 401 as \"Invalid authentication\" with the resolution \"Make sure you are using the correct API key.\"). Check {apiKeyEnvVar}. Create a key: {setupUrl}"
+        },
+        {
+            "status": 402,
+            "class": "provider",
+            "message": "StepFun returned HTTP 402 (the Error Codes page lists 402 as \"Insufficient balance\" with the resolution \"Add funds to your account.\")."
+        },
+        {
+            "status": 429,
+            "class": "rate-limit",
+            "message": "StepFun returned HTTP 429 (the Error Codes page lists 429 as \"Resource or rate limit exceeded, usually because requests are too frequent\" with the resolution \"Retry after a short delay.\")."
+        },
+        {
+            "status": 451,
+            "class": "provider",
+            "message": "StepFun returned HTTP 451 (the Error Codes page lists 451 as \"The request or response content failed review\" with the resolution \"Modify the request and try again.\")."
+        },
+        {
+            "status": 503,
+            "class": "provider",
+            "message": "StepFun returned HTTP 503 (the Error Codes page lists 503 as \"Server is currently overloaded\" with the resolution \"Retry after a short delay.\")."
+        }
+    ],
+    "setup": {
+        "url": "https://platform.stepfun.ai/interface-key",
+        "apiKeyFormat": null,
+        "billingPolicy": "no-free-tier",
+        "instructions": [
+            "1. Visit: 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.\"",
+            "2. Billing 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.\"",
+            "3. Set {apiKeyEnvVar} in your .env file"
+        ],
+        "description": "Docs-verified only: the vendor's GET https://api.stepfun.ai/v1/models needs a key (it answers HTTP 401 without one), so the five model ids come from the pricing page https://platform.stepfun.ai/docs/en/guides/pricing/details.md and the roster has not been checked; the entry is not yet live-verified. OpenAI-compatible endpoint at https://api.stepfun.ai/v1: the Chat Completions page (https://platform.stepfun.ai/docs/en/api-reference/chat/chat-completion-create.md) documents POST https://api.stepfun.ai/v1/chat/completions with a required model and messages, and streaming as data: chunks ending in data: [DONE]; the migration page (https://platform.stepfun.ai/docs/en/guides/developer/openai.md) says \"Stepfun models are compatible with the OpenAI API spec.\" Unauthenticated GETs made 2026-09-29: /models and /chat/completions each answered HTTP 401 with the body {\"error\":{\"message\":\"Incorrect API key provided\",\"type\":\"invalid_api_key\"}}; errorRules carry that 401 and the 402, 429, 451 and 503 statuses listed on the Error Codes page. models.defaultContextWindow (32000) and models.defaultMaxOutputTokens (16384) are conservative placeholders for model ids outside the catalog; the vendor does not publish a general default. Per-model contextWindow and maxOutputTokens values are the decimal forms of the labels the vendor prints (\"1M tokens\", \"256K tokens\", 32K, \"64k tokens\"). billingPolicy holds the schema value no-free-tier because the catalog schema has no unknown value; it is not a vendor statement. The base URL is the standard Open Platform endpoint; the Step Plan overview (https://platform.stepfun.ai/docs/en/step-plan/overview.md) lists a separate OpenAI SDK base URL, https://api.stepfun.ai/step_plan/v1. 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 StepFun."
+    },
+    "evidence": {
+        "rosterVerified": {
+            "date": "2026-09-29",
+            "status": 401,
+            "method": "docs-only — unauthenticated GET https://api.stepfun.ai/v1/models answers 401 without a key, so model ids are taken from https://platform.stepfun.ai/docs/en/guides/pricing/details.md (retrieved 2026-09-29); roster not verified"
+        },
+        "authProbe": {
+            "date": "2026-09-29",
+            "status": 401,
+            "code": "invalid_api_key",
+            "method": "unauthenticated GET https://api.stepfun.ai/v1/models and GET https://api.stepfun.ai/v1/chat/completions, no Authorization header — each HTTP 401, JSON body {\"error\":{\"message\":\"Incorrect API key provided\",\"type\":\"invalid_api_key\"}}; the code recorded here is the body's error.type value (the body has no error.code field); credential-free, no key used"
+        },
+        "billingProbe": {
+            "date": "2026-09-29",
+            "method": "public pages https://platform.stepfun.ai/docs/en/guides/pricing/intro.md (\"drawing from free credit first, then paid balance\"), https://platform.stepfun.ai/docs/en/guides/pricing/details.md (per-token prices and rate-limit tiers by cumulative top-up amount) and https://platform.stepfun.ai/docs/en/api-reference/error-codes.md (402 \"Insufficient balance\"); credential-free, no signup performed"
+        },
+        "liveMatrix": null,
+        "addedInPR": "https://github.com/juspay/neurolink/pull/1860"
+    }
+}

package/dist/providers/catalog/subconscious.json

@@ -0,0 +1,93 @@
+{
+    "$schema": "./provider-catalog.schema.json",
+    "id": "subconscious",
+    "displayName": "Subconscious",
+    "aliases": [],
+    "tier": 2,
+    "wire": {
+        "baseURL": "https://api.subconscious.dev/v1"
+    },
+    "models": {
+        "default": "subconscious/glm-5.3-marathon",
+        "fallbacks": [
+            "subconscious/deepseek-v4.1-flash-marathon",
+            "subconscious/tim-qwen3.6-27b"
+        ],
+        "defaultContextWindow": 200000,
+        "defaultMaxOutputTokens": 4096,
+        "catalog": {
+            "subconscious/glm-5.3-marathon": {
+                "pricingPerMTok": {
+                    "input": 1.4,
+                    "output": 4.4,
+                    "cachedInput": 0.26
+                },
+                "vision": false,
+                "status": "production",
+                "description": "NeuroLink default. The pricing page (https://www.subconscious.dev/pricing, retrieved 2026-09-29) lists the id subconscious/glm-5.3-marathon under the name 'GLM-5.3 Marathon', with the description 'Open-source frontier coding model', at $0.26 cached, $1.40 input and $4.40 output per 1M tokens. The API reference (https://docs.subconscious.dev/api-reference/openapi.json) lists this id as the model enum value. Present on the unauthenticated GET /v1/models roster (2026-09-29). vision is false as a schema-required placeholder the vendor does not publish for this id."
+            },
+            "subconscious/deepseek-v4.1-flash-marathon": {
+                "vision": false,
+                "status": "production",
+                "description": "NeuroLink fallback. Present on the unauthenticated GET /v1/models roster (2026-09-29). The vendor homepage FAQ (https://www.subconscious.dev, retrieved 2026-09-29) says 'On our managed inference service, we serve GLM 5.3 Marathon and DeepSeek V4.1 Flash Marathon.' No pricing is attached: the pricing page (https://www.subconscious.dev/pricing, retrieved 2026-09-29) lists the id subconscious/deepseek-v4-flash-marathon, which differs from this roster id, with the description 'Multimodal & high-throughput DeepSeek V4'. vision is false as a schema-required placeholder the vendor does not publish for this roster id. Not probed with a key."
+            },
+            "subconscious/tim-qwen3.6-27b": {
+                "vision": false,
+                "status": "production",
+                "description": "NeuroLink fallback. Present on the unauthenticated GET /v1/models roster (2026-09-29). The vendor blog post 'Introducing TIM-Qwen3.6-27B' (https://www.subconscious.dev/blog/introducing-tim-qwen3-6-27b, May 21, 2026) says the model is 'available via the OpenAI chat completions and Anthropic messages API formats'. vision is false as a schema-required placeholder the vendor does not publish for this id. Not probed with a key."
+            }
+        },
+        "topModels": [
+            "subconscious/glm-5.3-marathon",
+            "subconscious/deepseek-v4.1-flash-marathon",
+            "subconscious/tim-qwen3.6-27b"
+        ]
+    },
+    "capabilities": {
+        "text": true,
+        "streaming": true,
+        "tools": false,
+        "toolsWithStreaming": false,
+        "structuredOutput": false,
+        "structuredOutputWithTools": false,
+        "embeddings": false,
+        "thinking": false
+    },
+    "errorRules": [
+        {
+            "status": 401,
+            "class": "authentication",
+            "message": "Invalid or missing Subconscious API key. Check {apiKeyEnvVar}. Get one at {setupUrl}"
+        },
+        {
+            "status": 429,
+            "class": "rate-limit",
+            "message": "Subconscious returned HTTP 429: rate limited due to too many requests or tokens per minute."
+        }
+    ],
+    "setup": {
+        "url": "https://subconscious.dev/platform/api-keys",
+        "apiKeyFormat": null,
+        "billingPolicy": "no-free-tier",
+        "instructions": [
+            "1. Visit https://subconscious.dev/platform and sign up or sign in (the quickstart, https://docs.subconscious.dev/quickstart, describes signing up on the platform and generating an API key from the dashboard)",
+            "2. Create an API key at https://subconscious.dev/platform/api-keys and copy it (https://docs.subconscious.dev/ways-to-use/cloud-api says API keys are created and managed from the dashboard)",
+            "3. Pricing is at https://www.subconscious.dev/pricing (monthly token plans and usage-based per-token pricing); the cloud-API page says 'Usage is billed per token.' and 'Credits are added from your dashboard'",
+            "4. Set {apiKeyEnvVar} in your .env file"
+        ],
+        "description": "OpenAI-compatible Chat Completions endpoint at https://api.subconscious.dev/v1. The vendor overview (https://docs.subconscious.dev/overview) says 'Our API is compatible with both the OpenAI Completions and Anthropic Messages APIs'; this entry uses the OpenAI-format /chat/completions route. Verification level: docs- and roster-verified, not live-verified (evidence.liveMatrix is null). Checks made on 2026-09-29 were unauthenticated GET requests to /v1/models (HTTP 200, 4 models) and /v1/chat/completions (HTTP 405, allow: POST); no key was used and no POST was sent. The OpenAPI spec (https://docs.subconscious.dev/api-reference/openapi.json) lists statuses 400, 401 ('Unauthorized because of a missing or invalid API key'), 429 ('Rate limited due to too many requests or tokens per minute') and 500, so errorRules match on status. The spec says of response_format: 'Currently unsupported. The request may accept this field, but it is ignored and does not constrain the model output to JSON or a schema.' tools, toolsWithStreaming, structuredOutput, structuredOutputWithTools and thinking are declared false and were not probed with a key. models.defaultContextWindow (200000), models.defaultMaxOutputTokens (4096) and the vision value (false) of the three catalog models are placeholders the vendor does not publish per model. billingPolicy no-free-tier is the schema's required field value, not a vendor statement."
+    },
+    "evidence": {
+        "rosterVerified": {
+            "date": "2026-09-29",
+            "method": "unauthenticated GET https://api.subconscious.dev/v1/models — 4 models; credential-free, no key used",
+            "status": 200
+        },
+        "billingProbe": {
+            "date": "2026-09-29",
+            "method": "public pages https://docs.subconscious.dev/ways-to-use/cloud-api and https://www.subconscious.dev/pricing read without an account. The vendor blog post https://www.subconscious.dev/blog/subconscious-glm-5-2-makes-compact-obsolete (June 22, 2026, about GLM-5.2) says 'You also get $50 credits to test the model performance'; no account was created, so that offer was not tried; credential-free"
+        },
+        "liveMatrix": null,
+        "addedInPR": "https://github.com/juspay/neurolink/pull/1860"
+    }
+}