@juspay/neurolink
Version:
The pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.00002
166 lines (165 loc) • 14.7 kB
JSON
{
"$schema": "./provider-catalog.schema.json",
"id": "dashscope",
"displayName": "Alibaba Cloud Model Studio (DashScope)",
"aliases": [],
"tier": 2,
"wire": {
"baseURL": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
},
"models": {
"default": "qwen3.8-max",
"fallbacks": [
"qwen3.8-flash",
"qwen3.7-plus",
"qwen3.8-max-0902",
"qwen3.7-flash",
"deepseek-v4-pro",
"deepseek-v4-flash",
"kimi-k3"
],
"defaultContextWindow": 128000,
"defaultMaxOutputTokens": 8192,
"catalog": {
"qwen3.8-max": {
"contextWindow": 1000000,
"pricingPerMTok": {
"input": 2,
"output": 6
},
"vision": true,
"status": "production",
"description": "NeuroLink default. Named under Text generation on https://www.alibabacloud.com/help/en/model-studio/models (retrieved 2026-09-29) and used as the model in the OpenAI-compatible examples on https://www.alibabacloud.com/help/en/model-studio/first-api-call-to-qwen. https://www.alibabacloud.com/help/en/model-studio/text-generation-model says \"For the strongest reasoning, choose qwen3.8-max.\" and its Recommended models table lists Context 1M, Thinking mode Supported, Function Calling Supported, Built-in tools Supported, Structured output Supported. https://www.alibabacloud.com/help/en/model-studio/model-pricing, Singapore tab, International deployment scope: input $2 and output $6 per 1 million tokens for 0<Token≤1M, free quota 1 million tokens. Listed under Image & video, Understanding on the Models page; the vision page (https://www.alibabacloud.com/help/en/model-studio/vision) passes an image_url message to it and its image-quantity limit reads \"Qwen3.8-Max, Qwen3.8-Flash, Qwen3.7-Plus series: Up to 2,048 images\"."
},
"qwen3.8-flash": {
"contextWindow": 1000000,
"pricingPerMTok": {
"input": 0.15,
"output": 0.47
},
"vision": true,
"status": "production",
"description": "Fallback. Named under Text generation on https://www.alibabacloud.com/help/en/model-studio/models (retrieved 2026-09-29). The Recommended models table on https://www.alibabacloud.com/help/en/model-studio/text-generation-model lists Context 1M, Thinking mode Supported, Function Calling Supported, Built-in tools Supported, Structured output Supported. https://www.alibabacloud.com/help/en/model-studio/model-pricing, Singapore tab, International deployment scope: input $0.15 and output $0.47 per 1 million tokens for 0<Token≤1M. The vision page (https://www.alibabacloud.com/help/en/model-studio/vision) image-quantity limit reads \"Qwen3.8-Max, Qwen3.8-Flash, Qwen3.7-Plus series: Up to 2,048 images\"."
},
"qwen3.7-plus": {
"contextWindow": 1000000,
"vision": true,
"status": "production",
"description": "Fallback. https://www.alibabacloud.com/help/en/model-studio/text-generation-model (retrieved 2026-09-29) says \"We recommend qwen3.7-plus for balanced performance and cost, with full tool calling and a 1M-token context window for large codebases.\" and its Recommended models table lists Context 1M, Thinking mode Supported, Function Calling Supported, Built-in tools Supported, Structured output Supported. Named under Text generation and under Image & video, Understanding on https://www.alibabacloud.com/help/en/model-studio/models; the vision page (https://www.alibabacloud.com/help/en/model-studio/vision) image-quantity limit reads \"Qwen3.8-Max, Qwen3.8-Flash, Qwen3.7-Plus series: Up to 2,048 images\"."
},
"qwen3.8-max-0902": {
"contextWindow": 1000000,
"pricingPerMTok": {
"input": 2,
"output": 6
},
"vision": true,
"status": "production",
"description": "Fallback. The Recommended models table on https://www.alibabacloud.com/help/en/model-studio/text-generation-model (retrieved 2026-09-29) lists Context 1M, Thinking mode Supported, Function Calling Supported, Built-in tools Supported, Structured output Supported. https://www.alibabacloud.com/help/en/model-studio/model-pricing, Singapore tab, International deployment scope: input $2 and output $6 per 1 million tokens for 0<Token≤1M. The Visual understanding page (https://www.alibabacloud.com/help/en/model-studio/vision-model, retrieved 2026-09-29) names it in its Video support list (\"Up to 2 hours / 2 GB\") and its Recommended models row lists Max pixels/image 16M, Max images 2048 and Max videos 64."
},
"qwen3.7-flash": {
"contextWindow": 1000000,
"vision": true,
"status": "production",
"description": "Fallback. The Recommended models table on https://www.alibabacloud.com/help/en/model-studio/text-generation-model (retrieved 2026-09-29) lists Context 1M, Thinking mode Supported, Function Calling Supported, Built-in tools Supported, Structured output Supported. The vision page (https://www.alibabacloud.com/help/en/model-studio/vision) image-quantity limit reads \"Qwen3.7-Flash, Qwen3.6-Plus, Qwen3.6-Flash, Qwen3.5-Plus, Qwen3.5-Flash, Qwen3-VL, Qwen-VL, QVQ series: Up to 256 images\"."
},
"deepseek-v4-pro": {
"contextWindow": 1000000,
"pricingPerMTok": {
"input": 2.4,
"output": 4.8
},
"vision": false,
"status": "production",
"description": "Fallback. The Recommended models table on https://www.alibabacloud.com/help/en/model-studio/text-generation-model (retrieved 2026-09-29) lists Context 1M, Thinking mode Supported, Function Calling Supported, Built-in tools Unsupported, Structured output Supported. https://www.alibabacloud.com/help/en/model-studio/model-pricing, Singapore tab, International deployment scope: input $2.400 and output $4.800 per 1 million tokens. vision is false: https://www.alibabacloud.com/help/en/model-studio/error-code (retrieved 2026-09-29) refers to \"plain-text models like qwen3-max, qwen-plus, or deepseek-v4-pro\"."
},
"deepseek-v4-flash": {
"contextWindow": 1000000,
"pricingPerMTok": {
"input": 0.2,
"output": 0.4
},
"vision": false,
"status": "production",
"description": "Fallback. The Recommended models table on https://www.alibabacloud.com/help/en/model-studio/text-generation-model (retrieved 2026-09-29) lists Context 1M, Thinking mode Supported, Function Calling Supported, Built-in tools Unsupported, Structured output Supported. https://www.alibabacloud.com/help/en/model-studio/model-pricing, Singapore tab, International deployment scope: input $0.200 and output $0.400 per 1 million tokens. vision is false as a placeholder because the schema requires a boolean."
},
"kimi-k3": {
"pricingPerMTok": {
"input": 3,
"output": 15
},
"vision": true,
"status": "production",
"description": "Fallback. Named under Text generation and under Image & video, Understanding on https://www.alibabacloud.com/help/en/model-studio/models (retrieved 2026-09-29). https://www.alibabacloud.com/help/en/model-studio/model-pricing, Singapore tab, International deployment scope: input $3 and output $15 per 1 million tokens."
}
},
"topModels": [
"qwen3.8-max",
"qwen3.8-flash",
"qwen3.7-plus",
"qwen3.8-max-0902",
"qwen3.7-flash",
"deepseek-v4-pro",
"deepseek-v4-flash",
"kimi-k3"
]
},
"capabilities": {
"text": true,
"streaming": true,
"tools": "model-dependent",
"toolsWithStreaming": true,
"structuredOutput": true,
"structuredOutputWithTools": false,
"embeddings": false,
"thinking": false
},
"errorRules": [
{
"status": 401,
"class": "authentication",
"message": "DashScope returned HTTP 401. Check {apiKeyEnvVar}. Get a key at {setupUrl}. The vendor's error-code page (https://www.alibabacloud.com/help/en/model-studio/error-code) lists an API key and base URL from different regions as a cause."
},
{
"pattern": "FreeTierOnly|free tier of the model has been exhausted",
"class": "provider",
"message": "DashScope reports the free tier of the model has been exhausted (HTTP 403, code AllocationQuota.FreeTierOnly). The vendor's error-code page says the free quota exhaustion stop switch can be disabled to continue on a paid basis (https://www.alibabacloud.com/help/en/model-studio/error-code)."
},
{
"pattern": "Arrearage|account is in good standing",
"class": "provider",
"message": "DashScope denied access (HTTP 400, code Arrearage). The vendor's error-code page gives the cause as an overdue payment on the Alibaba Cloud account associated with the API key (https://www.alibabacloud.com/help/en/model-studio/error-code)."
}
],
"setup": {
"url": "https://modelstudio.console.alibabacloud.com/ap-southeast-1/settings/api-key",
"apiKeyFormat": null,
"billingPolicy": "free-tier",
"instructions": [
"1. Visit: https://account.alibabacloud.com/register/intl_register.htm and create an Alibaba Cloud account (linked from https://www.alibabacloud.com/help/en/model-studio/first-api-call-to-qwen)",
"2. Complete your account information, then open https://modelstudio.console.alibabacloud.com/ap-southeast-1 and agree to the service agreement to activate Model Studio (Singapore region); https://www.alibabacloud.com/help/en/model-studio/new-free-quota says the system then grants a free quota automatically",
"3. Create an API key at https://modelstudio.console.alibabacloud.com/ap-southeast-1/settings/api-key with the region set to Singapore; https://www.alibabacloud.com/help/en/model-studio/get-api-key states that each region has its own endpoint, API keys, and model list, and that they cannot be used across regions. Copy the key when it is shown",
"4. Free quota, per https://www.alibabacloud.com/help/en/model-studio/new-free-quota: valid for 90 days, typically 1,000,000 tokens for each model, and \"After the free quota is exhausted, you are automatically billed on a pay-as-you-go basis.\"",
"5. Set {apiKeyEnvVar} in your .env file (the vendor's examples use the same variable name)"
],
"description": "Alibaba Cloud Model Studio (DashScope), Singapore region, International deployment scope (https://www.alibabacloud.com/help/en/model-studio/regions: the China (Beijing) and Singapore regions each support one service deployment scope, Chinese mainland and International respectively). OpenAI-compatible endpoint at https://dashscope-intl.aliyuncs.com/compatible-mode/v1, which the regions page lists as the Singapore DashScope domain and labels the existing domain; https://www.alibabacloud.com/help/en/model-studio/qwen-api-via-openai-chat-completions says \"The existing domain remains fully functional.\" The vendor also documents a workspace-dedicated domain, https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1, labelled recommended on the regions page; set DASHSCOPE_BASE_URL to use it. Per-model contextWindow values are the decimal forms of the 1M labels on the text-generation page, since https://www.alibabacloud.com/help/en/model-studio/model-pricing states \"K means 1,000 and M means 1,000,000\". models.defaultContextWindow (128000) and models.defaultMaxOutputTokens (8192) are conservative placeholders; the vendor does not publish a general default. They apply wherever the catalog sets no value, which includes model ids outside the catalog, the contextWindow of kimi-k3 and the maxOutputTokens of each catalog id. vision: false on deepseek-v4-flash is a placeholder because the schema requires a boolean. capabilities.thinking is false because NeuroLink's thinkingLevel option has not been exercised against this provider (no credentials were used); the text-generation page lists Thinking mode Supported for the ids in its Recommended models table, and the Chat page (https://www.alibabacloud.com/help/en/model-studio/qwen-api-via-openai-chat-completions) documents enable_thinking and reasoning_effort. errorRules: HTTP 401 was observed on an unauthenticated GET of /models; the FreeTierOnly and Arrearage rules follow https://www.alibabacloud.com/help/en/model-studio/error-code."
},
"evidence": {
"rosterVerified": {
"date": "2026-09-29",
"status": 401,
"method": "docs-only — unauthenticated GET https://dashscope-intl.aliyuncs.com/compatible-mode/v1/models answers 401 without a key, so model ids are taken from https://www.alibabacloud.com/help/en/model-studio/text-generation-model and https://www.alibabacloud.com/help/en/model-studio/models (retrieved 2026-09-29); roster not verified"
},
"authProbe": {
"date": "2026-09-29",
"status": 401,
"method": "unauthenticated GET https://dashscope-intl.aliyuncs.com/compatible-mode/v1/models — JSON body with error.message \"You didn't provide an API key. You need to provide your API key in an Authorization header using Bearer auth (i.e. Authorization: Bearer YOUR_KEY).\", error.type \"invalid_request_error\", error.param null, error.code null and a top-level request_id; credential-free, no key used"
},
"billingProbe": {
"date": "2026-09-29",
"method": "public page https://www.alibabacloud.com/help/en/model-studio/new-free-quota — \"the platform automatically grants you a free quota for various models\"; \"After the free quota is exhausted, you are automatically billed on a pay-as-you-go basis.\"; credential-free"
},
"liveMatrix": null,
"addedInPR": "https://github.com/juspay/neurolink/pull/1862"
}
}