Free ModelScope API Key, Base URL & Rate Limits
Model ProviderModelScope is Alibaba's model hub and inference platform, providing free API access to Qwen, DeepSeek, and other models popular in the Chinese AI ecosystem.
Free TierFunction CallingVision
How to get a free ModelScope API key
- 1
- 2 Go to Access Tokens
- 3 Create an access token
- 4 Choose a model Qwen3.5 and DeepSeek available. 2,000 RPD total.
- 5 Configure OpenAI client Base URL: https://api-inference.modelscope.cn/v1
Provider Snapshot
Provider Type Model Provider
OpenAI Compatible No
Base URL https://api-inference.modelscope.cn/v1
Free Tier 47 free models online
Phone Required Unknown
Streaming Varies
Function Calling Yes
Vision Yes
Last Updated 2026-07-07
Supported Models 47 models
View in directory →| Model ID | Developer | Context | Availability | Free Tier | Use cases |
|---|---|---|---|---|---|
| deepseek-ai/DeepSeek-V4-Pro-0813 deepseek-ai/DeepSeek-V4-Pro-0813 | DeepSeek | 8K | Online | Yes | chat |
| Qwen/Qwen3.8-27B Qwen/Qwen3.8-27B | Alibaba | 8K | Online | Yes | chat |
| deepseek-ai/DeepSeek-V4-Pro deepseek-ai/DeepSeek-V4-Pro | ModelScope | 8K | Online | Yes | chat |
| deepseek-ai/DeepSeek-V4-Flash-0731 deepseek-ai/DeepSeek-V4-Flash | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3.5-397B-A17B Qwen/Qwen3.5-397B-A17B | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3.5-122B-A10B Qwen/Qwen3.5-122B-A10B | ModelScope | 8K | Online | Yes | chat |
| Tencent-Hunyuan/Hy3 Tencent-Hunyuan/Hy3 | ModelScope | 8K | Online | Yes | chat |
| ZhipuAI/GLM-4.7-Flash GLM-4.7-FlashX | ModelScope | 200K | Online | Yes | chat |
| ZhipuAI/GLM-5.2 GLM-5.1 | ModelScope | 1.0M | Online | Yes | chat |
| MiniMax/MiniMax-M3 MiniMax-M3 | ModelScope | 512K | Online | Yes | chat |
| opencompass/CompassJudger-1-32B-Instruct opencompass/CompassJudger-1-32B-Instruct | ModelScope | 8K | Online | Yes | chat |
| XGenerationLab/XiYanSQL-QwenCoder-32B-2412 XGenerationLab/XiYanSQL-QwenCoder-32B-2412 | ModelScope | 8K | Online | Yes | chat |
| XGenerationLab/XiYanSQL-QwenCoder-32B-2504 XGenerationLab/XiYanSQL-QwenCoder-32B-2504 | ModelScope | 8K | Online | Yes | chat |
| stepfun-ai/Step-3.5-Flash stepfun-ai/Step-3.5-Flash | ModelScope | 8K | Online | Yes | chat |
| stepfun-ai/Step-3.7-Flash stepfun-ai/Step-3.7-Flash | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3.8-Flash-Next Qwen/Qwen3.8-Flash-Next | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3.5-27B Qwen/Qwen3.5-27B | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3.5-35B-A3B Qwen/Qwen3.5-35B-A3B | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen/Qwen3-235B-A22B-Instruct-2507 | ModelScope | 8K | Online | Yes | chat |
| MedAIBase/AntAngelMed MedAIBase/AntAngelMed | ModelScope | 8K | Online | Yes | chat |
| MiniMax/MiniMax-M1-80k MiniMax/MiniMax-M1-80k | ModelScope | 8K | Online | Yes | chat |
| MusePublic/Qwen-Image-Edit MusePublic/Qwen-Image-Edit | ModelScope | 8K | Online | Yes | chat |
| OpenGVLab/InternVL3_5-241B-A28B OpenGVLab/InternVL3_5-241B-A28B | ModelScope | 8K | Online | Yes | chat |
| PaddlePaddle/ERNIE-4.5-21B-A3B-PT PaddlePaddle/ERNIE-4.5-21B-A3B-PT | ModelScope | 8K | Online | Yes | chat |
| PaddlePaddle/ERNIE-4.5-300B-A47B-PT PaddlePaddle/ERNIE-4.5-300B-A47B-PT | ModelScope | 8K | Online | Yes | chat |
| PaddlePaddle/ERNIE-4.5-VL-28B-A3B-PT PaddlePaddle/ERNIE-4.5-VL-28B-A3B-PT | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen-Image-Edit Qwen/Qwen-Image-Edit | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3-4B Qwen/Qwen3-4B | ModelScope | 8K | Online | Yes | chat |
| Shanghai_AI_Laboratory/Intern-S1 Shanghai_AI_Laboratory/Intern-S1 | ModelScope | 8K | Online | Yes | chat |
| Shanghai_AI_Laboratory/Intern-S2-Preview Shanghai_AI_Laboratory/Intern-S2-Preview | ModelScope | 8K | Online | Yes | chat |
| early-access/EA-29B-A4B early-access/EA-29B-A4B | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3-Coder-30B-A3B-Instruct Qwen/Qwen3-Coder-30B-A3B-Instruct | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3-VL-235B-A22B-Instruct Qwen/Qwen3-VL-235B-A22B-Instruct | ModelScope | 8K | Online | Yes | chat |
| meituan-longcat/LongCat-Flash-Lite meituan-longcat/LongCat-Flash-Lite | ModelScope | 8K | Online | Yes | chat |
| Shanghai_AI_Laboratory/Intern-S1-mini Shanghai_AI_Laboratory/Intern-S1-mini | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3-235B-A22B Qwen/Qwen3-235B-A22B | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3-Next-80B-A3B-Instruct Qwen/Qwen3-Next-80B-A3B-Instruct | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3-VL-8B-Thinking Qwen/Qwen3-VL-8B-Thinking | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3-VL-8B-Instruct Qwen/Qwen3-VL-8B-Instruct | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3-235B-A22B-Thinking-2507 Qwen/Qwen3-235B-A22B-Thinking-2507 | ModelScope | 8K | Online | Yes | chat |
| mistralai/Mistral-Large-Instruct-2407 mistralai/Mistral-Large-Instruct-2407 | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3-30B-A3B Qwen/Qwen3-30B-A3B | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3-Next-80B-A3B-Thinking Qwen/Qwen3-Next-80B-A3B-Thinking | ModelScope | 8K | Online | Yes | chat |
| PaddlePaddle/ERNIE-4.5-0.3B-PT PaddlePaddle/ERNIE-4.5-0.3B-PT | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3-30B-A3B-Thinking-2507 Qwen/Qwen3-30B-A3B-Thinking-2507 | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3-14B Qwen/Qwen3-14B | ModelScope | 8K | Online | Yes | chat |
| Qwen/Qwen3-8B Qwen/Qwen3-8B | ModelScope | 8K | Online | Yes | chat |
Developer Tools
Related Providers
View all →ModelScope FreeLLM Score free API access score
How we score → 70 /100
✅ Solid Choice — Strong in easy signup
Generosity Free limits and access terms
60 Access Signup and key availability
100 Model Breadth Free model coverage
55 Reliability Status and stability signals
55 Compatibility SDK and endpoint support
50 Quality Model capability signals
100 What is ModelScope?
Alibaba ModelScope — Qwen3.5, DeepSeek at 2,000 RPD free.
ModelScope is Alibaba's model hub and inference platform, providing free API access to Qwen, DeepSeek, and other models popular in the Chinese AI ecosystem. The free tier allows 2,000 requests/day total with a per-model cap of 500 RPD. Best latency for China-based users.
- 2,000 RPD total, 500 RPD per model
- Qwen3.5, DeepSeek available
- Best latency in China
- OpenAI-compatible endpoint
API Compatibility: Live-tested OpenAI-compatible Chat Completions and Responses
ModelScope Free Tier Limits & Pricing
Credit Card Not required
Phone Verification Unknown
Free Tier 47 free models online
Context Range 8K – 1.0M
Total Models 47 listed
API Compatibility Live-tested OpenAI-compatible Chat Completions and Responses
ModelScope API Setup Tutorials
Claude Code Environment variables and base URL setup Codex OpenAI-compatible config for local coding Gemini CLI Provider-specific API key routing notes
ModelScope is fully compatible with popular AI coding assistants like Cursor, Claude Code, and more. To see step-by-step API configuration instructions for your favorite tool, please visit our Global Configuration Guide →
ModelScope Model Use Cases
What ModelScope's free models are best for, based on aggregated model capabilities:
ModelScope Limitations & Caveats
- China-hosted — high latency outside Asia-Pacific
- 500 RPD per-model cap, 2,000 RPD total across all models
- Alibaba account or Chinese phone required
ModelScope FAQ
What's the difference between ModelScope and SiliconFlow?
ModelScope is Alibaba's official model hub with Qwen3.5 as the flagship. SiliconFlow is an independent platform. Both are China-hosted, but ModelScope has official Qwen models while SiliconFlow offers a broader mix including DeepSeek.
Does ModelScope have the latest Qwen models?
Yes — as Alibaba's own platform, ModelScope gets the latest Qwen releases (currently Qwen3.5) before they appear on other providers.
Can international users use ModelScope?
ModelScope requires an Alibaba account or Chinese phone for registration. International users may face difficulty signing up. Consider OpenRouter or Groq as alternatives for Qwen models.