ModelScope provides model inference API access to a wide range of open-source AI models via OpenAI-compatible endpoints.
Categories
ModelScope offers 18 LLM API models.
Speed benchmark average: 58 tok/s.
ModelScope is an API aggregator, offering models from multiple vendors.
api-inference.modelscope.cnms-ens-1f4a9445-d0e7.api-inference.modelscope.cnms-ens-327b7543-e27c.api-inference.modelscope.cnms-ens-51815792-b22c.api-inference.modelscope.cn| Model | Speed | Latency | Tests |
|---|---|---|---|
158.96 tok/s | 0.96s | 10 | |
126.44 tok/s | 4.27s | 5 | |
123.38 tok/s | 6.13s | 5 | |
76.12 tok/s | 9.33s | 5 | |
70.69 tok/s | 13.55s | 5 | |
61.17 tok/s | 0.94s | 5 | |
52.75 tok/s | 7.49s | 5 | |
44.92 tok/s | 1.16s | 8 | |
43.96 tok/s | 0.91s | 5 | |
43.12 tok/s | 1.11s | 5 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| 03/30/2026, 04:09 | kgiser/gpu_gpt_5 | 26.05 tok/s | 1.11s |
| 03/30/2026, 03:24 | kgiser/gpu_gpt_5 | 30.59 tok/s | 1.17s |
| 03/30/2026, 03:16 | TeichAI/Qwen3-30B-A3B-Thinking-2507-Claude-4.5-Sonnet-High-Reasoning-Distill-GGUF | 13.07 tok/s | 2.17s |
| 03/30/2026, 02:41 | Qwen/QVQ-72B-Preview | 44.75 tok/s | 1.16s |
| 03/30/2026, 02:39 | Qwen/Qwen3-Coder-480B-A35B-Instruct | 61.17 tok/s | 0.94s |
Synapse is an OpenAI-compatible API relay service providing access to multiple AI models with unified endpoints.
14 shared modelsA non-profit AI infrastructure offering free access to integrated large language models with privacy-focused, no-logging policies.
14 shared modelsSeamee API provides an AI model relay for accessing multiple LLMs through OpenAI-compatible endpoints.
14 shared models
天絮 API provides an AI model relay service with multiple access points and stable connectivity.
14 shared models
A third-party OpenRouter-compatible API relay providing access to multiple AI models.
13 shared modelsProvides AI-generated content APIs for various applications, including text and image generation.
13 shared models