心流 (iFlow) provides AI-powered API services including search, content generation, and model access through OpenAI-compatible endpoints.
Categories
心流 offers 8 LLM API models.
Speed benchmark average: 41 tok/s.
apis.iflow.cn| Model | Speed | Latency | Tests |
|---|---|---|---|
tstars2.0 | 94.52 tok/s | 0.37s | 10 |
42.97 tok/s | 0.96s | 17 | |
38.30 tok/s | 1.53s | 15 | |
37.44 tok/s | 17.65s | 10 | |
33.20 tok/s | 1.62s | 5 | |
25.60 tok/s | 0.48s | 5 | |
24.36 tok/s | 0.39s | 10 | |
18.92 tok/s | 29.02s | 10 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| 04/05/2026, 09:09 | deepseek-v3.2 | 38.75 tok/s | 0.69s |
| 03/28/2026, 09:42 | qwen3-235b-a22b-thinking-2507 | 20.69 tok/s | 24.55s |
| 03/28/2026, 09:39 | qwen3-235b | 44.84 tok/s | 17.21s |
| 03/28/2026, 08:57 | qwen3-235b | 30.05 tok/s | 18.09s |
| 03/28/2026, 08:06 | qwen3-coder-plus | 39.49 tok/s | 1.05s |
Provides access to over 500 AI models via OpenAI protocol with pay-as-you-go pricing, fast response times, and transparent billing.
7 shared models
A cost-effective API gateway offering discounted access to various large language models.
7 shared models
Alibaba Cloud DashScope provides AI model APIs including Qwen LLMs, vision, audio, and embedding models.
7 shared modelsAPI provider for AI services accessible via dedicated endpoints.
7 shared models
柏拉图AI (api.bltcy.cn) is a multi-dimensional API integration platform providing access to over 600 AI models, serving as an alternate endpoint.
7 shared models
毫秒API provides a stable, high-bandwidth API forwarding service for OpenAI-compatible models, including GPT, Claude, and Midjourney, with global server deployment and transparent pricing.
7 shared models