心流 (iFlow) 提供 AI 驱动的 API 服务，包括搜索、内容生成和模型访问，兼容 OpenAI API 格式。
心流 目前提供 7 个大模型 API。
速度基准测试平均吞吐 42 tok/s。
apis.iflow.cn排名基于社区提交的测试数据与定期健康探测，仅供参考，非官方数据。
| 模型 | 速度 | 延迟 | 测试数 |
|---|---|---|---|
42.97 tok/s | 0.96s | 17 | |
18.92 tok/s | 29.02s | 10 | |
| 时间 | 模型 | 速度 | 延迟 |
|---|---|---|---|
| Apr 5, 09:09 AM | deepseek-v3.2 | 38.75 tok/s | 0.69s |
| Mar 28, 09:42 AM | qwen3-235b-a22b-thinking-2507 | 20.69 tok/s | 24.55s |
| Mar 28, 09:39 AM | qwen3-235b | 44.84 tok/s | 17.21s |
| Mar 28, 08:57 AM | qwen3-235b | 30.05 tok/s | 18.09s |
| Mar 28, 08:06 AM | qwen3-coder-plus | 39.49 tok/s | 1.05s |
| Mar 28, 08:04 AM | deepseek-v3.2 | 40.80 tok/s | 0.70s |
| Mar 28, 07:57 AM | qwen3-235b-a22b-thinking-2507 | 17.15 tok/s | 33.48s |
| Mar 28, 07:56 AM | qwen3-coder-plus | 38.81 tok/s | 1.63s |
| Mar 10, 11:54 AM | qwen3-max | 33.20 tok/s | 1.62s |
| Mar 5, 08:42 AM | qwen3-coder-plus | 36.61 tok/s | 1.92s |
37.44 tok/s |
17.65s |
| 10 |
38.30 tok/s | 1.53s | 15 |
33.20 tok/s | 1.62s | 5 |
tstars2.0 | 94.52 tok/s | 0.37s | 10 |
24.36 tok/s | 0.39s | 10 |
api.bltcy.cn
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.
api.gpt.ge
Provides access to over 500 AI models via OpenAI protocol with pay-as-you-go pricing, fast response times, and transparent billing.
dashscope.aliyuncs.com
Alibaba Cloud DashScope provides AI model APIs including Qwen LLMs, vision, audio, and embedding models.
api.aaai.vip
API provider for AI services accessible via dedicated endpoints.
api.gptacg.top
A cost-effective API gateway offering discounted access to various large language models.
api.holdai.top
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.
