算力API提供OpenAI兼容接口，用于将DeepSeek-R1和QwQ等AI模型集成到应用程序中。
算了么 API 目前提供 12 个大模型 API。
速度基准测试平均吞吐 25 tok/s。
api.suanli.cn| 模型 | 速度 | 延迟 | 测试数 |
|---|---|---|---|
best-free | 101.41 tok/s | 17.62s | 10 |
46.77 tok/s | 5.66s | 385 | |
45.16 tok/s | 20.80s | 65 | |
38.81 tok/s | 19.77s | 69 | |
35.00 tok/s | 1.78s | 10 | |
28.31 tok/s | 2.66s | 45 | |
27.71 tok/s | 26.05s | 6449 | |
20.72 tok/s | 1.47s | 5 | |
19.73 tok/s | 25.26s | 6542 |
| 模型 | 输入 ($/M) | 输出 ($/M) |
|---|---|---|
| $0.0000 | $0.0000 | |
| $0.0000 | $0.0000 | |
| $0.0000 | $0.0000 | |
| $0.0000 | $0.0000 | |
| $0.0000 | $0.0000 |
| 时间 | 模型 | 速度 | 延迟 |
|---|---|---|---|
| 04/12/2026, 11:13 | Qwen/QwQ-32B | 40.99 tok/s | 25.47s |
| 04/04/2026, 21:04 | Qwen/QwQ-32B | 84.50 tok/s | 9.00s |
| 03/30/2026, 16:26 | Qwen/Qwen3-VL-32B-Thinking | 25.55 tok/s | 31.90s |
| 03/24/2026, 19:16 | Qwen/QwQ-32B | 55.25 tok/s | 14.54s |
| 03/24/2026, 17:04 | Qwen/Qwen3-VL-32B-Thinking | 32.33 tok/s | 16.93s |
Seamee API provides an AI model relay for accessing multiple LLMs through OpenAI-compatible endpoints.
6 个共享模型A non-profit AI infrastructure offering free access to integrated large language models with privacy-focused, no-logging policies.
5 个共享模型
天絮 API provides an AI model relay service with multiple access points and stable connectivity.
5 个共享模型
A unified API gateway for large language models, offering access to multiple providers through standardized endpoints.
5 个共享模型Provides AI-generated content APIs for various applications, including text and image generation.
5 个共享模型
AicanAPI provides an enterprise-grade API management platform with high-performance architecture, security compliance, and cost optimization for business digital transformation.
5 个共享模型