算了么 API

Name: 算了么 API
Rating: 1.2 (13580 reviews)

Provides OpenAI-compatible API access to open-source AI models like DeepSeek and QwQ, powered by shared idle computing resources.

算了么 API offers 12 LLM API models.

Speed benchmark average: 25 tok/s.

Avg Speed24.60 tok/s

Latency24.93 s

Total Tests13580

Models9

Updated4/18/2026

Created At8/13/2025

Online SinceApr 16, 2026, 02:23 AM

TaskData Export

Recent Test Records

Time	Model	Speed	Latency
Apr 12, 11:13 AM	Qwen/QwQ-32B	40.99 tok/s	25.47s
Apr 4, 09:04 PM	Qwen/QwQ-32B	84.50 tok/s	9.00s
Mar 30, 04:26 PM	Qwen/Qwen3-VL-32B-Thinking	25.55 tok/s	31.90s
Mar 24, 07:16 PM	Qwen/QwQ-32B	55.25 tok/s	14.54s
Mar 24, 05:04 PM	Qwen/Qwen3-VL-32B-Thinking	32.33 tok/s	16.93s
Mar 23, 01:58 AM	Qwen/Qwen3-VL-32B-Thinking	40.82 tok/s	13.97s
Mar 21, 04:26 PM	Qwen/QwQ-32B	47.27 tok/s	14.66s
Mar 19, 07:00 AM	Qwen/QwQ-32B	42.43 tok/s	21.92s
Mar 17, 02:44 PM	Qwen/QwQ-32B	40.05 tok/s	24.31s
Mar 17, 01:54 PM	Qwen/Qwen3-VL-32B-Thinking	50.67 tok/s	11.74s