提供免费的、兼容OpenAI的API接口，支持多个开源大语言模型，无需注册即可使用。
Performance Stats
Avg Speed
34.87t/s
Latency
1.60s
Total Tests
12,736
Models
50
| Model | Speed | Latency | Tests |
|---|---|---|---|
| deepseek/deepseek-v3 | 172.09 t/s | 2.64s | 90 |
| zhipu/glm-4.6v-flash | 111.38 t/s | 8.64s | 55 |
| zhipu/glm-4.6v-flash | 111.38 t/s | 8.64s | 55 |
| zhipu/glm-4.6v-flash | 111.38 t/s | 8.64s | 55 |
| zhipu/glm-4.1v-thinking-flash | 107.98 t/s | 7.61s | 85 |
| zhipu/glm-4.1v-thinking-flash | 107.98 t/s | 7.61s | 85 |
| qwen/qwen2.5-7b | 87.67 t/s | 1.48s | 135 |
| qwen/qwen2.5-7b | 87.67 t/s | 1.48s | 135 |
| deepseek/deepseek-v3-0324 | 82.12 t/s | 2.08s | 810 |
| openai/gpt-oss-20b | 58.49 t/s | 1.32s | 225 |
| zhipu/glm-4v-flash | 56.95 t/s | 0.78s | 75 |
| zhipu/glm-4-9b | 49.86 t/s | 0.58s | 45 |
| zhipu/glm-4.7-flash | 47.15 t/s | 22.04s | 75 |
| google/gemma-3-27b | 41.79 t/s | 2.85s | 260 |
| zhipu/glm-4-flash | 33.24 t/s | 0.95s | 7485 |
| meituan/longcat-flash-chat | 30.03 t/s | 2.06s | 30 |
| qwen/qwen3-8b | 28.77 t/s | 0.95s | 50 |
| zhipu/glm-4.5-flash | 28.75 t/s | 14.27s | 80 |
| zhipu/glm-4.5-flash | 28.75 t/s | 14.27s | 80 |
| google/gemini-2.0-flash-exp | 27.92 t/s | 0.54s | 470 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Mar 2, 06:16 PM | xiaomi/mimo-v2-flash | 0.00 t/s | 0.00s |
| Mar 2, 06:15 PM | google/gemini-2.0-flash-exp | 0.00 t/s | 0.00s |
| Mar 2, 06:14 PM | google/gemini-2.0-flash-exp | 0.00 t/s | 0.00s |
| Mar 2, 11:39 AM | zhipu/glm-4-flash | 30.27 t/s | 1.19s |
| Mar 2, 11:36 AM | zhipu/glm-4-flash | 31.37 t/s | 0.71s |
| Mar 2, 08:23 AM | zhipu/glm-4-flash | 29.29 t/s | 0.92s |
| Mar 2, 07:35 AM | zhipu/glm-4-flash | 30.89 t/s | 0.88s |
| Mar 2, 04:48 AM | deepseek/deepseek-v3-0324 | 0.00 t/s | 0.00s |
| Mar 2, 04:48 AM | qwen/qwen3-30b-a3b | 0.00 t/s | 0.00s |
| Mar 2, 04:47 AM | qwen/qwen2.5-7b | 90.28 t/s | 0.92s |