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。
Categories
| Model | Speed | Latency | Tests |
|---|---|---|---|
| deepseek/deepseek-v3 | 172.09 t/s | 2.64s | 90 |
| zhipu/glm-4.1v-thinking-flash | 107.62 t/s | 7.05s | 115 |
| zhipu/glm-4.1v-thinking-flash | 107.62 t/s | 7.05s | 115 |
| zhipu/glm-4.6v-flash | 102.10 t/s | 7.92s | 60 |
| zhipu/glm-4.6v-flash | 102.10 t/s | 7.92s | 60 |
| zhipu/glm-4.6v-flash | 102.10 t/s | 7.92s | 60 |
| qwen/qwen2.5-7b | 87.58 t/s | 1.39s | 150 |
| qwen/qwen2.5-7b | 87.58 t/s | 1.39s | 150 |
| deepseek/deepseek-v3-0324 | 76.46 t/s | 1.93s | 870 |
| zhipu/glm-4v-flash | 56.62 t/s | 0.69s | 100 |
| openai/gpt-oss-20b | 56.00 t/s | 1.26s | 235 |
| zhipu/glm-4-9b | 50.94 t/s | 0.55s | 60 |
| zhipu/glm-4.7-flash | 49.32 t/s | 21.91s | 105 |
| google/gemma-3-27b | 37.75 t/s | 2.55s | 295 |
| zhipu/glm-4-flash | 32.67 t/s | 0.95s | 8330 |
| meituan/longcat-flash-chat | 30.03 t/s | 2.06s | 30 |
| zhipu/glm-4.5-flash | 28.75 t/s | 14.27s | 80 |
| zhipu/glm-4.5-flash | 28.75 t/s | 14.27s | 80 |
| deepseek/deepseek-r1 | 27.87 t/s | 4.85s | 145 |
| qwen/qwen3-8b | 27.20 t/s | 0.86s | 75 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Mar 12, 07:45 AM | xiaomi/mimo-v2-flash | 0.00 t/s | 0.00s |
| Mar 12, 05:40 AM | zhipu/glm-4.1v-thinking-flash | 117.01 t/s | 4.98s |
| Mar 12, 05:38 AM | zhipu/glm-4-flash | 28.25 t/s | 0.91s |
| Mar 12, 05:30 AM | zhipu/glm-4.7-flash | 43.78 t/s | 23.87s |
| Mar 12, 05:26 AM | zhipu/glm-4-flash | 24.00 t/s | 0.94s |
| Mar 12, 05:25 AM | deepseek/deepseek-v3-0324 | 0.00 t/s | 0.00s |
| Mar 12, 05:25 AM | deepseek/deepseek-r1-0528 | 0.00 t/s | 0.00s |
| Mar 12, 05:23 AM | zhipu/glm-4-flash | 24.72 t/s | 0.98s |
| Mar 12, 04:37 AM | zhipu/glm-4-flash | 29.40 t/s | 1.23s |
| Mar 12, 04:37 AM | zhipu/glm-4-flash | 25.74 t/s | 0.92s |