A unified LLM API gateway offering access to multiple AI models with competitive pricing and stability.
| Model | Speed | Latency | Tests |
|---|---|---|---|
| deepseek-ai/DeepSeek-V3.1 | 37419.93 t/s | 3.04s | 15 |
| deepseek-ai/DeepSeek-V3.1 | 37419.93 t/s | 3.04s | 15 |
| gpt-oss-120b | 365.50 t/s | 2.12s | 5 |
| minimax/minimax-m2 | 65.00 t/s | 11.36s | 5 |
| gpt-4.1-mini | 61.27 t/s | 6.99s | 5 |
| google/gemma-3-27b | 37.94 t/s | 1.89s | 5 |
| Qwen/Qwen2.5-Coder-7B-Instruct | 26.91 t/s | 0.72s | 5 |
| Qwen/Qwen2.5-Coder-7B-Instruct | 26.91 t/s | 0.72s | 5 |
| Qwen/Qwen2.5-Coder-7B-Instruct | 26.91 t/s | 0.72s | 5 |
| gemini-2.5-flash-lite | 0.00 t/s | 1.52s | 5 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Nov 7, 06:11 AM | google/gemma-3-27b | 37.94 t/s | 1.89s |
| Nov 7, 06:07 AM | minimax/minimax-m2 | 65.00 t/s | 11.36s |
| Nov 6, 03:16 PM | deepseek-ai/DeepSeek-V3.1 | 50.41 t/s | 5.12s |
| Nov 6, 06:08 AM | deepseek-ai/DeepSeek-V3.1 | 112133.33 t/s | 1.99s |
| Nov 6, 06:05 AM | gpt-4.1-mini | 61.27 t/s | 6.99s |
| Nov 6, 06:05 AM | gemini-2.5-flash-lite | 0.00 t/s | 1.52s |
| Nov 6, 06:02 AM | gpt-oss-120b | 365.50 t/s | 2.12s |
| Nov 6, 05:58 AM | deepseek-ai/DeepSeek-V3.1 | 76.05 t/s | 2.01s |
| Nov 6, 05:55 AM | Qwen/Qwen2.5-Coder-7B-Instruct | 26.91 t/s | 0.72s |