A unified LLM API gateway offering access to multiple AI models with competitive pricing and stability.
| Model | Speed | Latency | Tests |
|---|---|---|---|
| ai.dev/gemini-2.5-flash-lite | 405.65 t/s | 0.78s | 5 |
| gcli/gemini-2.5-flash | 332.90 t/s | 8.61s | 5 |
| openai/gpt-5-nano | 321.87 t/s | 19.88s | 5 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Sep 21, 06:29 PM | gcli/gemini-2.5-flash | 332.90 t/s | 8.61s |
| Sep 21, 06:27 PM | openai/gpt-5-nano | 321.87 t/s | 19.88s |
| Sep 21, 06:26 PM | ai.dev/gemini-2.5-flash-lite | 405.65 t/s | 0.78s |