A3 provides AI model APIs for developers, offering scalable and accessible AI capabilities.
| Model | Speed | Latency | Tests |
|---|---|---|---|
| groq/compound-mini | 477.57 t/s | 0.89s | 5 |
| kimi-k2-instruct-0905 | 226.90 t/s | 0.29s | 10 |
| gemini-3-flash-preview | 161.96 t/s | 5.57s | 5 |
| glm-4.7-flash | 50.25 t/s | 20.72s | 5 |
| claude-sonnet-4-5 | 45.99 t/s | 1.35s | 5 |
| gpt-5.3-codex | 45.96 t/s | 2.04s | 5 |
| gpt-5.2 | 44.55 t/s | 1.72s | 5 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Feb 7, 11:34 AM | gpt-5.3-codex | 45.96 t/s | 2.04s |
| Feb 7, 11:32 AM | claude-sonnet-4-5 | 45.99 t/s | 1.35s |
| Feb 7, 11:30 AM | kimi-k2-instruct-0905 | 223.21 t/s | 0.29s |
| Feb 7, 11:29 AM | kimi-k2-instruct-0905 | 230.60 t/s | 0.28s |
| Feb 6, 04:18 PM | groq/compound-mini | 477.57 t/s | 0.89s |
| Feb 6, 03:59 PM | gpt-5.2 | 44.55 t/s | 1.72s |
| Feb 6, 03:57 PM | gemini-3-flash-preview | 161.96 t/s | 5.57s |
| Feb 6, 03:53 PM | glm-4.7-flash | 50.25 t/s | 20.72s |