OpenAI compatible API · Attested · Public status
Fireworks AI performance
Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Fireworks AI.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Fireworks AIfireworks
34 samples
Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.
| p50 TTFT | 1551 ms |
|---|---|
| p95 TTFT | 9446 ms |
| p50 TTFB | 1586 ms |
| Effective throughput | — |
| Uptime | 97.06% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| openai/gpt-oss-120b | 1120 ms | 1120 ms | — | 100.00% | — | 2 |
| openai/gpt-oss-20b | 1170 ms | 1170 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.6 | 1252 ms | 1252 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.2-fast | 1277 ms | 1277 ms | — | 100.00% | — | 8 |
| moonshotai/kimi-k2.7-code | 1378 ms | 1378 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.2 | 1551 ms | 1551 ms | — | 100.00% | — | 5 |
| minimax/minimax-m3 | 1688 ms | 1688 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v4-pro | 1724 ms | 1724 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash | 1773 ms | 1773 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-v4-flash-0731 | 7376 ms | 7376 ms | — | 100.00% | — | 3 |
| moonshotai/kimi-k3 | 1815 ms | 1815 ms | — | 80.00% | — | 5 |