OpenAI compatible API · Attested · Public status
Fireworks AI performance
Review measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Fireworks AI on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Fireworks AIfireworks
70 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 | 2259 ms |
|---|---|
| p95 TTFT | 7775 ms |
| p50 TTFB | 2535 ms |
| Effective throughput | 49 tok/s n=14 |
| Uptime | 98.57% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| moonshotai/kimi-k2.6 | 881 ms | 881 ms | 46 tok/s n=2 | 100.00% | — | 7 |
| openai/gpt-oss-20b | 1081 ms | 1081 ms | — | 100.00% | — | 5 |
| z-ai/glm-5.2-fast | 1258 ms | 1258 ms | 59 tok/s n=2 | 100.00% | — | 6 |
| openai/gpt-oss-120b | 1509 ms | 1509 ms | 98 tok/s n=2 | 100.00% | — | 5 |
| deepseek/deepseek-v4-pro | 1867 ms | 1867 ms | 36 tok/s n=1 | 100.00% | — | 11 |
| z-ai/glm-5.2 | 2259 ms | 2259 ms | 36 tok/s n=1 | 100.00% | — | 6 |
| moonshotai/kimi-k3 | 2571 ms | 2571 ms | 44 tok/s n=1 | 100.00% | — | 7 |
| deepseek/deepseek-v4-flash-0731 | 2891 ms | 2891 ms | 44 tok/s n=2 | 100.00% | — | 9 |
| deepseek/deepseek-v4-flash | 4038 ms | 4037 ms | 63 tok/s n=1 | 100.00% | — | 1 |
| moonshotai/kimi-k2.7-code | 5693 ms | 5693 ms | 51 tok/s n=1 | 100.00% | — | 9 |
| minimax/minimax-m3 | 3921 ms | 3920 ms | 67 tok/s n=1 | 75.00% | — | 4 |