OpenAI compatible API · Attested · Public status
Fireworks AI performance
Review measured TTFT, 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
359 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 | 1676 ms |
|---|---|
| p95 TTFT | 26245 ms |
| Effective throughput | 59 tok/s n=7 |
| Uptime | 99.72% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| minimax/minimax-m3 | 1676 ms | — | 100.00% | — | 150 |
| z-ai/glm-5.3 | 23042 ms | — | 94.44% | — | 18 |
| deepseek/deepseek-v4-flash-0731 | 23441 ms | 12 tok/s n=1 | 100.00% | — | 12 |
| z-ai/glm-5.3-fast | 832 ms | — | 100.00% | — | 2 |
| meta-models/muse-glimmer-30b | 879 ms | — | 100.00% | — | 1 |
| openai/gpt-oss-120b | 1043 ms | 90 tok/s n=1 | 100.00% | — | 3 |
| nvidia/nemotron-3-ultra-550b-a55b | 1108 ms | — | 100.00% | — | 2 |
| qwen/qwen3.8-max | 1501 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.6 | 1586 ms | 48 tok/s n=1 | 100.00% | — | 1 |
| deepseek/deepseek-v4-pro-0813 | 1595 ms | 59 tok/s n=1 | 100.00% | — | 1 |
| z-ai/glm-5.3-flash | 1658 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k3-fast | 1661 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-v4p1-flash | 1696 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.7-code | 3155 ms | 87 tok/s n=1 | 100.00% | — | 1 |
| moonshotai/kimi-k3 | 4072 ms | 54 tok/s n=1 | 100.00% | — | 2 |
| z-ai/glm-5.2-fast | — | — | 100.00% | — | 159 |
| z-ai/glm-5.2 | — | 82 tok/s n=1 | — | — | 0 |