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
15 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 | 808 ms |
|---|---|
| p95 TTFT | 4252 ms |
| Effective throughput | 117 tok/s n=4 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| nvidia/nemotron-3-ultra-550b-a55b | 691 ms | — | 100.00% | 3 provider_error |
1 |
| deepseek/deepseek-v4p1-flash | 743 ms | — | 100.00% | — | 2 |
| openai/gpt-oss-120b | 778 ms | — | 100.00% | — | 3 |
| nvidia/nemotron-3.5-lightning | 808 ms | — | 100.00% | — | 2 |
| minimax/minimax-m3 | 859 ms | 314 tok/s n=1 | 100.00% | 1 provider_error |
2 |
| z-ai/glm-5.3 | 974 ms | 178 tok/s n=1 | 100.00% | — | 2 |
| deepseek/deepseek-v4p1-flash-1017 | 1592 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k3 | 4252 ms | 56 tok/s n=2 | 100.00% | — | 1 |