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
26 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 | 1295 ms |
|---|---|
| p95 TTFT | 3078 ms |
| Effective throughput | 249 tok/s n=4 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| nvidia/nemotron-3.5-lightning | 706 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4p1-flash | 960 ms | — | 100.00% | — | 1 |
| minimax/minimax-m3 | 1025 ms | 301 tok/s n=2 | 100.00% | — | 2 |
| openai/gpt-oss-120b | 1044 ms | — | 100.00% | — | 3 |
| nvidia/nemotron-3-ultra-550b-a55b | 1155 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.3-flash | 1242 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k3 | 1256 ms | 149 tok/s n=1 | 100.00% | — | 2 |
| moonshotai/kimi-k3-fast | 1295 ms | — | 100.00% | — | 6 |
| qwen/qwen3.8-max | 1495 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4p1-flash-1017 | 1564 ms | — | 100.00% | — | 5 |
| z-ai/glm-5.3-fast | 1644 ms | — | 100.00% | — | 3 |
| z-ai/glm-5.3 | — | 196 tok/s n=1 | — | — | 0 |