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
209 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 | 2823 ms |
|---|---|
| p95 TTFT | 8523 ms |
| p50 TTFB | 2713 ms |
| Effective throughput | — |
| Uptime | 98.09% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| z-ai/glm-5.2-fast | 2405 ms | 2405 ms | — | 100.00% | — | 18 |
| openai/gpt-oss-20b | 2437 ms | 2437 ms | — | 100.00% | — | 23 |
| openai/gpt-oss-120b | 2469 ms | 2469 ms | — | 100.00% | — | 20 |
| deepseek/deepseek-v4-pro | 2535 ms | 2535 ms | — | 100.00% | — | 24 |
| moonshotai/kimi-k2.6 | 2652 ms | 2652 ms | — | 100.00% | — | 13 |
| deepseek/deepseek-v4-flash | 2823 ms | 2823 ms | — | 100.00% | — | 25 |
| z-ai/glm-5.2 | 3074 ms | 3074 ms | — | 100.00% | — | 14 |
| minimax/minimax-m3 | 3300 ms | 3300 ms | — | 100.00% | — | 20 |
| moonshotai/kimi-k2.7-code | 3591 ms | 3591 ms | — | 100.00% | — | 12 |
| deepseek/deepseek-v4-flash-0731 | 4854 ms | 4854 ms | — | 94.44% | — | 18 |
| moonshotai/kimi-k3 | 3270 ms | 3269 ms | — | 86.36% | — | 22 |