OpenAI compatible API · Attested · Public status
Chutes performance
Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Chutes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
chutes
57 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 | 2855 ms |
|---|---|
| p95 TTFT | 15854 ms |
| p50 TTFB | 2887 ms |
| Effective throughput | 34 tok/s n=3 |
| Uptime | 98.25% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| qwen/qwen3-235b-a22b-thinking-2507 | 2171 ms | 2171 ms | — | 100.00% | — | 3 |
| mistralai/mistral-nemo | 2282 ms | 2282 ms | — | 100.00% | 1 router_error |
6 |
| z-ai/glm-5.1 | 2386 ms | 2385 ms | — | 100.00% | — | 5 |
| qwen/qwen3.6-27b | 2600 ms | 2599 ms | — | 100.00% | — | 3 |
| moonshotai/kimi-k2.6 | 2855 ms | 2855 ms | 34 tok/s n=2 | 100.00% | — | 6 |
| google/gemma-4-31b-turbo | 3484 ms | 3484 ms | — | 100.00% | — | 6 |
| qwen/qwen3-32b | 3504 ms | 3503 ms | — | 100.00% | — | 9 |
| deepseek/deepseek-v3.2 | 3517 ms | 3517 ms | — | 100.00% | — | 7 |
| z-ai/glm-5.2 | 4049 ms | 4049 ms | 21 tok/s n=1 | 100.00% | — | 5 |
| qwen/qwen3.5-397b-a17b | 2475 ms | 2475 ms | — | 85.71% | — | 7 |