OpenAI compatible API · Attested · Public status
Chutes performance
Review measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Chutes on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Chuteschutes
54 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 | 2033 ms |
|---|---|
| p95 TTFT | 9581 ms |
| p50 TTFB | 2407 ms |
| Effective throughput | 27 tok/s n=2 |
| Uptime | 90.74% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| qwen/qwen3.6-27b | 1696 ms | 1696 ms | — | 100.00% | — | 6 |
| mistralai/mistral-nemo | 1850 ms | 1850 ms | — | 100.00% | — | 9 |
| qwen/qwen3.5-397b-a17b | 2033 ms | 2032 ms | — | 100.00% | — | 7 |
| qwen/qwen3-235b-a22b-thinking-2507 | 2181 ms | 2181 ms | — | 100.00% | — | 8 |
| google/gemma-4-31b-turbo | 2457 ms | 2457 ms | — | 100.00% | — | 5 |
| moonshotai/kimi-k2.6 | 3657 ms | 3657 ms | 27 tok/s n=2 | 100.00% | — | 5 |
| deepseek/deepseek-v3.2 | 3783 ms | 3783 ms | — | 100.00% | — | 3 |
| qwen/qwen3-32b | 17002 ms | 17002 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.1 | 2316 ms | 2316 ms | — | 80.00% | — | 5 |
| z-ai/glm-5.2 | 1438 ms | 1438 ms | — | 20.00% | — | 5 |