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
50 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 | 3575 ms |
|---|---|
| p95 TTFT | 15854 ms |
| p50 TTFB | 2958 ms |
| Effective throughput | 31 tok/s n=3 |
| Uptime | 96.00% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| qwen/qwen3-235b-a22b-thinking-2507 | 1379 ms | 1379 ms | — | 100.00% | — | 4 |
| mistralai/mistral-nemo | 1859 ms | 1859 ms | — | 100.00% | — | 6 |
| moonshotai/kimi-k2.6 | 2025 ms | 2025 ms | 34 tok/s n=1 | 100.00% | — | 6 |
| z-ai/glm-5.1 | 2027 ms | 2027 ms | — | 100.00% | — | 4 |
| qwen/qwen3.6-27b | 2600 ms | 2599 ms | — | 100.00% | — | 1 |
| qwen/qwen3-32b | 3575 ms | 3575 ms | — | 100.00% | — | 9 |
| z-ai/glm-5.2 | 3914 ms | 3914 ms | 31 tok/s n=2 | 100.00% | — | 4 |
| deepseek/deepseek-v3.2 | 4166 ms | 4166 ms | — | 100.00% | — | 7 |
| google/gemma-4-31b-turbo | 4308 ms | 4308 ms | — | 83.33% | — | 6 |
| qwen/qwen3.5-397b-a17b | 2361 ms | 2361 ms | — | 66.67% | — | 3 |