OpenAI compatible API · Attested · Public status
Chutes performance
Review measured TTFT, 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
18 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 | 6255 ms |
|---|---|
| p95 TTFT | 13033 ms |
| Effective throughput | 28 tok/s n=3 |
| Uptime | 55.56% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| google/gemma-4-31b-turbo | 6227 ms | — | 100.00% | — | 2 |
| qwen/qwen3.5-397b-a17b | 6255 ms | — | 100.00% | — | 3 |
| z-ai/glm-5.1 | 8369 ms | — | 100.00% | — | 2 |
| qwen/qwen3.6-27b | 9400 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.2 | 13033 ms | 13 tok/s n=1 | 100.00% | — | 1 |
| deepseek/deepseek-v3.2 | — | — | — | 1 provider_error |
0 |
| mistralai/mistral-nemo | — | — | 0.00% | — | 4 |
| moonshotai/kimi-k2.6 | — | 28 tok/s n=2 | — | — | 0 |
| moonshotai/kimi-k3 | — | — | 0.00% | — | 2 |
| nvidia/nemotron-3-nano-omni | — | — | 0.00% | — | 1 |
| qwen/qwen3-32b | — | — | 0.00% | 3 provider_error |
1 |