OpenAI compatible API · Attested · Public status
Chutes performance
Measured TTFT, TTFB, throughput, uptime, and sampled model routes for Chutes.
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default
chutes
191 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 | 5445 ms |
|---|---|
| p95 TTFT | ms |
| p50 TTFB | ms |
| Throughput | — |
| Uptime | 91.10% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Throughput | Uptime | Config excluded | Samples |
|---|---|---|---|---|---|---|
| mistralai/mistral-nemo | 3110 ms | 3109 ms | — | 100.00% | — | 21 |
| qwen/qwen3.5-397b-a17b | 3375 ms | 3375 ms | — | 100.00% | — | 22 |
| qwen/qwen3.6-27b | 4194 ms | 4194 ms | — | 100.00% | — | 14 |
| google/gemma-4-31b-turbo | 4461 ms | 4461 ms | — | 100.00% | — | 16 |
| qwen/qwen3-32b | 4817 ms | 4817 ms | — | 100.00% | — | 21 |
| moonshotai/kimi-k2.6 | 5445 ms | 5445 ms | — | 87.50% | — | 16 |
| z-ai/glm-5.2 | 5592 ms | 5592 ms | — | 100.00% | — | 15 |
| minimax/minimax-m2.5 | 6690 ms | 6690 ms | — | 100.00% | — | 6 |
| qwen/qwen3-235b-a22b-thinking-2507 | 7010 ms | 7010 ms | — | 100.00% | — | 14 |
| z-ai/glm-5 | 7638 ms | 7638 ms | — | 50.00% | — | 6 |
| deepseek/deepseek-v3.2 | 7864 ms | 7864 ms | — | 92.86% | — | 14 |
| z-ai/glm-5.1 | 14505 ms | 14504 ms | — | 83.33% | — | 12 |
| moonshotai/kimi-k2.5 | 21224 ms | 21224 ms | — | 35.71% | — | 14 |