OpenAI compatible API · Attested · Public status
Venice performance
Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Venice.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
venice
209 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 | 2876 ms |
|---|---|
| p95 TTFT | 6616 ms |
| p50 TTFB | 2968 ms |
| Effective throughput | — |
| Uptime | 97.61% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| qwen/qwen3.5-9b | 2514 ms | 2513 ms | — | 100.00% | — | 16 |
| z-ai/glm-5.2 | 2578 ms | 2578 ms | — | 100.00% | — | 18 |
| qwen/qwen3.6-27b | 2633 ms | 2633 ms | — | 100.00% | — | 13 |
| qwen/qwen3-235b-a22b-thinking-2507 | 2697 ms | 2697 ms | — | 100.00% | — | 14 |
| z-ai/glm-4.7 | 2876 ms | 2876 ms | — | 100.00% | — | 24 |
| z-ai/glm-4.6 | 2934 ms | 2934 ms | — | 100.00% | — | 14 |
| z-ai/glm-5.1 | 3037 ms | 3036 ms | — | 100.00% | — | 16 |
| qwen/qwen3.5-397b-a17b | 3233 ms | 3233 ms | — | 100.00% | — | 17 |
| z-ai/glm-5 | 3396 ms | 3396 ms | — | 100.00% | — | 17 |
| z-ai/glm-5v-turbo | 3980 ms | 3980 ms | — | 100.00% | — | 16 |
| z-ai/glm-5-turbo | 3734 ms | 3734 ms | — | 93.75% | — | 16 |
| z-ai/glm-4.7-flash | 2694 ms | 2694 ms | — | 85.71% | — | 28 |