OpenAI compatible API · Attested · Public status
Venice performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for Venice on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Venicevenice
28 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 | 1972 ms |
|---|---|
| p95 TTFT | 16644 ms |
| Effective throughput | 51 tok/s n=4 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| google/gemma-4-uncensored | 724 ms | — | 100.00% | — | 2 |
| qwen/qwen3-coder-480b-a35b-instruct-turbo | 928 ms | — | 100.00% | — | 2 |
| qwen/qwen3-235b-a22b-instruct-2507 | 1051 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-1-flash | 1310 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-pro | 1481 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-9b | 1578 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-397b-a17b | 1705 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-v4-flash-0731-fast | 1876 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-pro-0423 | 1878 ms | 25 tok/s n=1 | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash-0731 | 1929 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2-7-code | 1972 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.2-3b | 2126 ms | — | 100.00% | — | 2 |
| qwen/qwen-3-6-plus | 2382 ms | — | 100.00% | — | 2 |
| z-ai/glm-5v-turbo | 2791 ms | — | 100.00% | — | 2 |
| z-ai/glm-4.7 | 2865 ms | — | 100.00% | — | 1 |
| qwen/qwen-3-7-max | 2914 ms | — | 100.00% | — | 2 |
| qwen/qwen-3-8-27b | 3803 ms | — | 100.00% | — | 2 |
| qwen/qwen3-235b-a22b-thinking-2507 | 3839 ms | 9 tok/s n=1 | 100.00% | — | 1 |
| qwen/qwen-3-7-plus | 4220 ms | — | 100.00% | — | 1 |
| minimax/minimax-m25 | 4763 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k3 | — | 76 tok/s n=1 | — | — | 0 |
| z-ai/glm-5.2 | — | 86 tok/s n=1 | — | — | 0 |