OpenAI compatible API · Attested · Public status
Novita AI performance
Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Novita AI.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
novita
61 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 | 2018 ms |
|---|---|
| p95 TTFT | 7456 ms |
| p50 TTFB | 2782 ms |
| Effective throughput | 39 tok/s n=16 |
| Uptime | 91.80% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| zai-org/autoglm-phone-9b-multilingual | 673 ms | 673 ms | — | 100.00% | — | 2 |
| meta-llama/llama-3.1-8b-instruct | 807 ms | 806 ms | — | 100.00% | — | 2 |
| qwen/qwen-mt-plus | 820 ms | 820 ms | — | 100.00% | — | 1 |
| qwen/qwen3-vl-30b-a3b-instruct | 892 ms | 892 ms | — | 100.00% | — | 2 |
| qwen/qwen3-coder-30b-a3b-instruct | 932 ms | 932 ms | — | 100.00% | — | 2 |
| qwen/qwen3-omni-30b-a3b-instruct | 1038 ms | 1038 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-r1-distill-llama-70b | 1093 ms | 1093 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.5 | 1243 ms | 1243 ms | — | 100.00% | — | 1 |
| google/gemma-4-26b-a4b-it | 1347 ms | 1347 ms | — | 100.00% | — | 2 |
| qwen/qwen3-235b-a22b-thinking-2507 | 1466 ms | 1466 ms | — | 100.00% | — | 1 |
| minimax/minimax-m2.7 | 1510 ms | 1509 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.7-code | 1585 ms | 1585 ms | 39 tok/s n=1 | 100.00% | — | 2 |
| qwen/qwen3-235b-a22b-fp8 | 1658 ms | 1658 ms | — | 100.00% | — | 2 |
| qwen/qwen3-235b-a22b-instruct-2507 | 1786 ms | 1786 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-35b-a3b | 1815 ms | 1814 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-v3-0324 | 1849 ms | — | — | 100.00% | — | 1 |
| qwen/qwen3.5-27b | 1882 ms | 1881 ms | — | 100.00% | — | 1 |
| openai/gpt-oss-20b | 1913 ms | 1912 ms | — | 100.00% | — | 2 |
| qwen/qwen3.5-122b-a10b | 2018 ms | 2017 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-3-nano-30b-a3b | 2124 ms | 2124 ms | — | 100.00% | — | 1 |
| qwen/qwen3-omni-30b-a3b-thinking | 2129 ms | 2129 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-r1-0528 | 2206 ms | 2206 ms | — | 100.00% | — | 2 |
| minimax/minimax-m2.5 | 2262 ms | 2262 ms | — | 100.00% | — | 1 |
| qwen/qwen3-vl-235b-a22b-thinking | 2523 ms | 2523 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v3.1-terminus | 2783 ms | 2782 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v3.2 | 2836 ms | 2836 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash | 2953 ms | 2952 ms | 67 tok/s n=1 | 100.00% | — | 1 |
| openai/gpt-oss-120b | 3146 ms | 3146 ms | 21 tok/s n=1 | 100.00% | — | 1 |
| tencent/hy3 | 3205 ms | 3205 ms | 76 tok/s n=1 | 100.00% | — | 1 |
| inclusionai/ring-2.6-1t | 3358 ms | 3357 ms | — | 100.00% | — | 3 |
| zai-org/glm-4.6 | 3467 ms | 3467 ms | — | 100.00% | — | 1 |
| minimaxai/minimax-m1-80k | 3494 ms | 3494 ms | — | 100.00% | — | 1 |
| xiaomimimo/mimo-v2.5-pro | 3510 ms | 3510 ms | — | 100.00% | — | 1 |
| qwen/qwen3.6-35b-a3b | 3700 ms | 3700 ms | — | 100.00% | — | 1 |
| baidu/ernie-4.5-vl-424b-a47b | 3713 ms | 3712 ms | — | 100.00% | — | 1 |
| zai-org/glm-4.6v | 3740 ms | 3740 ms | — | 100.00% | — | 1 |
| minimax/minimax-m3 | 3856 ms | 3856 ms | 83 tok/s n=1 | 100.00% | — | 1 |
| inclusionai/ling-2.6-1t | 3869 ms | 3869 ms | — | 100.00% | — | 1 |
| microsoft/wizardlm-2-8x22b | 3877 ms | 3876 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-397b-a17b | 4010 ms | 4010 ms | — | 100.00% | — | 2 |
| qwen/qwen3.7-max | 4141 ms | 4141 ms | — | 100.00% | — | 1 |
| qwen/qwen-2.5-72b-instruct | 7456 ms | 7456 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k3 | 19657 ms | 19657 ms | 24 tok/s n=2 | 100.00% | — | 1 |
| baidu/cobuddy | — | — | — | 0.00% | — | 1 |
| deepseek/deepseek-v4-flash-0731 | — | — | 34 tok/s n=1 | — | — | 0 |
| deepseek/deepseek-v4-pro | — | — | 54 tok/s n=2 | — | — | 0 |
| google/gemma-3-12b-it | — | — | — | 0.00% | — | 2 |
| google/gemma-4-31b-it | — | — | 40 tok/s n=2 | — | — | 0 |
| inclusionai/ling-2.6-flash | — | — | — | 0.00% | — | 1 |
| inclusionai/ling-3.0-flash | — | — | 68 tok/s n=1 | — | — | 0 |
| mindai/macaron-v1-tall | — | — | — | 0.00% | — | 1 |
| mindai/macaron-v1-venti | — | — | 12 tok/s n=1 | — | — | 0 |
| z-ai/glm-5.2 | — | — | 25 tok/s n=2 | — | — | 0 |