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
208 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 | 2916 ms |
|---|---|
| p95 TTFT | 5343 ms |
| p50 TTFB | 3015 ms |
| Effective throughput | — |
| Uptime | 91.35% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| openai/gpt-oss-20b | 2413 ms | 2413 ms | — | 100.00% | — | 2 |
| qwen/qwen-2.5-72b-instruct | 2435 ms | 2435 ms | — | 100.00% | — | 2 |
| sao10k/l3-8b-lunaris | 2435 ms | 2435 ms | — | 100.00% | — | 2 |
| qwen/qwen3-235b-a22b-fp8 | 2511 ms | 2511 ms | — | 100.00% | — | 4 |
| deepseek/deepseek-ocr-2 | 2525 ms | 2524 ms | — | 100.00% | — | 3 |
| meta-llama/llama-3.3-70b-instruct | 2559 ms | 2559 ms | — | 100.00% | — | 1 |
| meta-llama/llama-4-scout-17b-16e-instruct | 2560 ms | 2560 ms | — | 100.00% | — | 4 |
| qwen/qwen3.6-35b-a3b | 2565 ms | 2565 ms | — | 100.00% | — | 2 |
| meta-llama/llama-3.1-8b-instruct | 2569 ms | 2569 ms | — | 100.00% | — | 1 |
| sao10k/l31-70b-euryale-v2.2 | 2571 ms | 2571 ms | — | 100.00% | — | 3 |
| openai/gpt-oss-120b | 2616 ms | 2616 ms | — | 100.00% | — | 4 |
| meta-llama/llama-4-maverick-17b-128e-instruct-fp8 | 2619 ms | 2619 ms | — | 100.00% | — | 4 |
| qwen/qwen3-235b-a22b-instruct-2507 | 2632 ms | 2632 ms | — | 100.00% | — | 4 |
| qwen/qwen3.5-27b | 2644 ms | 2644 ms | — | 100.00% | — | 2 |
| zai-org/glm-4.7-flash | 2646 ms | 2646 ms | — | 100.00% | — | 2 |
| zai-org/glm-4.6v | 2659 ms | 2659 ms | — | 100.00% | — | 2 |
| inclusionai/ling-2.6-flash | 2671 ms | 2671 ms | — | 100.00% | — | 1 |
| qwen/qwen3-coder-480b-a35b-instruct | 2686 ms | 2686 ms | — | 100.00% | — | 3 |
| moonshotai/kimi-k2-instruct | 2700 ms | 2700 ms | — | 100.00% | — | 2 |
| google/gemma-3-27b-it | 2709 ms | 2709 ms | — | 100.00% | — | 4 |
| zai-org/autoglm-phone-9b-multilingual | 2807 ms | 2807 ms | — | 100.00% | — | 3 |
| moonshotai/kimi-k2-0905 | 2811 ms | 2811 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.5 | 2815 ms | 2800 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-r1-distill-llama-70b | 2820 ms | 2820 ms | — | 100.00% | — | 3 |
| qwen/qwen3-235b-a22b-thinking-2507 | 2831 ms | 2831 ms | — | 100.00% | — | 1 |
| inclusionai/ling-2.6-1t | 2838 ms | 2838 ms | — | 100.00% | — | 1 |
| kwaipilot/kat-coder-pro | 2863 ms | 2862 ms | — | 100.00% | — | 1 |
| zai-org/glm-4.6 | 2870 ms | 2870 ms | — | 100.00% | — | 5 |
| deepseek/deepseek-v4-flash-0731 | 2884 ms | 2883 ms | — | 100.00% | — | 2 |
| qwen/qwen3.6-27b | 2887 ms | 2887 ms | — | 100.00% | — | 4 |
| qwen/qwen3-omni-30b-a3b-instruct | 2890 ms | 2890 ms | — | 100.00% | — | 3 |
| qwen/qwen3-vl-235b-a22b-instruct | 2901 ms | 2901 ms | — | 100.00% | — | 4 |
| qwen/qwen3-next-80b-a3b-instruct | 2909 ms | 2909 ms | — | 100.00% | — | 1 |
| qwen/qwen3-vl-235b-a22b-thinking | 2911 ms | 2911 ms | — | 100.00% | — | 4 |
| qwen/qwen3.5-122b-a10b | 2916 ms | 2916 ms | — | 100.00% | — | 3 |
| zai-org/glm-4.5v | 2927 ms | 2926 ms | — | 100.00% | — | 2 |
| qwen/qwen3-omni-30b-a3b-thinking | 2952 ms | 2951 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-397b-a17b | 2976 ms | 2976 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-r1-turbo | 2996 ms | 2995 ms | — | 100.00% | — | 5 |
| deepseek/deepseek-ocr | 3016 ms | 3016 ms | — | 100.00% | — | 2 |
| qwen/qwen3.5-35b-a3b | 3017 ms | 3017 ms | — | 100.00% | — | 1 |
| minimax/minimax-m2.7 | 3026 ms | 3026 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v4-pro | 3034 ms | 3034 ms | — | 100.00% | — | 4 |
| deepseek/deepseek-r1-0528 | 3088 ms | 3087 ms | — | 100.00% | — | 1 |
| minimax/minimax-m2.5 | 3108 ms | 3108 ms | — | 100.00% | — | 1 |
| zai-org/glm-5 | 3126 ms | 3126 ms | — | 100.00% | — | 1 |
| inclusionai/ling-3.0-flash | 3157 ms | 3157 ms | — | 100.00% | — | 5 |
| minimax/minimax-m2.1 | 3201 ms | 3201 ms | — | 100.00% | — | 4 |
| minimaxai/minimax-m1-80k | 3247 ms | 3247 ms | — | 100.00% | — | 4 |
| moonshotai/kimi-k2.7-code | 3337 ms | 3337 ms | — | 100.00% | — | 2 |
| minimax/minimax-m2.5-highspeed | 3340 ms | 3340 ms | — | 100.00% | — | 3 |
| google/gemma-4-26b-a4b-it | 3366 ms | 3366 ms | — | 100.00% | — | 3 |
| qwen/qwen3-max | 3384 ms | 3384 ms | — | 100.00% | — | 2 |
| baidu/ernie-4.5-vl-424b-a47b | 3419 ms | 3419 ms | — | 100.00% | — | 4 |
| deepseek/deepseek-v3.2 | 3426 ms | 3426 ms | — | 100.00% | — | 2 |
| zai-org/glm-4.7 | 3431 ms | 3431 ms | — | 100.00% | — | 4 |
| deepseek/deepseek-v3-turbo | 3688 ms | 3687 ms | — | 100.00% | — | 1 |
| zai-org/glm-5.1 | 3712 ms | 3711 ms | — | 100.00% | — | 4 |
| qwen/qwen3-coder-next | 3734 ms | 3734 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-3-nano-30b-a3b | 3739 ms | 3739 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v3.1 | 3833 ms | 3833 ms | — | 100.00% | — | 4 |
| deepseek/deepseek-v4-flash | 3841 ms | 3841 ms | — | 100.00% | — | 3 |
| tencent/hy3 | 3843 ms | 3843 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v3-0324 | 3861 ms | 3861 ms | — | 100.00% | — | 1 |
| stepfun/step-3.7-flash | 3964 ms | 3963 ms | — | 100.00% | — | 4 |
| inclusionai/ring-2.6-1t | 3981 ms | 3981 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v3.1-terminus | 4140 ms | 4139 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.2 | 4681 ms | 4681 ms | — | 100.00% | — | 3 |
| mindai/macaron-v1-venti | 5936 ms | 5935 ms | — | 100.00% | — | 3 |
| google/gemma-4-31b-it | 2885 ms | 2885 ms | — | 75.00% | — | 4 |
| xiaomimimo/mimo-v2.5-pro | 4510 ms | 4510 ms | — | 66.67% | — | 3 |
| mistralai/mistral-nemo | 8210 ms | 8210 ms | — | 66.67% | — | 3 |
| zai-org/glm-4.5-air | 2898 ms | 2898 ms | — | 50.00% | — | 2 |
| microsoft/wizardlm-2-8x22b | 2960 ms | 2959 ms | — | 50.00% | — | 2 |
| baichuan/baichuan-m2-32b | — | — | — | 0.00% | — | 3 |
| baidu/cobuddy | — | — | — | 0.00% | — | 2 |
| baidu/ernie-4.5-21B-a3b | — | — | — | 0.00% | — | 2 |
| google/gemma-3-12b-it | — | — | — | 0.00% | — | 4 |
| mindai/macaron-v1-tall | — | — | — | 0.00% | — | 2 |