OpenAI compatible API · Attested · Public status
Novita AI performance
Review measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Novita AI on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Novita AInovita
47 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 | 1859 ms |
|---|---|
| p95 TTFT | 4327 ms |
| p50 TTFB | 1858 ms |
| Effective throughput | 62 tok/s n=20 |
| Uptime | 89.36% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| meta-llama/llama-3.3-70b-instruct | 833 ms | 833 ms | — | 100.00% | — | 3 |
| google/gemma-4-31b-it | 949 ms | 949 ms | 12 tok/s n=1 | 100.00% | — | 2 |
| deepseek/deepseek-ocr-2 | 966 ms | 966 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2-instruct | 1070 ms | 1070 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash-0731 | 1222 ms | 1222 ms | 86 tok/s n=2 | 100.00% | — | 2 |
| zai-org/glm-5 | 1256 ms | 1256 ms | — | 100.00% | — | 1 |
| zai-org/glm-4.5v | 1338 ms | 1338 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-pro | 1432 ms | 1432 ms | 60 tok/s n=1 | 100.00% | — | 1 |
| mistralai/mistral-nemo | 1521 ms | 1520 ms | — | 100.00% | — | 1 |
| minimax/minimax-m2.1 | 1562 ms | 1562 ms | — | 100.00% | — | 2 |
| xiaomimimo/mimo-v2.5-pro | 1661 ms | 1661 ms | — | 100.00% | — | 1 |
| sao10k/l3-8b-lunaris | 1708 ms | 1707 ms | — | 100.00% | — | 1 |
| zai-org/glm-4.5-air | 1714 ms | 1714 ms | — | 100.00% | — | 1 |
| zai-org/glm-4.7-flash | 1787 ms | 1787 ms | — | 100.00% | — | 1 |
| minimax/minimax-m2 | 1832 ms | 1831 ms | — | 100.00% | — | 1 |
| qwen/qwen-mt-plus | 1859 ms | 1858 ms | — | 100.00% | — | 2 |
| minimax/minimax-m2.7 | 1872 ms | 1872 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v3.1 | 2073 ms | 2073 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v3-0324 | 2081 ms | 2081 ms | — | 100.00% | — | 2 |
| minimax/minimax-m2.5-highspeed | 2340 ms | 2340 ms | — | 100.00% | — | 1 |
| qwen/qwen3-coder-30b-a3b-instruct | 2455 ms | 2455 ms | — | 100.00% | — | 1 |
| qwen/qwen3-vl-30b-a3b-instruct | 2665 ms | 2665 ms | — | 100.00% | — | 1 |
| qwen/qwen3.7-max | 2757 ms | 2757 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v3.2 | 2803 ms | 2803 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.6 | 2869 ms | 2869 ms | 35 tok/s n=2 | 100.00% | — | 1 |
| qwen/qwen3.8-max | 2920 ms | 2920 ms | 68 tok/s n=1 | 100.00% | — | 2 |
| zai-org/glm-4.6v | 3000 ms | 3000 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-r1-0528 | 3141 ms | 3141 ms | — | 100.00% | — | 1 |
| kwaipilot/kat-coder-pro | 3224 ms | 3224 ms | — | 100.00% | — | 1 |
| qwen/qwen3-omni-30b-a3b-instruct | 4449 ms | 4449 ms | — | 100.00% | — | 1 |
| google/gemma-3-27b-it | 6693 ms | 6693 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-122b-a10b | 4327 ms | 4327 ms | — | 50.00% | — | 2 |
| deepseek/deepseek-v4-flash | — | — | 77 tok/s n=1 | — | — | 0 |
| google/gemma-3-12b-it | — | — | — | 0.00% | — | 2 |
| inclusionai/ling-3.0-flash | — | — | 141 tok/s n=2 | — | — | 0 |
| mindai/macaron-v1-tall | — | — | — | 0.00% | — | 2 |
| mindai/macaron-v1-venti | — | — | 13 tok/s n=2 | — | — | 0 |
| minimax/minimax-m3 | — | — | 56 tok/s n=1 | — | — | 0 |
| moonshotai/kimi-k2.7-code | — | — | 34 tok/s n=1 | — | — | 0 |
| moonshotai/kimi-k3 | — | — | 14 tok/s n=1 | — | — | 0 |
| openai/gpt-oss-120b | — | — | 64 tok/s n=2 | — | — | 0 |
| tencent/hy3 | — | — | 93 tok/s n=2 | — | — | 0 |
| z-ai/glm-5.2 | — | — | 22 tok/s n=1 | — | — | 0 |