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
467 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 | 7695 ms |
|---|---|
| p95 TTFT | 17221 ms |
| p50 TTFB | 3569 ms |
| Effective throughput | 57 tok/s n=14 |
| Uptime | 33.83% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| microsoft/wizardlm-2-8x22b | 7695 ms | 4820 ms | — | 25.67% | — | 409 |
| qwen/qwen3-235b-a22b-instruct-2507 | 985 ms | 985 ms | — | 100.00% | — | 1 |
| zai-org/glm-4.5-air | 1181 ms | 1181 ms | — | 100.00% | — | 1 |
| minimax/minimax-m3 | 1206 ms | 1206 ms | 57 tok/s n=2 | 100.00% | — | 1 |
| qwen/qwen3-omni-30b-a3b-thinking | 1230 ms | 1229 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash-0731 | 1348 ms | 1348 ms | 58 tok/s n=1 | 100.00% | — | 1 |
| moonshotai/kimi-k2-instruct | 1394 ms | 1393 ms | — | 100.00% | — | 2 |
| qwen/qwen3-235b-a22b-thinking-2507 | 1403 ms | 1403 ms | — | 100.00% | — | 1 |
| sao10k/l31-70b-euryale-v2.2 | 1802 ms | 1802 ms | — | 100.00% | — | 1 |
| openai/gpt-oss-20b | 1850 ms | 1850 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-r1-distill-llama-70b | 1908 ms | 1908 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2-0905 | 1923 ms | 1923 ms | — | 100.00% | 3 provider_error |
2 |
| deepseek/deepseek-v3-turbo | 2181 ms | 2180 ms | — | 100.00% | — | 2 |
| minimax/minimax-m2.5-highspeed | 2336 ms | 2336 ms | — | 100.00% | — | 1 |
| qwen/qwen3.8-max | 2821 ms | 2821 ms | — | 100.00% | — | 2 |
| Sao10K/L3-8B-Stheno-v3.2 | 2859 ms | 2859 ms | — | 100.00% | — | 8 |
| qwen/qwen3-next-80b-a3b-instruct | 3268 ms | 3268 ms | — | 100.00% | — | 1 |
| inclusionai/ring-2.6-1t | 3415 ms | 3414 ms | — | 100.00% | — | 1 |
| minimaxai/minimax-m1-80k | 3650 ms | 3650 ms | — | 100.00% | — | 2 |
| qwen/qwen3.6-27b | 3714 ms | 3713 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.7-code | 3806 ms | 3806 ms | 42 tok/s n=1 | 100.00% | — | 1 |
| qwen/qwen3.5-397b-a17b | 3951 ms | 3951 ms | — | 100.00% | — | 1 |
| minimax/minimax-m2.1 | 4159 ms | 4158 ms | — | 100.00% | — | 2 |
| qwen/qwen3-omni-30b-a3b-instruct | 4250 ms | 4250 ms | — | 100.00% | — | 1 |
| inclusionai/ling-2.6-flash | 4267 ms | 4267 ms | — | 100.00% | — | 1 |
| google/gemma-4-31b-it | 4323 ms | 4322 ms | 31 tok/s n=1 | 100.00% | — | 2 |
| qwen/qwen3-vl-235b-a22b-instruct | 4430 ms | 4430 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-r1-0528 | 4569 ms | 4569 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.2 | 4707 ms | 4707 ms | 60 tok/s n=2 | 100.00% | — | 1 |
| stepfun/step-3.7-flash | 8329 ms | 8329 ms | — | 100.00% | — | 3 |
| moonshotai/kimi-k2.5 | 18267 ms | 18267 ms | — | 100.00% | — | 1 |
| baidu/ernie-4.5-vl-424b-a47b | — | — | — | 100.00% | — | 2 |
| kwaipilot/kat-coder-pro | — | — | — | 100.00% | — | 1 |
| mindai/macaron-v1-venti | — | — | — | 100.00% | — | 1 |
| qwen/qwen-2.5-72b-instruct | — | — | — | 100.00% | — | 1 |
| zai-org/autoglm-phone-9b-multilingual | — | — | — | 100.00% | 1 provider_error |
1 |
| zai-org/glm-4.6 | 3643 ms | 3642 ms | — | 50.00% | — | 2 |
| baichuan/baichuan-m2-32b | — | — | — | 0.00% | — | 2 |
| baidu/cobuddy | — | — | — | 0.00% | — | 1 |
| deepseek/deepseek-v4-flash | — | — | 61 tok/s n=2 | — | — | 0 |
| google/gemma-3-12b-it | — | — | — | 0.00% | — | 1 |
| inclusionai/ling-3.0-flash | — | — | 121 tok/s n=1 | — | — | 0 |
| moonshotai/kimi-k2.6 | — | — | 34 tok/s n=1 | — | — | 0 |
| moonshotai/kimi-k3 | — | — | 29 tok/s n=1 | — | — | 0 |
| openai/gpt-oss-120b | — | — | 20 tok/s n=1 | — | — | 0 |
| qwen/qwen3.7-max | — | — | 85 tok/s n=1 | — | — | 0 |