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 AInovita
22 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 | 1536 ms |
|---|---|
| p95 TTFT | 2436 ms |
| p50 TTFB | 1536 ms |
| Effective throughput | — |
| Uptime | 90.91% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| meta-llama/llama-3.1-8b-instruct | 1207 ms | 1207 ms | — | 100.00% | — | 1 |
| qwen/qwen3-coder-30b-a3b-instruct | 1352 ms | 1352 ms | — | 100.00% | — | 3 |
| qwen/qwen3-coder-480b-a35b-instruct | 1402 ms | 1402 ms | — | 100.00% | — | 1 |
| qwen/qwen3-omni-30b-a3b-instruct | 1453 ms | 1452 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-r1-distill-llama-70b | 1465 ms | 1465 ms | — | 100.00% | — | 1 |
| google/gemma-4-31b-it | 1481 ms | 1481 ms | — | 100.00% | — | 1 |
| inclusionai/ring-2.6-1t | 1518 ms | 1517 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2-instruct | 1536 ms | 1536 ms | — | 100.00% | — | 1 |
| minimax/minimax-m2.5 | 1757 ms | 1756 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.6 | 1927 ms | 1927 ms | — | 100.00% | — | 1 |
| zai-org/glm-5 | 1929 ms | 1929 ms | — | 100.00% | — | 1 |
| minimaxai/minimax-m1-80k | 1954 ms | 1954 ms | — | 100.00% | — | 1 |
| qwen/qwen3-omni-30b-a3b-thinking | 2009 ms | 2009 ms | — | 100.00% | — | 1 |
| baidu/ernie-4.5-vl-424b-a47b | 2024 ms | 2024 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v3.2-exp | 2312 ms | 2311 ms | — | 100.00% | — | 1 |
| stepfun/step-3.7-flash | 2418 ms | 2418 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.2 | 2436 ms | 2436 ms | — | 100.00% | — | 1 |
| google/gemma-4-26b-a4b-it | 7601 ms | 7601 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.3-70b-instruct | — | — | — | 0.00% | — | 1 |
| microsoft/wizardlm-2-8x22b | — | — | — | 0.00% | — | 1 |