OpenAI compatible API · Attested · Public status
Novita AI performance
Review measured TTFT, 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
33 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 | 2514 ms |
|---|---|
| p95 TTFT | 17012 ms |
| Effective throughput | 84 tok/s n=8 |
| Uptime | 84.85% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| zai-org/autoglm-phone-9b-multilingual | 1000 ms | — | 100.00% | — | 1 |
| openai/gpt-oss-20b | 1300 ms | — | 100.00% | — | 1 |
| qwen/qwen3-235b-a22b-instruct-2507 | 1429 ms | — | 100.00% | — | 1 |
| zai-org/glm-4.6v | 1584 ms | — | 100.00% | — | 1 |
| google/gemma-4-26b-a4b-it | 1592 ms | — | 100.00% | — | 1 |
| qwen/qwen3-next-80b-a3b-instruct | 1832 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4.1-flash | 1863 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.3-70b-instruct | 2004 ms | — | 100.00% | — | 1 |
| meta-llama/llama-4-scout-17b-16e-instruct | 2045 ms | — | 100.00% | — | 1 |
| microsoft/wizardlm-2-8x22b | 2074 ms | — | 100.00% | — | 1 |
| minimax/minimax-m3 | 2189 ms | 89 tok/s n=2 | 100.00% | — | 1 |
| qwen/qwen3.5-122b-a10b | 2390 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.6 | 2514 ms | 17 tok/s n=1 | 100.00% | — | 1 |
| moonshotai/kimi-k2-instruct | 2696 ms | — | 100.00% | — | 1 |
| qwen/qwen3.8-max | 2810 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.2 | 2827 ms | 79 tok/s n=1 | 100.00% | — | 1 |
| qwen/qwen3.7-max | 2920 ms | — | 100.00% | — | 1 |
| qwen/qwen3.8-27b | 3247 ms | — | 100.00% | — | 2 |
| google/gemma-4-31b-it | 3605 ms | 56 tok/s n=1 | 100.00% | — | 1 |
| zai-org/glm-4.7-flash | 4669 ms | — | 50.00% | — | 2 |
| xiaomimimo/mimo-v2.5 | 7435 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.3-p | 17012 ms | — | 100.00% | — | 1 |
| openai/gpt-oss-120b | 22168 ms | 54 tok/s n=1 | 100.00% | — | 1 |
| Sao10K/L3-8B-Stheno-v3.2 | — | — | 100.00% | — | 1 |
| deepseek/deepseek-ocr-2 | — | — | 100.00% | — | 2 |
| sao10k/l3-8b-lunaris | — | — | 100.00% | — | 1 |
| baidu/cobuddy | — | — | 0.00% | — | 1 |
| baidu/ernie-4.5-21B-a3b | — | — | 0.00% | — | 2 |
| deepseek/deepseek-v4-flash | — | 137 tok/s n=1 | — | — | 0 |
| mindai/macaron-v1-tall | — | — | 0.00% | — | 1 |
| qwen/qwen3-235b-a22b-thinking-2507 | — | 101 tok/s n=1 | — | — | 0 |