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
35 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 | 1708 ms |
|---|---|
| p95 TTFT | 12861 ms |
| Effective throughput | 55 tok/s n=9 |
| Uptime | 94.29% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| qwen/qwen3.8-27b | 871 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash-0731 | 1052 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.3 | 1147 ms | 151 tok/s n=1 | 100.00% | — | 2 |
| zai-org/glm-4.5v | 1227 ms | — | 100.00% | — | 1 |
| inclusionai/ling-3.0-flash | 1253 ms | — | 100.00% | — | 2 |
| zai-org/autoglm-phone-9b-multilingual | 1283 ms | — | 100.00% | — | 1 |
| microsoft/wizardlm-2-8x22b | 1320 ms | — | 100.00% | — | 1 |
| zai-org/glm-5 | 1455 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-ocr-2 | 1496 ms | — | 100.00% | — | 1 |
| mindai/macaron-v1-venti | 1657 ms | — | 100.00% | — | 2 |
| qwen/qwen3-omni-30b-a3b-thinking | 1687 ms | — | 100.00% | — | 1 |
| minimax/minimax-m3 | 1708 ms | 102 tok/s n=2 | 100.00% | — | 1 |
| minimax/minimax-m2.7 | 1760 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4.1-flash-1017 | 1808 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.7-code | 1898 ms | 42 tok/s n=1 | 100.00% | — | 1 |
| z-ai/glm-5.3-p | 1960 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.5 | 2136 ms | — | 100.00% | — | 2 |
| minimax/minimax-m3.1-flash | 2228 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.2 | 2237 ms | 62 tok/s n=1 | 100.00% | — | 1 |
| deepseek/deepseek-v4-pro | 2367 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4.1-flash-p | 2436 ms | — | 100.00% | — | 1 |
| zai-org/glm-4.7-flash | 2467 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k3.1-pro-highspeed | 2530 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash-0731-p | 2663 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.6 | 3279 ms | 39 tok/s n=2 | 100.00% | — | 1 |
| moonshotai/kimi-k3 | 3516 ms | 55 tok/s n=1 | 100.00% | — | 1 |
| meta-llama/llama-4-scout-17b-16e-instruct | 18434 ms | — | 100.00% | — | 1 |
| baidu/cobuddy | — | — | 0.00% | — | 1 |
| google/gemma-3-12b-it | — | — | 0.00% | — | 1 |
| google/gemma-4-31b-it | — | 32 tok/s n=1 | — | — | 0 |
| moonshotai/kimi-k2-thinking | — | — | — | 1 unsupported_route |
0 |