OpenAI compatible API · Attested · Public status
Nebius Token Factory performance
Review measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Nebius Token Factory on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Nebius Token Factorynebius
94 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 | 2173 ms |
|---|---|
| p95 TTFT | 11354 ms |
| p50 TTFB | 2551 ms |
| Effective throughput | 99 tok/s n=7 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| Qwen/Qwen3-235B-A22B-Instruct-2507 | 1434 ms | 1433 ms | — | 100.00% | — | 10 |
| nvidia/Nemotron-3-Nano-Omni | 820 ms | 820 ms | — | 100.00% | — | 1 |
| Qwen/Qwen3-30B-A3B-Instruct-2507 | 1004 ms | 1004 ms | — | 100.00% | — | 6 |
| NousResearch/Hermes-4-405B | 1175 ms | 1175 ms | — | 100.00% | — | 6 |
| Qwen/Qwen3-32B | 1252 ms | 1252 ms | — | 100.00% | — | 7 |
| deepseek-ai/DeepSeek-V4-Pro | 1561 ms | 1561 ms | — | 100.00% | — | 3 |
| nvidia/nemotron-3-ultra-550b-a55b | 1688 ms | 1687 ms | 128 tok/s n=1 | 100.00% | — | 1 |
| moonshotai/kimi-k3 | 1836 ms | 1835 ms | 28 tok/s n=2 | 100.00% | — | 2 |
| deepseek/deepseek-v4-flash | 1934 ms | 1933 ms | 99 tok/s n=2 | 100.00% | — | 1 |
| moonshotai/Kimi-K2.7-Code | 2173 ms | 2172 ms | — | 100.00% | — | 5 |
| google/gemma-3-27b-it | 2174 ms | 2173 ms | — | 100.00% | — | 1 |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B | 2317 ms | 2316 ms | — | 100.00% | — | 1 |
| Qwen/Qwen2.5-VL-72B-Instruct | 2581 ms | 2581 ms | — | 100.00% | — | 6 |
| nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 | 2795 ms | 2795 ms | — | 100.00% | — | 2 |
| nvidia/nemotron-3-super-120b-a12b | 2896 ms | 2896 ms | — | 100.00% | — | 1 |
| Qwen/Qwen3-Next-80B-A3B-Thinking | 3384 ms | 3383 ms | — | 100.00% | — | 8 |
| NousResearch/Hermes-4-70B | 3550 ms | 3550 ms | — | 100.00% | — | 8 |
| openbmb/MiniCPM-V-4_5 | 4139 ms | 4138 ms | — | 100.00% | — | 2 |
| zai-org/GLM-5.2 | 4308 ms | 4307 ms | — | 100.00% | — | 1 |
| MiniMaxAI/MiniMax-M3 | 4409 ms | 4409 ms | — | 100.00% | — | 6 |
| openai/gpt-oss-120b | 4421 ms | 4421 ms | 53 tok/s n=1 | 100.00% | — | 1 |
| nvidia/nemotron-3_5-lightning | 5578 ms | 5577 ms | 113 tok/s n=1 | 100.00% | — | 1 |
| zai-org/GLM-5.1 | 11354 ms | 11353 ms | — | 100.00% | — | 1 |
| meta-llama/Llama-3.3-70B-Instruct | 16387 ms | 16387 ms | — | 100.00% | — | 1 |
| MiniMaxAI/MiniMax-M2.5 | — | — | — | 100.00% | 2 probe_config_error |
7 |
| Qwen/Qwen3.5-397B-A17B | — | — | — | 100.00% | 2 probe_config_error |
5 |