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
48 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 | 1859 ms |
|---|---|
| p95 TTFT | 5211 ms |
| p50 TTFB | 2078 ms |
| Effective throughput | 80 tok/s n=9 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| google/gemma-3-27b-it | 819 ms | 819 ms | — | 100.00% | — | 1 |
| openai/gpt-oss-120b | 1212 ms | 1212 ms | 57 tok/s n=2 | 100.00% | — | 2 |
| Qwen/Qwen2.5-VL-72B-Instruct | 1256 ms | 1256 ms | — | 100.00% | — | 3 |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B | 1304 ms | 1304 ms | — | 100.00% | — | 2 |
| Qwen/Qwen3-32B | 1405 ms | 1404 ms | — | 100.00% | — | 3 |
| deepseek-ai/DeepSeek-V4-Pro | 1423 ms | 1423 ms | — | 100.00% | — | 2 |
| moonshotai/Kimi-K2.7-Code | 1665 ms | 1665 ms | — | 100.00% | — | 4 |
| moonshotai/kimi-k3 | 1689 ms | 1689 ms | 62 tok/s n=1 | 100.00% | — | 2 |
| moonshotai/Kimi-K2.6 | 1720 ms | 1720 ms | — | 100.00% | — | 4 |
| nvidia/nemotron-3-ultra-550b-a55b | 1859 ms | 1859 ms | 105 tok/s n=2 | 100.00% | 1 unsupported_route |
3 |
| MiniMaxAI/MiniMax-M3 | 2078 ms | 2078 ms | 80 tok/s n=2 | 100.00% | — | 2 |
| nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 | 2118 ms | 2118 ms | — | 100.00% | — | 1 |
| meta-llama/Llama-3.3-70B-Instruct | 2186 ms | 2185 ms | — | 100.00% | — | 4 |
| NousResearch/Hermes-4-405B | 2224 ms | 2224 ms | — | 100.00% | — | 2 |
| nvidia/Cosmos3-Super-Reasoner | 2236 ms | 2236 ms | 54 tok/s n=1 | 100.00% | — | 1 |
| Qwen/Qwen3-30B-A3B-Instruct-2507 | 2281 ms | 2280 ms | — | 100.00% | — | 2 |
| openbmb/MiniCPM-V-4_5 | 2410 ms | 2409 ms | 87 tok/s n=1 | 100.00% | — | 1 |
| Qwen/Qwen3-235B-A22B-Instruct-2507 | 2490 ms | 2490 ms | — | 100.00% | — | 3 |
| nvidia/Nemotron-3-Nano-Omni | 2769 ms | 2769 ms | — | 100.00% | — | 1 |
| Qwen/Qwen3-Next-80B-A3B-Thinking | 2792 ms | 2792 ms | — | 100.00% | — | 3 |
| NousResearch/Hermes-4-70B | 3437 ms | 3436 ms | — | 100.00% | — | 1 |
| zai-org/GLM-5.1 | 4248 ms | 4247 ms | — | 100.00% | — | 1 |