OpenAI compatible API · Attested · Public status
Nebius Token Factory performance
Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Nebius Token Factory.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
nebius
55 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 | 1759 ms |
|---|---|
| p95 TTFT | 9987 ms |
| p50 TTFB | 2073 ms |
| Effective throughput | 112 tok/s n=7 |
| Uptime | 98.18% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| openbmb/MiniCPM-V-4_5 | 659 ms | 659 ms | 114 tok/s n=1 | 100.00% | — | 3 |
| nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 | 726 ms | 725 ms | — | 100.00% | — | 2 |
| Qwen/Qwen3-30B-A3B-Instruct-2507 | 1066 ms | 1066 ms | — | 100.00% | — | 3 |
| NousResearch/Hermes-4-70B | 1351 ms | 1351 ms | — | 100.00% | — | 2 |
| moonshotai/Kimi-K2.7-Code | 1514 ms | 1513 ms | — | 100.00% | — | 3 |
| meta-llama/Llama-3.3-70B-Instruct | 1521 ms | 1521 ms | — | 100.00% | — | 8 |
| MiniMaxAI/MiniMax-M3 | 1563 ms | 1563 ms | 112 tok/s n=1 | 100.00% | — | 1 |
| nvidia/Nemotron-3-Nano-Omni | 1618 ms | 1617 ms | — | 100.00% | — | 1 |
| openai/gpt-oss-120b | 1619 ms | 1619 ms | 225 tok/s n=1 | 100.00% | — | 1 |
| moonshotai/Kimi-K2.6 | 1759 ms | 1759 ms | — | 100.00% | — | 4 |
| Qwen/Qwen2.5-VL-72B-Instruct | 1855 ms | 1854 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-3-super-120b-a12b | 2047 ms | 2046 ms | — | 100.00% | — | 2 |
| zai-org/GLM-5.2 | 2073 ms | 2073 ms | — | 100.00% | — | 1 |
| nvidia/Cosmos3-Super-Reasoner | 2353 ms | 2353 ms | 62 tok/s n=1 | 100.00% | — | 4 |
| NousResearch/Hermes-4-405B | 2441 ms | 2441 ms | — | 100.00% | — | 1 |
| google/gemma-3-27b-it | 2462 ms | 2462 ms | — | 100.00% | — | 5 |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B | 2723 ms | 2722 ms | — | 100.00% | — | 1 |
| Qwen/Qwen3-235B-A22B-Instruct-2507 | 2736 ms | 2735 ms | — | 100.00% | — | 3 |
| moonshotai/kimi-k3 | 3184 ms | 3184 ms | 80 tok/s n=2 | 100.00% | — | 1 |
| Qwen/Qwen3-Next-80B-A3B-Thinking | 3330 ms | 3330 ms | — | 100.00% | — | 3 |
| Qwen/Qwen3-32B | 3411 ms | 3411 ms | — | 100.00% | — | 1 |
| deepseek-ai/DeepSeek-V4-Pro | 3489 ms | 3489 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-3-ultra-550b-a55b | 3558 ms | 3558 ms | 112 tok/s n=1 | 100.00% | — | 1 |
| zai-org/GLM-5.1 | 4479 ms | 4479 ms | — | 50.00% | — | 2 |