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
49 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 | 2449 ms |
|---|---|
| p95 TTFT | 13273 ms |
| p50 TTFB | 2441 ms |
| Effective throughput | 102 tok/s n=8 |
| Uptime | 97.96% |
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% | — | 2 |
| moonshotai/Kimi-K2.7-Code | 1161 ms | 1161 ms | — | 100.00% | — | 1 |
| NousResearch/Hermes-4-70B | 1423 ms | 1422 ms | — | 100.00% | — | 4 |
| MiniMaxAI/MiniMax-M3 | 1563 ms | 1563 ms | 112 tok/s n=1 | 100.00% | — | 1 |
| openai/gpt-oss-120b | 1619 ms | 1619 ms | 164 tok/s n=2 | 100.00% | — | 2 |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B | 1920 ms | 1920 ms | — | 100.00% | — | 2 |
| nvidia/nemotron-3-super-120b-a12b | 2047 ms | 2046 ms | — | 100.00% | — | 1 |
| moonshotai/Kimi-K2.6 | 2360 ms | 2360 ms | — | 100.00% | — | 3 |
| NousResearch/Hermes-4-405B | 2441 ms | 2441 ms | — | 100.00% | — | 1 |
| Qwen/Qwen3-235B-A22B-Instruct-2507 | 2449 ms | 2449 ms | — | 100.00% | — | 4 |
| google/gemma-3-27b-it | 2462 ms | 2462 ms | — | 100.00% | — | 7 |
| Qwen/Qwen3-Next-80B-A3B-Thinking | 2484 ms | 2484 ms | — | 100.00% | — | 2 |
| nvidia/Cosmos3-Super-Reasoner | 2738 ms | 2738 ms | 62 tok/s n=1 | 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 |
| meta-llama/Llama-3.3-70B-Instruct | 6942 ms | 6942 ms | — | 100.00% | — | 6 |
| zai-org/GLM-5.2 | 20341 ms | 20341 ms | — | 100.00% | — | 1 |
| zai-org/GLM-5.1 | 4479 ms | 4479 ms | — | 50.00% | — | 2 |
| moonshotai/kimi-k3 | — | — | 65 tok/s n=1 | — | — | 0 |
| nvidia/nemotron-3-ultra-550b-a55b | — | — | 92 tok/s n=2 | — | — | 0 |