OpenAI compatible API · Attested · Public status
Nebius Token Factory performance
Review measured TTFT, 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
497 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 | 4171 ms |
|---|---|
| p95 TTFT | 8166 ms |
| Effective throughput | 105 tok/s n=2 |
| Uptime | 99.20% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| deepseek/deepseek-v4-flash-0731 | 4171 ms | — | 99.37% | — | 479 |
| nvidia/nemotron-3-super-120b-a12b | 1415 ms | — | 100.00% | — | 1 |
| google/gemma-3-27b-it | 1447 ms | — | 100.00% | — | 1 |
| moonshotai/Kimi-K2.7-Code | 1477 ms | — | 100.00% | — | 1 |
| deepseek-ai/DeepSeek-V4-Pro | 1675 ms | — | 100.00% | — | 4 |
| z-ai/glm-5.3 | 1780 ms | — | 50.00% | — | 2 |
| moonshotai/kimi-k3 | 2443 ms | — | 100.00% | — | 3 |
| moonshotai/Kimi-K2.6 | 2786 ms | — | 100.00% | — | 2 |
| NousResearch/Hermes-4-405B | 3230 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.3-flash | 3687 ms | — | 100.00% | — | 1 |
| Qwen/Qwen3-235B-A22B-Instruct-2507 | 4159 ms | — | 100.00% | — | 1 |
| zai-org/GLM-5.1 | 6718 ms | — | 100.00% | — | 1 |
| openai/gpt-oss-120b | — | 105 tok/s n=2 | — | — | 0 |