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
95 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 | 4491 ms |
|---|---|
| p95 TTFT | 8825 ms |
| Effective throughput | 105 tok/s n=2 |
| Uptime | 97.89% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| deepseek/deepseek-v4-flash-0731 | 4491 ms | — | 98.61% | — | 72 |
| google/gemma-3-27b-it | 1202 ms | — | 100.00% | — | 4 |
| deepseek-ai/DeepSeek-V4-Pro | 1309 ms | — | 100.00% | — | 2 |
| nvidia/nemotron-3-super-120b-a12b | 1415 ms | — | 100.00% | — | 1 |
| moonshotai/Kimi-K2.7-Code | 1477 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.3 | 1780 ms | — | 66.67% | — | 3 |
| moonshotai/kimi-k3 | 2298 ms | 103 tok/s n=1 | 100.00% | — | 4 |
| openbmb/MiniCPM-V-4_5 | 3244 ms | — | 100.00% | — | 1 |
| Qwen/Qwen3.5-397B-A17B | 3379 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.3-flash | 3687 ms | — | 100.00% | — | 1 |
| moonshotai/Kimi-K2.6 | 3874 ms | — | 100.00% | — | 1 |
| Qwen/Qwen3-235B-A22B-Instruct-2507 | 4159 ms | — | 100.00% | — | 2 |
| zai-org/GLM-5.1 | 6718 ms | — | 100.00% | — | 1 |
| Qwen/Qwen3-30B-A3B-Instruct-2507 | 14035 ms | — | 100.00% | — | 1 |
| openai/gpt-oss-120b | — | 107 tok/s n=1 | — | — | 0 |