OpenAI compatible API · Attested · Public status

Nebius Token Factory performance

Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Nebius Token Factory.

Verify gateway
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.

Nebius Token Factorynebius

28 samples

Provider overview

Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.

p50 TTFT1121 ms
p95 TTFT3939 ms
p50 TTFB1239 ms
Effective throughput
Uptime100.00%

Measured model routes

Modelp50 TTFTp50 TTFBEffective throughputUptimeConfig excludedAvailability samples
openbmb/MiniCPM-V-4_5 615 ms 615 ms 100.00% 1
nvidia/Cosmos3-Super-Reasoner 619 ms 619 ms 100.00% 2
NousResearch/Hermes-4-70B 1040 ms 1039 ms 100.00% 3
NousResearch/Hermes-4-405B 1055 ms 1055 ms 100.00% 2
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 1059 ms 1059 ms 100.00% 1
Qwen/Qwen3-32B 1101 ms 1101 ms 100.00% 1
google/gemma-3-27b-it 1102 ms 1102 ms 100.00% 2
nvidia/Nemotron-3-Nano-Omni 1121 ms 1120 ms 100.00% 2
moonshotai/Kimi-K2.6 1218 ms 1218 ms 100.00% 1
zai-org/GLM-5.2 1332 ms 1332 ms 100.00% 1
Qwen/Qwen2.5-VL-72B-Instruct 1355 ms 1355 ms 100.00% 1
deepseek-ai/DeepSeek-V4-Pro 1514 ms 1513 ms 100.00% 2
nvidia/nemotron-3-ultra-550b-a55b 1536 ms 1536 ms 100.00% 2
MiniMaxAI/MiniMax-M3 1576 ms 1576 ms 100.00% 1
nvidia/nemotron-3-super-120b-a12b 1585 ms 1584 ms 100.00% 1
moonshotai/kimi-k3 1894 ms 1894 ms 100.00% 1
Qwen/Qwen3-Next-80B-A3B-Thinking 2498 ms 2498 ms 100.00% 2
zai-org/GLM-5.1 3939 ms 3938 ms 100.00% 1
meta-llama/Llama-3.3-70B-Instruct 7781 ms 7781 ms 100.00% 1
Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

By signing in you agree to the terms of service and privacy policy.