Nebius Token Factory: Models and Prices

Inference provider serving open-weight models.

Nebius Token Factory served 328B tokens of other labs' open-weight models over Nov 2 to Nov 8, 2026 through a large public LLM router, #33 among providers.

Open-weight models

ModelFamilyShare of modelTokens, 7dInput $/MOutput $/MTokens/sUptime 3dContext
Nemotron 3.5 Super VLNemotron2.8%104B$0.30$0.907799.5%1.05M
MiniMax M3.1 FlashMiniMax0.9%46B$0.15$0.60103100.0%1.05M
DeepSeek V4.1 Flash 1017DeepSeek<0.1%38B$0.30$1.2096100.0%1.05M
Qwen3.8 27BQwen5.9%35B$0.45$3.0025099.2%1M
DeepSeek V4.1 FlashDeepSeek0.1%20B$0.30$1.207199.9%1.05M
Beam 1.0 501B A23BOther open-weight20.0%18B$0.25$1.0019498.2%1.05M
Kimi K3.1 ProKimi0.4%17B$2.00$10.0010196.9%1.05M
Qwen3 30B A3B Instruct 2507Qwen100.0%16B$0.10$0.305196.1%262K
DeepSeek V4 Flash 0731DeepSeek0.2%7B$0.14$0.282796.7%1.05M
Muse Spark OpenOther open-weight5.2%7B$1.25$4.25146100.0%1.05M
DeepSeek V4 Pro 0813DeepSeek1.0%6B$1.32$3.965999.8%1.05M
gpt-oss-120bgpt-oss2.3%6B$0.15$0.60251100.0%131K
GLM 5.3 FlashGLM<0.1%4B$0.15$0.507899.8%1.05M
Nemotron 3 Nano 30B A3BNemotron100.0%3B$0.06$0.2490100.0%262K
GLM 5.1GLM7.4%959M$1.40$4.403599.4%203K
GLM 5.3GLM--$1.40$4.404797.9%1.05M
GLM 5.2GLM--$1.40$4.4016381.0%1.05M
DeepSeek V4 Pro 0423DeepSeek--$1.75$3.504097.9%1.05M
Gemma 3 27BGemma--$0.10$0.303498.4%110K
Hermes 4 405BOther open-weight--$1.00$3.0041100.0%131K

List prices per million tokens as of November 8, 2026. Share: of all tokens served on that model; a dash where the volume is not reported.

Company

Headquarters
Netherlands

Finance your GPUs

Serving tokens on your own GPUs? Tell us the cluster, the models you serve and the contracts behind them, and we will share it with partner funders that fit.

Prefer email? hello@amcompute.com