What is Nebius Token Factory
Nebius Token Factory is a managed inference and post-training platform for open models, with public serverless endpoints, dedicated deployments, batch processing and an OpenAI-compatible API.
Serverless and batch pricing
As of September 19, 2026, new accounts receive US$1 in free credit. Public endpoints use per-token pay-as-you-go pricing. Current rates per million tokens include DeepSeek V4.1 Flash at US$0.30 input and US$1.20 output, GPT OSS 120B at US$0.15 and US$0.60, GLM 5.3 at US$1.40 and US$4.40, Qwen 3.5 397B A17B at US$0.60 and US$3.60, and Nemotron 3.5 Lightning at US$0.06 and US$0.24.
The live catalogue currently lists 24 active public models and identifies their regions, quantisation, context allowance and supported use cases. Batch inference is billed at 50% of the base real-time model price, rounded up to the nearest cent.
Dedicated and enterprise inference
Dedicated endpoints are billed per GPU hour with per-minute granularity and provide isolated capacity, selectable regions, custom weights, controlled autoscaling and no standard shared-service rate limits. Enterprise arrangements add volume discounts, governed workspaces, SSO, unified billing, auditability and a 99.9% uptime SLA.
Official sources: Nebius Token Factory pricing, Dedicated endpoint documentation, Token Factory platform overview.