Nebius
European AI inference on Token Factory. Two flavors: fast (low latency) and base (cost-efficient). Batch at 50% off.
At a glance: Nebius has 24 models listed on Inference Hub: 22 LLMs, 1 coding model and 1 embedding model. The cheapest text model is Nemotron 3.5 Lightning at $0.060 input and $0.240 output per 1M tokens, and the most expensive is Kimi K3 at $3.00 input and $15.00 output per 1M tokens. Free tier: 1 dollar in free credits to start. Prices are checked against Nebius's own pricing every week.
Features
Compliance
None listed
Pricing Model
per tokenDetails
https://api.studio.nebius.ai/v1 Model Catalog (30)
Nebius guides
Zero Data Retention for AI APIs: Which Providers Store Your Prompts, and How to Turn It Off
Which AI API providers store prompts, for how long, and how to get zero data retention at OpenAI, Anthropic, Google, Azure, Bedrock, OpenRouter and 20 hosts.
Nov 2026AI APIs with Free Tiers in 2026: The Complete Guide
Every AI API with a free tier and its limits: Gemini, Groq, Cloudflare, Together AI, OpenRouter, fal.ai and more. Build with LLM and image APIs for $0.
Nebius API FAQ
Is the Nebius API free?
Yes, Nebius has a free tier: 1 dollar in free credits to start. Paid usage is billed per model.
What is the cheapest Nebius model?
Qwen3 Embedding 8B at $0.01 in / $0 out per 1M tokens, based on the 30 models we track for Nebius.
How many models does Nebius offer?
We track 30 Nebius models: 28 LLM, 1 coding, 1 embedding.
Is the Nebius API OpenAI-compatible?
Yes. Nebius exposes an OpenAI-compatible endpoint, so you can use the OpenAI SDKs by changing the base URL and API key.
Run Nebius? Add a "Prices tracked on Inference Hub" badge to your site, or email hello@inferencehub.org if a price here is wrong.