Nebius
NL · serverless
European cloud with EU-resident inference and its own GPU capacity. The AI Studio product is now Nebius Token Factory.
- Category
- serverless
- Free tier
- Yes
- OpenAI API
- Compatible
- Adds on top
- None - sets its own prices
Margin over the underlying model price
What Nebius charges
Live prices for widely-hosted open-weight models, sampled from the shared catalogue. Compare the same row against other hosts on each model page.
| Model | Input / 1M | Output / 1M | Context | Throughput |
|---|---|---|---|---|
| GLM 5.3 Flash | $0.150 | $0.500 | 1.0M | - |
| Beam 1.0 501B A23B | $0.250 | $1.00 | 1.0M | - |
| DeepSeek V4.1 Flash 1017 | $0.300 | $1.20 | 1.0M | - |
| Nemotron 3.5 Super VL | $0.300 | $0.900 | 1.0M | - |
| DeepSeek V4.1 Flash | $0.300 | $1.20 | 1.0M | - |
| Muse Spark Open | $1.25 | $4.25 | 1.0M | - |
Nebius alternatives
Other services in the same category. These are genuine substitutes - services in a different category solve a different problem.
Frequently asked
Is Nebius OpenAI-compatible?
Yes. Nebius accepts the OpenAI chat-completions request shape, so most SDKs work by changing the base URL and API key.
Does Nebius have a free tier?
Yes - Nebius offers free usage, though limits and eligible models change frequently. Check the pricing page before relying on it.
How does Nebius charge?
Per token Margin over the underlying model price: none - sets its own prices.