Nebius AI
European AI cloud platform for scalable ML workloads. Requesty routes to 4 Nebius AI models starting at $0.13 per 1M input tokens with context windows up to 256K tokens. One API key, OpenAI-compatible SDK, no markup.
Flagship model
meta-llama/Llama-3.3-70B-InstructMMLU Pro
68.9%
GPQA
50.5%
HumanEval
88.4%
SWE-Bench
23.3%
All Nebius AI models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | SWE-Bench |
|---|---|---|---|---|---|---|
gpt-oss-120b | 131K | 128K | $0.15 | $0.60 | 🧠🔧 | — |
deepseek-ai/DeepSeek-V3.2 | 164K | 128K | $0.30 | $0.45 | 🧠🔧 | — |
moonshotai/kimi-k2.5 | 256K | 128K | $0.50 | $2.50 | 👁🧠🔧 | — |
meta-llama/Llama-3.3-70B-Instruct | 128K | — | $0.13 | $0.40 | 🔧 | 23% |
About Nebius AI on Requesty
How many Nebius AI models are available through Requesty?
Requesty routes to 4 Nebius AI models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Nebius AI model?
The cheapest Nebius AI model starts at $0.13 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Nebius AI pricing?
No. Requesty passes through exactly what Nebius AI charges. You pay the same per-token rates as going direct — plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train Nebius AI models?
Nebius AI's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are Nebius AI models hosted?
Nebius AI models are hosted in 🇪🇺 EU. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI — filter by region on the Nebius AI rows in the models explorer.