Nebius AI Models
European AI cloud platform for scalable ML workloads. Requesty routes to 19 Nebius AI models starting at $0.06 per 1M input tokens with context windows up to 1.0M tokens. One API key, OpenAI-compatible SDK, no markup.
Flagship model
kimi-k3Intelligence Index
57.1
Coding Index
76.2
GPQA Diamond
93.5%
All Nebius AI models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | Coding |
|---|---|---|---|---|---|---|
kimi-k3 | 1.0M | 131K | $3.00 | $15.00 | 🧠🔧 | 76 |
glm-5.2 | 1M | 131K | $1.40 | $4.40 | 🧠🔧 | 69 |
gemma-3-27b-it | 128K | 8K | $0.10 | $0.30 | 🧠🔧 | N/A |
qwen/qwen3-32b | 128K | — | $0.10 | $0.30 | 🧠🔧 | N/A |
qwen/qwen3-next-80b-a3b-thinking | 128K | — | $0.15 | $1.20 | 🧠🔧 | N/A |
nousresearch/hermes-4-70b | 128K | — | $0.13 | $0.40 | 🧠🔧 | N/A |
qwen/qwen3-30b-a3b-instruct-2507 | 128K | — | $0.10 | $0.30 | 🧠🔧 | N/A |
qwen/qwen3-235b-a22b-instruct-2507 | 128K | — | $0.20 | $0.60 | 🧠🔧 | 22 |
qwen/qwen3.5-397b-a17b | 128K | — | $0.60 | $3.60 | 👁🧠🔧 | 48 |
minimaxi/minimax-m2.5 | 128K | — | $0.30 | $1.20 | 🧠🔧 | N/A |
nvidia/nemotron-3-super-120b-a12b | 128K | — | $0.30 | $0.90 | 🧠🔧 | N/A |
nvidia/nemotron-3-ultra-550b-a55b | 128K | — | $1.00 | $3.00 | 🧠🔧 | N/A |
deepseek-ai/deepseek-v4-pro | 164K | 128K | $1.75 | $3.50 | 🧠🔧 | 59 |
moonshotai/kimi-k2.6 | 256K | 128K | $0.95 | $4.00 | 👁🧠🔧 | 62 |
nousresearch/hermes-4-405b | 128K | — | $1.00 | $3.00 | 🧠🔧 | N/A |
zai-org/glm-5.1 | 200K | — | $1.40 | $4.40 | 🧠🔧 | 56 |
nvidia/nemotron-3-nano-omni | 300K | — | $0.06 | $0.24 | 🧠🔧 | N/A |
gpt-oss-120b | 131K | 128K | $0.15 | $0.60 | 🧠🔧 | 30 |
meta-llama/Llama-3.3-70B-Instruct | 128K | — | $0.13 | $0.40 | 🔧 | N/A |
About Nebius AI on Requesty
How many Nebius AI models are available through Requesty?
Requesty routes to 19 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 $0.06 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 600+ 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.