Nebius
Build and scale faster on the purpose-built AI cloud, engineered from silicon to API. Inference platform · OpenAI-compatible API · European · Gpu Cloud · Open Source · Serverless
Intelligence vs Price
Best value among Nebius models on this chart: Kimi K3 · GLM-5.3 Flash · DeepSeek V4 Flash (and 1 more on the dashed frontier). Prices use each model's lowest available Nebius price across regions. Hover any dot for full pricing, or click a creator in the legend to isolate.
Nebius models
18 models in eu-north1, 18 with pricing| Select | Model | Creator | Input Price, $ | Output Price, $ | Context | Max Output | Inference Providers | Intelligence | Coding |
|---|---|---|---|---|---|---|---|---|---|
| GLM-5.1 | 1.40 | 4.40 | 205K | 203K | #1 | #1 | |||
| GPT OSS 120B | 0.15 | 0.6 | 131K | 131K | #2 | #2 | |||
| Nemotron Lightning 3.5 | 0.06 | 0.24 | 1.0M | 236K | #3 | #3 | |||
| Qwen3 235B A22B Instruct | 0.2 | 0.6 | 262K | 16K | #4 | N/A | |||
| Nemotron Nano 3 30B A3B | 0.06 | 0.24 | 262K | 236K | #5 | #5 | |||
| Qwen3 32B | 0.1 | 0.3 | 131K | 41K | #6 | #4 | |||
| Llama 3.3 70B Instruct | 0.13 | 0.4 | 131K | 120K | #7 | #6 | |||
| Llama 3.1 Nemotron 1 Ultra 253B | 0.6 | 1.80 | 128K | N/A | #8 | N/A | |||
| Qwen3 30B A3B Instruct | 0.1 | 0.3 | 262K | 32K | #9 | N/A | |||
| Cosmos 3 Super Reasoner | 0.1 | 0.3 | N/A | N/A | N/A | N/A | |||
| Gemma 3 27B Instruct | 0.1 | 0.3 | 262K | 131K | N/A | N/A | |||
| Hermes 4 405B | 1.00 | 3.00 | 131K | 118K | N/A | N/A | |||
| Hermes 4 70B | 0.13 | 0.4 | 131K | 118K | N/A | N/A | |||
| MiniCPM-V 4.5 VL | Openbmb | 0.658 | 1.11 | N/A | N/A | N/A | N/A | ||
| Nemotron Nano 3 Omni | 0.06 | 0.24 | N/A | N/A | N/A | N/A | |||
| Qwen2.5 VL 72B Instruct | 0.25 | 0.75 | 131K | 128K | N/A | N/A | |||
| Qwen3 Embedding 8B | 0.01 | N/A | 41K | 4K | N/A | N/A | |||
| Qwen3 Next 80B A3B Thinking | 0.15 | 1.20 | 262K | 66K | N/A | N/A |