Nebius models & pricing
Nebius hosts 61 models (61 with public pricing) covering 2 modalities. European GPU cloud with Inference Studio for Llama, Qwen, DeepSeek, FLUX. Cheapest input starts at $0.0100/M tokens; the most premium goes up to $3.00/M. Use Future AGI's Agent Command Center to route any Nebius model with cost-optimized fallback and unified observability.
chat 57
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Qwen2.5 Coder 7B | $0.0100/M | $0.0300/M | $0.0150/M | 32,768 | tools |
| Llama Guard 3 8B | $0.0200/M | $0.0600/M | $0.0300/M | 128,000 | |
| Llama 3.1 8B Instruct | $0.0200/M | $0.0600/M | $0.0300/M | 128,000 | tools |
| Qwen2 VL 7B Instruct | $0.0200/M | $0.0600/M | $0.0300/M | 131,072 | vision |
| Mistral Nemo Instruct 2407 | $0.0400/M | $0.120/M | $0.0600/M | 128,000 | tools |
| Nvidia Nemotron 3.5 Lightning | $0.0600/M | $0.240/M | $0.105/M | 1,048,576 | tools · reasoning |
| Nvidia Nemotron 3 nano Omni | $0.0600/M | $0.240/M | $0.105/M | 262,144 | tools · vision · reasoning |
| Nvidia Nvidia Nemotron 3 nano 30B A3B | $0.0600/M | $0.240/M | $0.105/M | 262,144 | tools · reasoning |
| Qwen2.5 32B Instruct | $0.0600/M | $0.200/M | $0.0950/M | 128,000 | tools |
| Qwen3 14B | $0.0800/M | $0.240/M | $0.120/M | 32,768 | tools |
| Qwen3 4B | $0.0800/M | $0.240/M | $0.120/M | 32,768 | tools |
| Gemma 3 27B IT | $0.1000/M | $0.300/M | $0.150/M | 110,000 | tools · vision |
| Nvidia Cosmos3 Super Reasoner | $0.1000/M | $0.300/M | $0.150/M | 262,144 | tools · vision · reasoning |
| Nvidia Llama 3.3 Nemotron Super 49B v1 | $0.1000/M | $0.400/M | $0.175/M | 131,072 | tools |
| Qwen3 30B A3B | $0.1000/M | $0.300/M | $0.150/M | 32,768 | tools |
| Qwen3 30B A3B Instruct 2507 | $0.1000/M | $0.300/M | $0.150/M | 262,144 | tools |
| Qwen3 32B | $0.1000/M | $0.300/M | $0.150/M | 40,960 | tools |
| Llama 3.3 70B Instruct | $0.130/M | $0.400/M | $0.198/M | 131,072 | tools |
| Llama 3.1 70B Instruct | $0.130/M | $0.400/M | $0.198/M | 128,000 | tools |
| Nousresearch Hermes 4 70B | $0.130/M | $0.400/M | $0.198/M | 131,072 | tools · reasoning |
| Qwen2.5 72B Instruct | $0.130/M | $0.400/M | $0.198/M | 128,000 | tools |
| Qwen2 VL 72B Instruct | $0.130/M | $0.400/M | $0.198/M | 131,072 | tools · vision |
| DeepSeek V4 Flash | $0.140/M | $0.280/M | $0.175/M | 1,048,576 | tools · reasoning |
| DeepSeek V4 Flash 0731 | $0.140/M | $0.280/M | $0.175/M | 1,024,000 | tools · reasoning |
| gpt-oss 120B | $0.150/M | $0.600/M | $0.262/M | 131,072 | tools · reasoning |
| Qwen3 Next 80B A3B Thinking | $0.150/M | $1.20/M | $0.413/M | 128,000 | tools · reasoning |
| QwQ 32B | $0.150/M | $0.450/M | $0.225/M | 32,768 | tools · reasoning |
| GLM 5.3 Flash | $0.150/M | $0.500/M | $0.238/M | 1,024,000 | tools · vision · reasoning |
| Qwen3 235B A22B | $0.200/M | $0.600/M | $0.300/M | 262,144 | tools |
| Qwen3 235B A22B Instruct 2507 | $0.200/M | $0.600/M | $0.300/M | 262,144 | tools |
| DeepSeek R1 Distill Llama 70B | $0.250/M | $0.750/M | $0.375/M | 128,000 | tools |
| Qwen2.5 VL 72B Instruct | $0.250/M | $0.750/M | $0.375/M | 32,000 | tools · vision |
| Reflection Beam | $0.250/M | $1.00/M | $0.438/M | 1,048,576 | tools · reasoning |
| DeepSeek V4.1 Flash | $0.300/M | $1.20/M | $0.525/M | 1,048,000 | tools · vision · reasoning |
| MiniMax M2.5 | $0.300/M | $1.20/M | $0.525/M | 196,608 | tools · reasoning |
| MiniMax M3 | $0.300/M | $1.20/M | $0.525/M | 1,048,576 | tools · vision · reasoning |
| Nvidia Nemotron 3 Super 120B A12B | $0.300/M | $0.900/M | $0.450/M | 262,144 | tools · reasoning |
| Qwen3.8 27B | $0.450/M | $3.00/M | $1.09/M | 262,144 | tools · reasoning |
| DeepSeek V3 | $0.500/M | $1.50/M | $0.750/M | 128,000 | tools |
| DeepSeek v3.0324 | $0.500/M | $1.50/M | $0.750/M | 128,000 | tools |
| Nvidia Llama 3.1 Nemotron Ultra 253B v1 | $0.600/M | $1.80/M | $0.900/M | 128,000 | tools |
| Qwen3.5 397B A17B | $0.600/M | $3.60/M | $1.35/M | 262,144 | tools · reasoning |
| Openbmb Minicpm V 4.5 | $0.658/M | $1.11/M | $0.771/M | 32,000 | vision |
| DeepSeek R1 | $0.800/M | $2.40/M | $1.20/M | 128,000 | tools · reasoning |
| DeepSeek R1 0528 | $0.800/M | $2.40/M | $1.20/M | 164,000 | tools · reasoning |
| Kimi K2.6 | $0.950/M | $4.00/M | $1.71/M | 262,144 | tools · vision · reasoning |
| Kimi K2.7 Code | $0.950/M | $4.00/M | $1.71/M | 262,144 | tools · vision · reasoning |
| Llama 3.1 405B Instruct | $1.00/M | $3.00/M | $1.50/M | 128,000 | tools |
| Nousresearch Hermes 3 Llama 3.1 405B | $1.00/M | $3.00/M | $1.50/M | 128,000 | tools |
| Nousresearch Hermes 4 405B | $1.00/M | $3.00/M | $1.50/M | 131,072 | tools · reasoning |
| Nvidia Nemotron 3 Ultra 550B A55B | $1.00/M | $3.00/M | $1.50/M | 1,048,576 | tools · reasoning |
| DeepSeek V4 Pro 0813 | $1.32/M | $3.96/M | $1.98/M | 979,000 | tools · reasoning |
| GLM 5.1 | $1.40/M | $4.40/M | $2.15/M | 202,752 | tools · reasoning |
| GLM 5.2 | $1.40/M | $4.40/M | $2.15/M | 1,048,576 | tools · reasoning |
| GLM 5.3 | $1.40/M | $4.40/M | $2.15/M | 1,024,000 | tools · reasoning |
| DeepSeek V4 Pro | $1.75/M | $3.50/M | $2.19/M | 1,048,576 | tools · reasoning |
| Kimi K3 | $3.00/M | $15.00/M | $6.00/M | 1,024,000 | tools · vision · reasoning |
embedding 4
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Baai BGE En Icl | $0.0100/M | — | — | 32,768 | |
| Baai BGE Multilingual Gemma2 | $0.0100/M | — | — | 8,192 | |
| Intfloat E5 Mistral 7B Instruct | $0.0100/M | — | — | 32,768 | |
| Qwen3 Embedding 8B | $0.0100/M | — | — | 40,960 |
FAQ
How many Nebius models are there?
61 Nebius models are listed across 2 modalities on this page. 61 have public per-token pricing.
How is Nebius pricing verified?
Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.
Which Nebius model is cheapest?
Input pricing on Nebius starts at $0.0100 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.
Can I route to Nebius via an OpenAI-compatible API?
Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a Nebius target, and call Nebius models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.