Nebius AI Pricing

Compare Nebius AI inference pricing for 29 models. European cloud infrastructure with GPU clusters for LLM inference.

Last updated: Apr 22, 2026

Nebius AI Overview

Total Models

LLMs

Embedding Models

$—

Cheapest LLM Input/1M

Provider	Model	Context	Input/1M	Output/1M
NB Nebius	deepseek-ai/DeepSeek-V3.2	—	$N/A	$N/A
NB Nebius	deepseek-ai/DeepSeek-V3.2-fast	—	$N/A	$N/A
NB Nebius	google/gemma-2-2b-it	—	$N/A	$N/A
NB Nebius	google/gemma-3-27b-it	—	$N/A	$N/A
NB Nebius	meta-llama/Llama-3.3-70B-Instruct	—	$N/A	$N/A
NB Nebius	meta-llama/Meta-Llama-3.1-8B-Instruct	—	$N/A	$N/A
NB Nebius	MiniMaxAI/MiniMax-M2.5	—	$N/A	$N/A
NB Nebius	MiniMaxAI/MiniMax-M2.5-fast	—	$N/A	$N/A
NB Nebius	moonshotai/Kimi-K2.5	—	$N/A	$N/A
NB Nebius	moonshotai/Kimi-K2.5-fast	—	$N/A	$N/A
NB Nebius	NousResearch/Hermes-4-405B	—	$N/A	$N/A
NB Nebius	NousResearch/Hermes-4-70B	—	$N/A	$N/A
NB Nebius	nvidia/Llama-3_1-Nemotron-Ultra-253B-v1	—	$N/A	$N/A
NB Nebius	nvidia/nemotron-3-super-120b-a12b	—	$N/A	$N/A
NB Nebius	nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B	—	$N/A	$N/A
NB Nebius	openai/gpt-oss-120b	—	$N/A	$N/A
NB Nebius	openai/gpt-oss-120b-fast	—	$N/A	$N/A
NB Nebius	PrimeIntellect/INTELLECT-3	—	$N/A	$N/A
NB Nebius	Qwen/Qwen2.5-VL-72B-Instruct	—	$N/A	$N/A
NB Nebius	Qwen/Qwen3-235B-A22B-Instruct-2507	—	$N/A	$N/A
NB Nebius	Qwen/Qwen3-235B-A22B-Thinking-2507-fast	—	$N/A	$N/A
NB Nebius	Qwen/Qwen3-30B-A3B-Instruct-2507	—	$N/A	$N/A
NB Nebius	Qwen/Qwen3-32B	—	$N/A	$N/A
NB Nebius	Qwen/Qwen3.5-397B-A17B	—	$N/A	$N/A
NB Nebius	Qwen/Qwen3.5-397B-A17B-fast	—	$N/A	$N/A
NB Nebius	Qwen/Qwen3-Embedding-8B	—	$N/A	$N/A
NB Nebius	Qwen/Qwen3-Next-80B-A3B-Thinking	—	$N/A	$N/A
NB Nebius	Qwen/Qwen3-Next-80B-A3B-Thinking-fast	—	$N/A	$N/A
NB Nebius	zai-org/GLM-5	—	$N/A	$N/A