Nebius AI models — pricing & benchmarks

Official siteDocsPricingAPI

Discover the most efficient way to build, tune and run your AI models and applications on top-notch NVIDIA® GPUs. Inference platform · OpenAI-compatible API · European · Gpu Cloud · Open Source · Serverless

Intelligence vs Price

Best value among Nebius models on this chart: DeepSeek V3 324 · QwQ 32B · Qwen3 30B A3B (and 3 more on the dashed frontier). Hover any dot for full pricing, or click a creator in the legend to isolate.

Nebius models

30 models, 30 with pricing

Model	Creator	Input Price, $	Output Price, $	Context	Max Output	Inference Providers	Intelligence	Coding
DeepSeek V3 324	DeepSeek	0.200	0.400	164K	16K	compare (13)	22.3#1	22.0#1
QwQ 32B	Alibaba	0.150	0.200	131K	16K	compare (8)	19.7#2	N/A
DeepSeek R1	DeepSeek	0.280	0.400	164K	66K	compare (14)	18.8#3	15.9#3
Llama 3.1 405B Instruct	Meta	0.120	0.300	131K	16K	compare (11)	17.4#4	14.5#4
DeepSeek V3	DeepSeek	0.200	0.200	400K	128K	compare (12)	16.5#5	16.4#2
DeepSeek R1 Distill Llama 70B	DeepSeek	0.200	0.375	131K	16K	compare (11)	16.0#6	11.4#7
Qwen2.5 72B Instruct	Alibaba	0.120	0.300	131K	16K	compare (8)	15.6#7	11.9#6
Qwen3 30B A3B	Alibaba	0.080	0.290	131K	20K	compare (7)	15.0#8	14.2#5
Llama 3.3 70B Instruct	Meta	0.100	0.200	131K	120K	compare (20)	14.5#9	10.7#9
Qwen2.5 32B Instruct	Alibaba	0.060	0.200	131K	8K	compare (3)	13.2#10	N/A
Llama 3.1 70B Instruct	Meta	0.100	0.100	131K	16K	compare (13)	12.5#11	10.9#8
Llama 3.1 8B Instruct	Meta	0.020	0.030	200K	128K	compare (20)	11.8#12	4.9#10
Mistral 7B Instruct	Mistral AI	0.010	0.100	127K	16K	compare (9)	7.4#13	N/A
BGE EN ICL	Baai	0.010	N/A	33K	N/A	compare (1)	N/A	N/A
BGE Multilingual Gemma2	Baai	0.010	N/A	8K	N/A	compare (1)	N/A	N/A
DeepSeek R1 528	DeepSeek	0.200	0.250	164K	33K	compare (12)	N/A	N/A
Gemma 3 27B Instruct	Google	0.060	0.160	131K	16K	compare (6)	N/A	N/A
Hermes 3 Llama 3.1 405B	Nous Research	1.00	1.00	131K	16K	compare (3)	N/A	N/A
Llama 3.1 Nemotron 1 Ultra 253B	NVIDIA	0.600	1.80	128K	N/A	compare (1)	N/A	N/A
Llama 3.3 Nemotron 1 Super 49B	NVIDIA	0.100	0.400	131K	N/A	compare (1)	N/A	N/A
LlamaGuard 3 8B	Meta	0.020	0.030	131K	16K	compare (5)	N/A	N/A
Nemo Instruct (24.07)	Mistral AI	0.020	0.040	131K	512	compare (5)	N/A	N/A
Qwen2 VL 72B Instruct	Alibaba	0.130	0.400	131K	2K	compare (3)	N/A	N/A
Qwen2 VL 7B Instruct	Alibaba	0.020	0.060	131K	N/A	compare (2)	N/A	N/A
Qwen2.5 Coder 7B	Alibaba	0.010	0.030	33K	8K	compare (3)	N/A	N/A
Qwen2.5 VL 72B Instruct	Alibaba	0.130	0.400	131K	8K	compare (7)	N/A	N/A
Qwen3 14B	Alibaba	0.060	0.200	132K	41K	compare (7)	N/A	N/A
Qwen3 235B A22B	Alibaba	0.071	0.100	262K	131K	compare (9)	N/A	N/A
Qwen3 32B	Alibaba	0.050	0.100	131K	41K	compare (15)	N/A	N/A
Qwen3 4B	Alibaba	0.030	0.030	131K	20K	compare (4)	N/A	N/A