Nscale AI models — pricing & benchmarks

Official siteDocsPricingAPI

Nscale full-stack AI cloud platform and services are designed for scale, resilience, and speed. Inference platform · OpenAI-compatible API · European · Gpu Cloud · Image Generation · Open Source · Serverless

Intelligence vs Price

Best value among Nscale models on this chart: QwQ 32B · DeepSeek R1 Distill Qwen 32B · DeepSeek R1 Distill Qwen 14B (and 4 more on the dashed frontier). Hover any dot for full pricing, or click a creator in the legend to isolate.

Nscale models

14 models, 14 with pricing

Model	Creator	Input Price, $	Output Price, $	Context	Max Output	Inference Providers	Intelligence	Coding
QwQ 32B	Alibaba	0.150	0.200	131K	16K	compare (8)	19.7#1	N/A
DeepSeek R1 Distill Qwen 32B	DeepSeek	0.150	0.150	131K	33K	compare (7)	17.2#2	N/A
DeepSeek R1 Distill Llama 70B	DeepSeek	0.200	0.375	131K	16K	compare (11)	16.0#3	11.4#1
DeepSeek R1 Distill Qwen 14B	DeepSeek	0.070	0.070	131K	16K	compare (5)	15.8#4	N/A
Llama 3.3 70B Instruct	Meta	0.100	0.200	131K	120K	compare (20)	14.5#5	10.7#2
Qwen2.5 Coder 32B Instruct	Alibaba	0.050	0.100	131K	33K	compare (8)	12.9#6	N/A
DeepSeek R1 Distill Llama 8B	DeepSeek	0.025	0.025	131K	N/A	compare (3)	12.1#7	N/A
Llama 3.1 8B Instruct	Meta	0.020	0.030	200K	128K	compare (20)	11.8#8	4.9#3
Qwen2.5 Coder 7B Instruct	Alibaba	0.010	0.030	131K	8K	compare (4)	10.0#9	N/A
Mixtral 8x22B Instruct	Mistral AI	0.600	0.600	66K	2K	compare (6)	9.8#10	N/A
DeepSeek R1 Distill Qwen 1.5B	DeepSeek	0.090	0.090	131K	N/A	compare (3)	9.1#11	N/A
DeepSeek R1 Distill Qwen 7B	DeepSeek	0.072	0.144	131K	16K	compare (4)	N/A	N/A
Llama 4 17B Scout Instruct	Meta	0.050	0.100	10.0M	16K	compare (11)	N/A	N/A
Qwen2.5 Coder 3B Instruct	Alibaba	0.010	0.030	33K	N/A	compare (3)	N/A	N/A