API provider

Nscale

What this provider sells and at what price. A price belongs to the offer, not the model: at another provider the same model may cost several times more or less.

14 models with a price
resold models
aggregate databases price source

Models & prices

Model Developer Input, $/1M Output, $/1M Blended, $/1M
Mixtral 8x22B Mistral AI $0.6 $0.6 $0.6
Qwen: QwQ 32B Alibaba (Qwen) $0.18 $0.2 $0.19
Llama 4 Scout 17B 16E Instruct Meta AI $0.09 $0.29 $0.14
DeepSeek R1 Distill Llama 70B DeepSeek $0.38 $0.38 $0.38
Deepseek R1 Distill Qwen 32B DeepSeek $0.15 $0.15 $0.15
DeepSeek R1 Distill Llama 8B DeepSeek $0.03 $0.03 $0.03
DeepSeek R1 Distill Qwen 1.5B DeepSeek $0.09 $0.09 $0.09
DeepSeek R1 Distill Qwen 14B DeepSeek $0.07 $0.07 $0.07
DeepSeek R1 Distill Qwen 7B DeepSeek $0.2 $0.2 $0.2
Llama 3.3 70B Instruct Meta AI $0.2 $0.2 $0.2
Qwen2.5 Coder 32b Instruct Alibaba (Qwen) $0.06 $0.2 $0.1
Llama 3.1 8B Meta AI $0.03 $0.03 $0.03
Qwen2.5 Coder 3B Instruct Alibaba (Qwen) $0.01 $0.03 $0.02
Qwen2.5-Coder 7B Instruct Alibaba (Qwen) $0.01 $0.03 $0.02

These are this provider’s prices, not the market’s best: the same model may cost differently at another provider. The blended price uses a three-input-tokens-to-one-output scheme — the way to compare models whose output costs several times more than input. Only the base per-token rate counts, without batch or discounted tiers; input and output come from one price list, not two minimums from different ones.