Nscale LLM API pricing

Every model Nscale serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first. Verified against LiteLLM and OpenRouter daily.

Models served

on this provider

Cheapest input

$0.01

per 1M tokens

Cheapest output

$0.03

per 1M tokens

Max context

10.5M

tokens

					Model ID
Qwen2 5 Coder 3B Instruct	Alibaba	n/a	$0.01	$0.03	nscale/Qwen/Qwen2.5-Coder-3B-Instruct
Qwen2 5 Coder 7B Instruct	Alibaba	n/a	$0.01	$0.03	nscale/Qwen/Qwen2.5-Coder-7B-Instruct
DeepSeek R1 Distill Llama 8B	DeepSeek	131K	$0.03	$0.03	nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Llama 3.1 8B Instruct	Meta	200K	$0.03	$0.03	nscale/meta-llama/Llama-3.1-8B-Instruct
Qwen2 5 Coder 32B Instruct	Alibaba	33K	$0.06	$0.20	nscale/Qwen/Qwen2.5-Coder-32B-Instruct
DeepSeek R1 Distill Qwen 14B	DeepSeek	131K	$0.07	$0.07	nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
DeepSeek R1 Distill Qwen 1 5B	DeepSeek	n/a	$0.09	$0.09	nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Llama 4 Scout 17B 16e Instruct	Meta	10.5M	$0.09	$0.29	nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct
DeepSeek R1 Distill Qwen 32B	DeepSeek	131K	$0.15	$0.15	nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
QwQ 32B	Alibaba	131K	$0.18	$0.20	nscale/Qwen/QwQ-32B
Llama 3.3 70B Instruct	Meta	131K	$0.20	$0.20	nscale/meta-llama/Llama-3.3-70B-Instruct
DeepSeek R1 Distill Qwen 7B	DeepSeek	131K	$0.20	$0.20	nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
R1 Distill Llama 70B	DeepSeek	131K	$0.38	$0.38	nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Mixtral 8x22B Instruct V0 1	Mistral	66K	$0.60	$0.60	nscale/mistralai/mixtral-8x22b-instruct-v0.1

Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI