Nscale API pricing
Hosted14 language, 2 image models
As of Oct 14, 2026, Nscale lists 16 language and image models through its API. Its cheapest language model is Qwen2.5 Coder 7B Instruct at $0.01 input / $0.03 output per million tokens.
Language models (14)
Prices per million tokens.
nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
- Input
- $0.375
- Output
- $0.375
- Context
- —
nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
- Input
- $0.07
- Output
- $0.07
- Context
- —
nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
- Input
- $0.15
- Output
- $0.15
- Context
- —
nscale/meta-llama/Llama-3.3-70B-Instruct
- Input
- $0.20
- Output
- $0.20
- Context
- —
Llama 4 Scout 17B 16e Instruct
nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct
- Input
- $0.09
- Output
- $0.29
- Context
- —
nscale/meta-llama/Llama-3.1-8B-Instruct
- Input
- $0.03
- Output
- $0.03
- Context
- —
nscale/Qwen/Qwen2.5-Coder-7B-Instruct
- Input
- $0.01
- Output
- $0.03
- Context
- —
nscale/Qwen/Qwen2.5-Coder-32B-Instruct
- Input
- $0.06
- Output
- $0.20
- Context
- —
nscale/Qwen/QwQ-32B
- Input
- $0.18
- Output
- $0.20
- Context
- —
DeepSeek R1 Distill Llama 8B
nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B
- Input
- $0.025
- Output
- $0.025
- Context
- —
DeepSeek R1 Distill Qwen 1.5B
nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
- Input
- $0.09
- Output
- $0.09
- Context
- —
DeepSeek R1 Distill Qwen 7B
nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
- Input
- $0.20
- Output
- $0.20
- Context
- —
Mixtral 8x22b Instruct V0.1
nscale/mistralai/mixtral-8x22b-instruct-v0.1
- Input
- $0.60
- Output
- $0.60
- Context
- —
Qwen2.5 Coder 3B Instruct
nscale/Qwen/Qwen2.5-Coder-3B-Instruct
- Input
- $0.01
- Output
- $0.03
- Context
- —
Image models (2)
Prices in USD from LiteLLM and models.dev, checked daily; confirm on Nscale's pricing page before you rely on a number.