Nscale
Inference
Models
16
Frontier
0
Cheaper here
0
than the headline price
Dearer here
3
than the headline price
Cheapest listing per model, USD per million tokens.
| Model | Here, input / output | Released |
|---|---|---|
| Llama 4 Scout 17B 16e Instruct MetaLlama-4-Scout-17B-16E-Instruct | $0.09 / $0.29 | Apr 2025 |
| Llama 3.3 70B Instruct MetaLlama-3.3-70B-Instruct | $0.20 / $0.20 | Dec 2024 |
| Qwen2.5 Coder 32B Instruct Alibaba QwenQwen2.5-Coder-32B-Instruct | $0.06 / $0.20 | Nov 2024 |
| Llama 3.1 8B Instruct MetaLlama-3.1-8B-Instruct | $0.03 / $0.03 +9% vs Novita AI | Jul 2024 |
| DeepSeek R1 Distill Llama 70B DeepSeekDeepSeek-R1-Distill-Llama-70B | $0.375 / $0.375 +25% vs DeepInfra | - |
| DeepSeek R1 Distill Qwen 32B DeepSeekDeepSeek-R1-Distill-Qwen-32B | $0.15 / $0.15 | - |
| QwQ 32B Alibaba QwenQwQ-32B | $0.18 / $0.20 | - |
| DeepSeek R1 Distill Qwen 14B DeepSeekDeepSeek-R1-Distill-Qwen-14B | $0.07 / $0.07 | - |
| DeepSeek R1 Distill Llama 8B DeepSeekDeepSeek-R1-Distill-Llama-8B | $0.025 / $0.025 | - |
| DeepSeek R1 Distill Qwen 7B DeepSeekDeepSeek-R1-Distill-Qwen-7B | $0.20 / $0.20 +60% vs GMI Cloud | - |
| DeepSeek R1 Distill Qwen 1 5B DeepSeekDeepSeek-R1-Distill-Qwen-1.5B | $0.09 / $0.09 | - |
| Mixtral 8x22b Instruct V0.1 Mistral AImixtral-8x22b-instruct-v0.1 | $0.60 / $0.60 | - |
| Qwen2.5 Coder 3B Instruct Alibaba QwenQwen2.5-Coder-3B-Instruct | $0.01 / $0.03 | - |
| Qwen2.5 Coder 7B Instruct Alibaba QwenQwen2.5-Coder-7B-Instruct | $0.01 / $0.03 | - |
| FLUX 1 Schnell Black Forest Labs · ImageFLUX.1-schnell | Not listed | - |
| Stable Diffusion XL Base 1.0 Independent · Imagestable-diffusion-xl-base-1.0 | Not listed | - |