input_mtok and output_mtok, US dollars per 1,000,000 tokens. Source of truth: prices/providers/huggingface_nscale.yml.
| Model | Name | Input $ / Mtok | Output $ / Mtok | Context |
|---|---|---|---|---|
Qwen/QwQ-32B | QwQ-32B | $0.18 | $0.2 | 131,072 |
Qwen/Qwen2.5-Coder-32B-Instruct | Qwen2.5-Coder-32B-Instruct | $0.06 | $0.2 | 131,072 |
Qwen/Qwen2.5-Coder-3B-Instruct | Qwen2.5-Coder-3B-Instruct | $0.01 | $0.03 | 32,768 |
Qwen/Qwen2.5-Coder-7B-Instruct | Qwen2.5-Coder-7B-Instruct | $0.01 | $0.03 | 131,072 |
Qwen/Qwen3-14B | Qwen3-14B | $0.07 | $0.2 | 40,960 |
Qwen/Qwen3-235B-A22B | Qwen3-235B-A22B | $0.2 | $0.6 | 32,000 |
Qwen/Qwen3-32B | Qwen3-32B | $0.08 | $0.25 | 40,960 |
Qwen/Qwen3-4B-Instruct-2507 | Qwen3-4B-Instruct-2507 | $0.01 | $0.03 | 262,144 |
Qwen/Qwen3-4B-Thinking-2507 | Qwen3-4B-Thinking-2507 | $0.01 | $0.03 | 262,144 |
Qwen/Qwen3-8B | Qwen3-8B | $0.07 | $0.18 | 40,960 |
deepseek-ai/DeepSeek-R1-Distill-Llama-70B | DeepSeek-R1-Distill-Llama-70B | $0.75 | $0.75 | 131,072 |
deepseek-ai/DeepSeek-R1-Distill-Llama-8B | DeepSeek-R1-Distill-Llama-8B | $0.05 | $0.05 | 131,072 |
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B | DeepSeek-R1-Distill-Qwen-1.5B | $0.1 | $0.1 | 131,072 |
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | DeepSeek-R1-Distill-Qwen-32B | $0.3 | $0.3 | 131,072 |
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B | DeepSeek-R1-Distill-Qwen-7B | $0.15 | $0.15 | 131,072 |
meta-llama/Llama-3.1-8B-Instruct | Llama-3.1-8B-Instruct | $0.06 | $0.06 | 131,072 |
meta-llama/Llama-3.3-70B-Instruct | Llama-3.3-70B-Instruct | $0.4 | $0.4 | 131,072 |
meta-llama/Llama-4-Scout-17B-16E-Instruct | Llama-4-Scout-17B-16E-Instruct | $0.09 | $0.29 | 890,000 |
openai/gpt-oss-120b | gpt-oss-120b | $0.1 | $0.4 | 131,072 |
openai/gpt-oss-20b | gpt-oss-20b | $0.05 | $0.2 | 131,072 |