input_mtok and output_mtok, US dollars per 1,000,000 tokens. Source of truth: prices/providers/huggingface_together.yml.
| Model | Name | Input $ / Mtok | Output $ / Mtok | Context |
|---|---|---|---|---|
EssentialAI/rnj-1-instruct | rnj-1-instruct | $0.15 | $0.15 | 32,768 |
Qwen/Qwen2.5-7B-Instruct | Qwen2.5-7B-Instruct | $0.3 | $0.3 | 32,768 |
Qwen/Qwen3-235B-A22B-Instruct-2507 | Qwen3-235B-A22B-Instruct-2507 | $0.2 | $0.6 | 262,144 |
Qwen/Qwen3-Coder-480B-A35B-Instruct | Qwen3-Coder-480B-A35B-Instruct | $2 | $2 | 262,144 |
Qwen/Qwen3-Coder-Next-FP8 | Qwen3-Coder-Next-FP8 | $0.5 | $1.2 | 262,144 |
Qwen/Qwen3-Next-80B-A3B-Instruct | Qwen3-Next-80B-A3B-Instruct | $0.15 | $1.5 | 262,144 |
Qwen/Qwen3-VL-8B-Instruct | Qwen3-VL-8B-Instruct | $0.18 | $0.68 | 262,144 |
Qwen/Qwen3.5-397B-A17B | Qwen3.5-397B-A17B | $0.6 | $3.6 | 262,144 |
Qwen/Qwen3.5-9B | Qwen3.5-9B | $0.1 | $0.15 | 262,144 |
deepcogito/cogito-671b-v2.1 | cogito-671b-v2.1 | $1.25 | $1.25 | 163,840 |
deepseek-ai/DeepSeek-R1 | DeepSeek-R1 | $3 | $7 | 163,840 |
deepseek-ai/DeepSeek-V3 | DeepSeek-V3 | $1.25 | $1.25 | 131,072 |
deepseek-ai/DeepSeek-V3.1 | DeepSeek-V3.1 | $0.6 | $1.7 | 131,072 |
google/gemma-3n-E4B-it | gemma-3n-E4B-it | $0.02 | $0.04 | 32,768 |
meta-llama/Llama-3.3-70B-Instruct | Llama-3.3-70B-Instruct | $0.88 | $0.88 | 131,072 |
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | Llama-4-Maverick-17B-128E-Instruct-FP8 | $0.27 | $0.85 | 1,048,576 |
moonshotai/Kimi-K2.5 | Kimi-K2.5 | $0.5 | $2.8 | 262,144 |
openai/gpt-oss-120b | gpt-oss-120b | $0.15 | $0.6 | 131,072 |
openai/gpt-oss-20b | gpt-oss-20b | $0.05 | $0.2 | 131,072 |
zai-org/GLM-4.5-Air-FP8 | GLM-4.5-Air-FP8 | $0.2 | $1.1 | 131,072 |
zai-org/GLM-4.6 | GLM-4.6 | $0.6 | $2.2 | 202,752 |
zai-org/GLM-4.7-FP8 | GLM-4.7-FP8 | $0.45 | $2 | 202,752 |
zai-org/GLM-5 | GLM-5 | $1 | $3.2 | 202,752 |