Hugging Face Inference Providers models and pricing
We track 85 models on Hugging Face Inference Providers (86 listings) from 12 labs. The cheapest paid model is Qwen 3 Embedding 4B, at $0.01 per million input tokens and Free per million output tokens. Input prices range from $0.01 to $3 and output prices from $0.06 to $15 per million tokens. 1 model is listed free. The largest context window is 1M tokens (Inkling 2 Small, Kimi K3.1 Pro Highspeed and 10 other models). Prices last verified 18 Nov 2026.
Prices in USD per million tokens. Official site
Cheapest models on Hugging Face Inference Providers
- Qwen 3 Embedding 4B$0.01 / Free
- Qwen 3 Embedding 8B$0.01 / Free
- Llama 3.1 8B Instruct$0.06 / $0.06
- Gemma 3 4B IT$0.05 / $0.10
- AutoGLM Phone 9B Multilingual$0.04 / $0.14
Input / output per million tokens, paid models, by combined price.
Newest models on Hugging Face Inference Providers
- Inkling 2 Small5 Nov 2026
- Kimi K3.1 Pro Highspeed23 Oct 2026
- MiniMax-M3.1-Flash19 Oct 2026
- DeepSeek V4.1 Flash 101717 Oct 2026
- DeepSeek V4.1 Flash10 Sept 2026
By the lab's release date.
All Hugging Face Inference Providers models and prices
| Model | Lab | Input | Output | Context | Source |
|---|---|---|---|---|---|
| Inkling 2 Small thinkingmachines/Inkling-2-Small | Thinkingmachines | $0.30 | $1 | 1M | models.dev |
| Kimi K3.1 Pro Highspeed moonshotai/Kimi-K3.1-Pro | Moonshot AI | $2 | $10 | 1M | models.dev |
| MiniMax-M3.1-Flash MiniMaxAI/MiniMax-M3.1-Flash | MiniMax | $0.15 | $0.60 | 1M | models.dev |
| DeepSeek V4.1 Flash 1017 deepseek-ai/DeepSeek-V4.1-Flash-1017 | DeepSeek | $0.30 | $1.20 | 1M | models.dev |
| DeepSeek V4.1 Flash deepseek-ai/DeepSeek-V4.1-Flash | DeepSeek | $0.30 | $1.20 | 1M | models.dev |
| Tencent Hy4 Preview tencent/Hy4-preview | Tencent (Hunyuan) | $0.83 | $2.50 | 1M | models.dev |
| GLM-5.3-Flash zai-org/GLM-5.3-Flash | Zhipu AI (Z.ai) | $0.15 | $0.50 | 1M | models.dev |
| DeepSeek V4 Flash Vision Exp deepseek-ai/DeepSeek-V4-Flash-Vision-Exp | DeepSeek | $0.44 | $1.32 | 1M | models.dev |
| GLM-5.3 zai-org/GLM-5.3 | Zhipu AI (Z.ai) | $1.40 | $4.40 | 1M | models.dev |
| Qwen3.8 27B Qwen/Qwen3.8-27B | Alibaba (Qwen) | $0.40 | $3 | 262K | models.dev |
| DeepSeek V4 Pro deepseek-ai/DeepSeek-V4-Pro-0813 | DeepSeek | $1.32 | $3.96 | 1M | models.dev |
| DeepSeek V4 Pro deepseek-ai/DeepSeek-V4-Pro | DeepSeek | $0.43 | $0.87 | 1M | models.dev |
| Qwen3.8 2.4T A95B Qwen/Qwen3.8-2.4T-A95B | Alibaba (Qwen) | $2.50 | $6.25 | 262K | models.dev |
| DeepSeek V4 Flash 0731 deepseek-ai/DeepSeek-V4-Flash-0731 | DeepSeek | $0.14 | $0.28 | 1M | models.dev |
| Inkling Small thinkingmachines/Inkling-Small | Thinkingmachines | $0.50 | $1.20 | 524K | models.dev |
| Kimi K3 moonshotai/Kimi-K3 | Moonshot AI | $3 | $15 | 1M | models.dev |
| Inkling thinkingmachines/Inkling | Thinkingmachines | $1 | $4.05 | 1M | models.dev |
| Hy3 tencent/Hy3 | Tencent (Hunyuan) | $0.14 | $0.58 | 262K | models.dev |
| GLM-5.2 zai-org/GLM-5.2 | Zhipu AI (Z.ai) | $1.40 | $4.40 | 262K | models.dev |
| Kimi K2.7 Code moonshotai/Kimi-K2.7-Code | Moonshot AI | $0.95 | $4 | 262K | models.dev |
| MiniMax-M3 MiniMaxAI/MiniMax-M3 | MiniMax | $0.30 | $1.20 | 524K | models.dev |
| Step 3.7 Flash stepfun-ai/Step-3.7-Flash | StepFun | $0.20 | $1.15 | 262K | models.dev |
| DeepSeek V4 Flash deepseek-ai/DeepSeek-V4-Flash | DeepSeek | $0.14 | $0.28 | 1M | models.dev |
| Qwen3.6 27B Qwen/Qwen3.6-27B | Alibaba (Qwen) | $0.47 | $3.19 | 262K | models.dev |
| MiMo-V2.5-Pro XiaomiMiMo/MiMo-V2.5-Pro | Xiaomi (MiMo) | $1 | $3 | 1M | models.dev |
| MiMo-V2.5 XiaomiMiMo/MiMo-V2.5 | Xiaomi (MiMo) | $0.40 | $2 | 262K | models.dev |
| Kimi K2.6 moonshotai/Kimi-K2.6 | Moonshot AI | $0.95 | $4 | 262K | models.dev |
| Qwen3.6 35B-A3B Qwen/Qwen3.6-35B-A3B | Alibaba (Qwen) | $0.15 | $0.95 | 262K | models.dev |
| GLM-5.1 zai-org/GLM-5.1 | Zhipu AI (Z.ai) | $1 | $3.20 | 203K | models.dev |
| Gemma 4 26B A4B IT google/gemma-4-26B-A4B-it | Google DeepMind | $0.13 | $0.40 | 262K | models.dev |
| Gemma 4 31B IT google/gemma-4-31B-it | Google DeepMind | $0.14 | $0.40 | 262K | models.dev |
| MiniMax-M2.7 MiniMaxAI/MiniMax-M2.7 | MiniMax | $0.30 | $1.20 | 205K | models.dev |
| Qwen3.5 122B-A10B Qwen/Qwen3.5-122B-A10B | Alibaba (Qwen) | $0.40 | $3.20 | 262K | models.dev |
| Qwen3.5 35B-A3B Qwen/Qwen3.5-35B-A3B | Alibaba (Qwen) | $0.25 | $2 | 262K | models.dev |
| Qwen3.5 27B Qwen/Qwen3.5-27B | Alibaba (Qwen) | $0.30 | $2.40 | 262K | models.dev |
| Qwen/Qwen3.5-9B Qwen/Qwen3.5-9B | Alibaba (Qwen) | $0.17 | $0.25 | 262K | models.dev |
| Qwen3.5 397B-A17B Qwen/Qwen3.5-397B-A17B | Alibaba (Qwen) | $0.60 | $3.60 | 262K | models.dev |
| MiniMax-M2.5 MiniMaxAI/MiniMax-M2.5 | MiniMax | $0.30 | $1.20 | 205K | models.dev |
| GLM-5 zai-org/GLM-5 | Zhipu AI (Z.ai) | $1 | $3.20 | 203K | models.dev |
| Qwen3 Coder Next Qwen/Qwen3-Coder-Next | Alibaba (Qwen) | $0.20 | $1.50 | 262K | models.dev |
| Step 3.5 Flash stepfun-ai/Step-3.5-Flash | StepFun | $0.10 | $0.30 | 262K | models.dev |
| Kimi K2.5 moonshotai/Kimi-K2.5 | Moonshot AI | $0.60 | $3 | 262K | models.dev |
| GLM-4.7-Flash zai-org/GLM-4.7-Flash | Zhipu AI (Z.ai) | Free | Free | 200K | models.dev |
| MiniMax-M2.1 MiniMaxAI/MiniMax-M2.1 | MiniMax | $0.30 | $1.20 | 205K | models.dev |
| GLM-4.7 zai-org/GLM-4.7 | Zhipu AI (Z.ai) | $0.60 | $2.20 | 205K | models.dev |
| AutoGLM Phone 9B Multilingual zai-org/AutoGLM-Phone-9B-Multilingual | Zhipu AI (Z.ai) | $0.04 | $0.14 | 66K | models.dev |
| GLM-4.6V zai-org/GLM-4.6V | Zhipu AI (Z.ai) | $0.30 | $0.90 | 131K | models.dev |
| GLM-4.6V-Flash zai-org/GLM-4.6V-Flash | Zhipu AI (Z.ai) | $0.30 | $0.90 | 131K | models.dev |
| DeepSeek V3.2 deepseek-ai/DeepSeek-V3.2 | DeepSeek | $0.28 | $0.40 | 164K | models.dev |
| Kimi-K2-Thinking moonshotai/Kimi-K2-Thinking | Moonshot AI | $0.60 | $2.50 | 262K | models.dev |
| MiniMax-M2 MiniMaxAI/MiniMax-M2 | MiniMax | $0.30 | $1.20 | 205K | models.dev |
| Qwen3 VL 30B A3B Instruct Qwen/Qwen3-VL-30B-A3B-Instruct | Alibaba (Qwen) | $0.20 | $0.70 | 131K | models.dev |
| GLM-4.6 zai-org/GLM-4.6 | Zhipu AI (Z.ai) | $0.55 | $2.20 | 205K | models.dev |
| Qwen3 VL 235B A22B Instruct Qwen/Qwen3-VL-235B-A22B-Instruct | Alibaba (Qwen) | $0.30 | $1.50 | 131K | models.dev |
| Qwen3 VL 235B A22B Thinking Qwen/Qwen3-VL-235B-A22B-Thinking | Alibaba (Qwen) | $0.98 | $3.95 | 131K | models.dev |
| Kimi-K2-Instruct-0905 moonshotai/Kimi-K2-Instruct-0905 | Moonshot AI | $1 | $3 | 262K | models.dev |
| Qwen3-Next 80B-A3B Instruct Qwen/Qwen3-Next-80B-A3B-Instruct | Alibaba (Qwen) | $0.25 | $1 | 262K | models.dev |
| DeepSeek-V3.1 deepseek-ai/DeepSeek-V3.1 | DeepSeek | $0.27 | $1 | 131K | models.dev |
| GLM-4.5V zai-org/GLM-4.5V | Zhipu AI (Z.ai) | $0.60 | $1.80 | 66K | models.dev |
| gpt-oss-20b openai/gpt-oss-20b | OpenAI | $0.10 | $0.50 | 131K | models.dev |
| gpt-oss-120b openai/gpt-oss-120b | OpenAI | $0.25 | $0.69 | 131K | models.dev |
| GLM-4.5-Air zai-org/GLM-4.5-Air | Zhipu AI (Z.ai) | $0.13 | $0.85 | 131K | models.dev |
| GLM-4.5 zai-org/GLM-4.5 | Zhipu AI (Z.ai) | $0.60 | $2.20 | 131K | models.dev |
| Qwen3-235B-A22B-Thinking-2507 Qwen/Qwen3-235B-A22B-Thinking-2507 | Alibaba (Qwen) | $0.30 | $3 | 262K | models.dev |
| Qwen3 235B A22B Instruct 2507 Qwen/Qwen3-235B-A22B-Instruct-2507 | Alibaba (Qwen) | $0.85 | $2.56 | 262K | models.dev |
| Kimi-K2-Instruct moonshotai/Kimi-K2-Instruct | Moonshot AI | $1 | $3 | 131K | models.dev |
| MiniMax M1 80K MiniMaxAI/MiniMax-M1-80k | MiniMax | $0.55 | $2.20 | 1M | models.dev |
| Qwen 3 Embedding 4B Qwen/Qwen3-Embedding-4B | Alibaba (Qwen) | $0.01 | Free | 33K | models.dev |
| Qwen 3 Embedding 8B Qwen/Qwen3-Embedding-8B | Alibaba (Qwen) | $0.01 | Free | 33K | models.dev |
| DeepSeek-R1-0528 deepseek-ai/DeepSeek-R1-0528 | DeepSeek | $3 | $5 | 164K | models.dev |
| Llama Guard 4 12B meta-llama/Llama-Guard-4-12B | Meta | $0.18 | $0.18 | 164K | models.dev |
| Qwen3-30B-A3B Qwen/Qwen3-30B-A3B | Alibaba (Qwen) | $0.12 | $0.50 | 41K | models.dev |
| Qwen3 235B-A22B Qwen/Qwen3-235B-A22B | Alibaba (Qwen) | $0.20 | $0.80 | 41K | models.dev |
| Qwen3 32B Qwen/Qwen3-32B | Alibaba (Qwen) | $0.29 | $0.59 | 131K | models.dev |
| Qwen3-Coder 30B-A3B Instruct Qwen/Qwen3-Coder-30B-A3B-Instruct | Alibaba (Qwen) | $0.07 | $0.26 | 262K | models.dev |
| Qwen3-Coder 480B-A35B Instruct Qwen/Qwen3-Coder-480B-A35B-Instruct | Alibaba (Qwen) | $2 | $2 | 262K | models.dev |
| Qwen3 8B Qwen/Qwen3-8B | Alibaba (Qwen) | $0.07 | $0.18 | 41K | models.dev |
| DeepSeek V3 0324 deepseek-ai/DeepSeek-V3-0324 | DeepSeek | $0.27 | $1.12 | 164K | models.dev |
| Gemma 3 12B IT google/gemma-3-12b-it | Google DeepMind | $0.05 | $0.15 | 131K | models.dev |
| Gemma 3 4B IT google/gemma-3-4b-it | Google DeepMind | $0.05 | $0.10 | 131K | models.dev |
| Gemma 3 27B IT google/gemma-3-27b-it | Google DeepMind | $0.08 | $0.16 | 131K | models.dev |
| DeepSeek-R1 deepseek-ai/DeepSeek-R1 | DeepSeek | $0.70 | $2.50 | 64K | models.dev |
| DeepSeek-V3 deepseek-ai/DeepSeek-V3 | DeepSeek | $0.40 | $1.30 | 64K | models.dev |
| Llama-3.3-70B-Instruct meta-llama/Llama-3.3-70B-Instruct | Meta | $0.59 | $0.79 | 131K | models.dev |
| Qwen2.5-Coder-32B-Instruct Qwen/Qwen2.5-Coder-32B-Instruct | Alibaba (Qwen) | $0.06 | $0.20 | 131K | models.dev |
| Llama 3.1 8B Instruct meta-llama/Llama-3.1-8B-Instruct | Meta | $0.06 | $0.06 | 131K | models.dev |
Frequently asked questions
How much does Hugging Face Inference Providers cost per million tokens?
Prices on Hugging Face Inference Providers depend on the model. Across the 85 models we track, input costs $0.01 to $3 per million tokens and output costs $0.06 to $15 per million tokens. 1 model is listed free. Prices last verified 18 Nov 2026.
What is the cheapest model on Hugging Face Inference Providers?
Qwen 3 Embedding 4B from Alibaba (Qwen) is the cheapest paid model we track on Hugging Face Inference Providers, at $0.01 per million input tokens and Free per million output tokens. Next are Qwen 3 Embedding 8B ($0.01 / Free) and Llama 3.1 8B Instruct ($0.06 / $0.06). Prices last verified 18 Nov 2026.
How many models does Hugging Face Inference Providers offer?
We currently track 85 active models on Hugging Face Inference Providers from 12 labs, led by Alibaba (Qwen) (25), Zhipu AI (Z.ai) (14), DeepSeek (12) and Moonshot AI (8).
Which model on Hugging Face Inference Providers has the largest context window?
Inkling 2 Small, Kimi K3.1 Pro Highspeed and 10 other models share the largest context window we track on Hugging Face Inference Providers: 1,048,576 tokens (1M).