Inference Catalog | Inference Endpoints by Hugging Face

gemma-3-12b-it

Image-Text-to-Text

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L40S

$ 1.8

/ hour

gemma-3-27b-it

Image-Text-to-Text

TGI

Accelerated Text Generation Inference

GPU 4x Nvidia L4

$ 3.8

/ hour

ibm-granite /

granite-3.1-8b-base

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L40S

$ 1.8

/ hour

Llama-2-13b-chat-hf

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L40S

$ 1.8

/ hour

Llama-2-13b-hf

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L40S

$ 1.8

/ hour

Llama-2-70b-chat-hf

Text Generation

TGI

Accelerated Text Generation Inference

GPU 4x Nvidia L40S

$ 8.3

/ hour

Llama-2-70b-hf

Text Generation

TGI

Accelerated Text Generation Inference

GPU 4x Nvidia L40S

$ 8.3

/ hour

Llama-2-7b-chat-hf

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L40S

$ 1.8

/ hour

Llama-2-7b-hf

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L40S

$ 1.8

/ hour

Llama-3.1-70B

Text Generation

TGI

Accelerated Text Generation Inference

GPU 4x Nvidia L40S

$ 8.3

/ hour

Llama-3.1-70B-Instruct

Text Generation

TGI

Accelerated Text Generation Inference

GPU 4x Nvidia L40S

$ 8.3

/ hour

Llama-3.1-8B

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L4

$ 0.8

/ hour

Llama-3.1-8B-Instruct

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L4

$ 0.8

/ hour

Llama-3.2-11B-Vision-Instruct

Image-Text-to-Text

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L40S

$ 1.8

/ hour

Llama-3.2-1B

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L4

$ 0.8

/ hour

Llama-3.2-1B-Instruct

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L4

$ 0.8

/ hour

Llama-3.2-3B

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L4

$ 0.8

/ hour

Llama-3.2-3B-Instruct

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L4

$ 0.8

/ hour

llava-hf /

llava-v1.6-vicuna-13b-hf

Image-Text-to-Text

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L40S

$ 1.8

/ hour

Meta-Llama-3-70B

Text Generation

TGI

Accelerated Text Generation Inference

GPU 4x Nvidia A100

$ 16

/ hour

Meta-Llama-3-70B-Instruct

Text Generation

TGI

Accelerated Text Generation Inference

GPU 4x Nvidia A100

$ 16

/ hour

Meta-Llama-3-8B

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L4

$ 0.8

/ hour

Meta-Llama-3-8B-Instruct

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L4

$ 0.8

/ hour

Mistral-7B-Instruct-v0.3

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L4

$ 0.8

/ hour

Mistral-7B-v0.3

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L4

$ 0.8

/ hour

Mistral-Nemo-Instruct-2407

Text Generation

TGI

Accelerated Text Generation Inference

GPU 4x Nvidia L4

$ 3.8

/ hour

Mistral-Small-24B-Instruct-2501

Text Generation

TGI

Accelerated Text Generation Inference

GPU 4x Nvidia L4

$ 3.8

/ hour

Mixtral-8x22B-Instruct-v0.1

Text Generation

TGI

Accelerated Text Generation Inference

GPU 8x Nvidia L40S

$ 23.5

/ hour

Mixtral-8x7B-Instruct-v0.1

Text Generation

TGI

Accelerated Text Generation Inference

GPU 2x Nvidia A100

$ 8

/ hour

Mixtral-8x7B-v0.1

Text Generation

TGI

Accelerated Text Generation Inference

GPU 2x Nvidia A100

$ 8

/ hour

Intel /

neural-chat-7b-v3-1

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L4

$ 0.8

/ hour

Intel /

neural-chat-7b-v3-3

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L4

$ 0.8

/ hour

openchat /

openchat-3.5-0106

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L4

$ 0.8

/ hour

paligemma2-10b-mix-224

Image-Text-to-Text

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L40S

$ 1.8

/ hour

paligemma2-10b-mix-448

Image-Text-to-Text

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L40S

$ 1.8

/ hour

paligemma2-3b-mix-448

Image-Text-to-Text

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L4

$ 0.8

/ hour

microsoft /

Phi-3-mini-128k-instruct

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L4

$ 0.8

/ hour

microsoft /

Phi-3-mini-4k-instruct

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L4

$ 0.8

/ hour

microsoft /

phi-4

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L40S

$ 1.8

/ hour

Qwen2.5-14B-Instruct

Text Generation

TGI

Accelerated Text Generation Inference

GPU 2x Nvidia A100

$ 8

/ hour

Qwen2.5-14B-Instruct-1M

Text Generation

TGI

Accelerated Text Generation Inference

GPU 2x Nvidia A100

$ 8

/ hour

Qwen2.5-72B-Instruct

Text Generation

TGI

Accelerated Text Generation Inference

GPU 4x Nvidia A100

$ 16

/ hour

Qwen2.5-7B-Instruct

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L40S

$ 1.8

/ hour

Qwen2.5-Coder-14B-Instruct

Text Generation

TGI

Accelerated Text Generation Inference

GPU 2x Nvidia A100

$ 8

/ hour

Qwen2.5-Coder-32B-Instruct

Text Generation

TGI

Accelerated Text Generation Inference

GPU 2x Nvidia A100

$ 8

/ hour

Qwen2.5-Coder-7B-Instruct

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L40S

$ 1.8

/ hour

Qwen2.5-Math-72B-Instruct

Text Generation

TGI

Accelerated Text Generation Inference

GPU 4x Nvidia A100

$ 16

/ hour

Qwen2.5-Math-7B-Instruct

Text Generation

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L40S

$ 1.8

/ hour

Qwen2.5-VL-7B-Instruct

Image-Text-to-Text

TGI

Accelerated Text Generation Inference

GPU 1x Nvidia L40S

$ 1.8

/ hour