All Providers
9Models
5Families
125KMax Context
$0.01–$0.20Input Cost/MTok
$0–$0.50Output Cost/MTok

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights

Setup

Set the following environment variable to use Inference:

INFERENCE_API_KEY

Models (9)

ModelModel IDInput CostOutput CostContextCapabilities
Qwen 3 Embedding 4Bqwenqwen/qwen3-embedding-4b$0.01/MTok$0/MTok32KOpen
Llama 3.2 1B Instructllamameta/llama-3.2-1b-instruct$0.01/MTok$0.01/MTok16KToolsOpen
Llama 3.2 3B Instructllamameta/llama-3.2-3b-instruct$0.02/MTok$0.02/MTok16KToolsOpen
Llama 3.1 8B Instructllamameta/llama-3.1-8b-instruct$0.03/MTok$0.03/MTok16KToolsOpen
Mistral Nemo 12B Instructmistral-nemomistral/mistral-nemo-12b-instruct$0.04/MTok$0.10/MTok16KToolsOpen
Llama 3.2 11B Vision Instructllamameta/llama-3.2-11b-vision-instruct$0.06/MTok$0.06/MTok16KToolsFilesOpen
Osmosis Structure 0.6Bosmosisosmosis/osmosis-structure-0.6b$0.10/MTok$0.50/MTok4KToolsOpen
Google Gemma 3gemmagoogle/gemma-3$0.15/MTok$0.30/MTok125KToolsFilesOpen
Qwen 2.5 7B Vision Instructqwenqwen/qwen-2.5-7b-vision-instruct$0.20/MTok$0.20/MTok125KToolsFilesOpen