Inference
9 models available
Models
Browse all models from Inference
Mistral Nemo 12B Instruct
inference
Tool UseOpen Weights
Input
$0.04/1M
Output
$0.10/1M
Context
16K
Max Output
4K
Google Gemma 3
inference
Tool UseOpen WeightsVision
Input
$0.15/1M
Output
$0.30/1M
Context
125K
Max Output
4K
Osmosis Structure 0.6B
inference
Tool UseOpen Weights
Input
$0.10/1M
Output
$0.50/1M
Context
4K
Max Output
2K
Qwen 3 Embedding 4B
inference
Open Weights
Input
$0.01/1M
Output
Free/1M
Context
32K
Max Output
2K
Qwen 2.5 7B Vision Instruct
inference
Tool UseOpen WeightsVision
Input
$0.20/1M
Output
$0.20/1M
Context
125K
Max Output
4K
Llama 3.2 11B Vision Instruct
inference
Tool UseOpen WeightsVision
Input
$0.06/1M
Output
$0.06/1M
Context
16K
Max Output
4K
Llama 3.1 8B Instruct
inference
Tool UseOpen Weights
Input
$0.03/1M
Output
$0.03/1M
Context
16K
Max Output
4K
Llama 3.2 3B Instruct
inference
Tool UseOpen Weights
Input
$0.02/1M
Output
$0.02/1M
Context
16K
Max Output
4K
Llama 3.2 1B Instruct
inference
Tool UseOpen Weights
Input
$0.01/1M
Output
$0.01/1M
Context
16K
Max Output
4K
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
INFERENCE_API_KEY
API Base URL
https://inference.net/v1