Together

Together

Deploy, scale, and customize open-source LLMs with ease and efficiency.

Visit Together

About Together

Together is an AI model deployment and inference platform designed for teams and enterprises that need scalable access to leading open-source large language models. It offers serverless inference, dedicated endpoints, custom hardware deployments, automated fine-tuning, and secure code execution for various LLMs. Together is ideal for organizations seeking flexibility, cost-effectiveness, and high-performance infrastructure for AI workloads such as model serving, experimentation, and production deployments.

Pricing Plans
Batch API / Serverless Inference
Varies by model, e.g. $0.05–$4.50 per 1M tokens
Dedicated Endpoints
Contact us
Custom GPU Deployment
Contact us
Model Training & Fine-Tuning
From $0.48
Code Sandbox
$0.04/mo
Code Interpreter
$0.03/mo
Shared Filesystem
$0.16/mo

Resources

Product Website

Visit Together's official website for product details and getting started.

Visit website →

Documentation

Comprehensive guides and API references for deploying and using Together's platform.

View docs →