Together AI

Provider

Serverless and dedicated inference, fine-tuning and GPUs for open models

Price: Pay per use
Access: API key

About

Together AI runs 100+ open models for chat, images, video and audio behind an OpenAI-compatible API, and adds fine-tuning, dedicated endpoints and GPU clusters. It is for teams building on open-weight models. Usage is prepaid, with a $5 minimum.

What you can do with it

Call open models like Kimi, GLM, Qwen and DeepSeek with one API
Fine-tune open models with LoRA, full SFT or DPO on your data
Deploy a model on dedicated GPUs with autoscaling

Get started

Create an account and buy at least $5 of credits
Create an API key
Set TOGETHER_API_KEY in your environment

Example

curl -X POST "https://api.together.ai/v1/chat/completions" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MiniMaxAI/MiniMax-M3",
    "messages": [
      {"role": "user", "content": "What are the top 3 things to do in New York?"}
    ]
  }'

Details

Hosting: Hosted service
Available in: Worldwide
Official SDKs: Python, JavaScript/TypeScript
MCP server: None