Ploba logo

Find the right AI tool for the job: apps, agents, APIs, MCP servers and datasets, explained plainly.

Get the AI Digest

Discover

  • Explore
  • Top Charts
  • Categories
  • Agents
  • MCP servers
  • Developer tools

Learn & community

  • Learn AI
  • AI Glossary
  • Blog
  • Hackathons
  • People
  • AI Digest

For makers

  • List your tool
  • Docs
  • Claim a listing
  • Advertise
  • Write for us

Company

  • About
  • Careers
  • Changelog
  • Trust
  • Security
  • Contact

© 2026 Ploba. All rights reserved.

  • Privacy
  • Terms
  • Cookies
  • Advertising
  • All policies
llms.txt
Ploba logo
DiscoverHackathonsPeopleLearnAI Digest
Sign inGet started
HomeTop ChartsExploreCategories
TypesWeb apps1,894Agents585Plugins416APIs376Mobile apps152Datasets85
AdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise hereAdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise here
  1. Explore
  2. /
  3. Developer Tools
  4. /
  5. Together AI
Developer Tools
Together AI icon

Together AI

by Together AI

Together AI is a cloud platform for running, fine-tuning and serving open-source AI models through an OpenAI-compatible API. It also offers dedicated endpoints and GPU clusters.

API·Usage-based

Visit together.ai(opens in a new tab)

About Together AI

Key features of Together AI

  • OpenAI-compatible inference API for open-source models
  • Serverless and dedicated inference
  • Fine-tuning with SFT, DPO and reinforcement learning
  • GPU clusters with attached storage
  • Batch API for asynchronous jobs
  • Evals API with LLM judges
  • Bring your own model weights
  • Together CLI for endpoints, fine-tunes and clusters

Who Together AI is for

  • Developers building AI apps and agents
  • ML teams fine-tuning open models
  • Companies needing dedicated GPUs or clusters
  • Teams comparing open-source models

How to use Together AI

  1. 1

    Step 1: Create an account and get an API key.

  2. 2

    Step 2: Install the Python or TypeScript client, or use cURL against the chat completions endpoint.

  3. 3

    Step 3: Pick a model from the models library and send your first request.

  4. 4

    Step 4: Try models in the playground and export the code.

  5. 5

    Step 5: Move to dedicated endpoints, batch jobs or fine-tuning as your workload grows.

  6. 6

    Step 6: Use the Together CLI to manage endpoints, fine-tunes and GPU clusters.

Together AI FAQ

Is the API compatible with OpenAI's?

Yes. The docs describe an OpenAI-compatible API for running open-source models.

What is the difference between serverless and dedicated inference?

Serverless charges by the tokens you use, while dedicated inference provisions single-tenant GPUs for predictable, isolated latency and charges by GPU hours.

Can I serve my own model?

Yes. You can upload your own weights and serve them through the Together AI API, or run your own Docker containers on managed GPUs.

How do I install the CLI?

It needs Python 3.10 or later and uv. Install it with uv tool install "together[cli]" and run tg --help to list commands.

Technical details

API endpoint

Requirements

  • Developer environment; Together AI account/API key; billing setup for paid usage

Environment variables

Details

Pricing
Usage-basedFree to start. Serverless inference is usage-based, billed per token by model size; dedicated endpoints are billed by GPU hours. Fine-tuning and GPU clusters have separate pricing on the pricing page.
Type
API
Platforms
  • API
  • CLI
Categories
Developer ToolsAIData
Added
Sep 14, 2026

Links

  • Documentationdocs.together.ai
Together AI iconPublisherTogether AI

Built from public sources

We put this page together from Together AI’s own website and docs so you can compare it with other tools. Ploba isn’t affiliated with Together AI.

Work at Together AI? Claim the listing to manage it yourself.

Something wrong here?

Related tools

See more
Bittensor iconBittensorBittensor · FreeBittensor is an open network where independent subnets produce digital commodities such as compute, inference, storage and prediction, and contributors are paid in TAO. A Python SDK and the btcli command line give access to the chain.Developer Tools · FreeUnstructured iconUnstructuredUnstructured · Usage-basedDocument ETL platform that converts complex files into structured, AI-ready data for retrieval and agent workflows.Developer Tools · Usage-basedChainbase AI iconChainbase AIChainbase · Contact for pricingChainbase AI is a set of tools that gives AI agents access to onchain data from 90+ blockchains. It includes agent skills, a command-line tool and an MCP server.Developer Tools · Contact for pricing