Together AI

api.together.xyz

Community

Together AI provides a fast inference platform for running open-source large language models, embedding models, and image generation models. It offers an OpenAI-compatible API for chat completions, text completions, embeddings, image generation, fine-tuning, and model management at competitive pricing.

Auth

api_key

Pricing

free

Spec version

1.0

Base URL

https://api.together.xyz

Crawl failures

1

Last verified

2026-03-01T11:09:43.000Z

Health

This is a community-maintained manifest. Health monitoring is not available because this service doesn't host its own /.well-known/agent endpoint yet. Learn more about trust levels →

Capabilities

create_chat_completion

communication

Generate a chat completion response given a conversation history. Supports all open-source chat models hosted on Together AI with streaming, tool calling, and JSON mode.

Detail: https://api.together.xyz/capabilities/create_chat_completion

create_completion

communication

Generate a text completion given a prompt string. Supports language models for raw text generation tasks like code completion, creative writing, and text continuation.

Detail: https://api.together.xyz/capabilities/create_completion

create_embeddings

communication

Generate vector embeddings for input text. Useful for semantic search, clustering, and retrieval-augmented generation (RAG) workflows.

Detail: https://api.together.xyz/capabilities/create_embeddings

create_fine_tune_job

communication

Create a fine-tuning job to train a custom model on your dataset. Supports LoRA and full fine-tuning on supported open-source base models.

Detail: https://api.together.xyz/capabilities/create_fine_tune_job

create_image

communication

Generate images from text prompts using open-source diffusion models like Stable Diffusion XL and FLUX. Supports configurable resolution, steps, and seed for reproducibility.

Detail: https://api.together.xyz/capabilities/create_image

list_models

communication

List all available models on the Together AI platform. Returns model IDs, types (chat, language, code, image, embedding), and context length information.

Detail: https://api.together.xyz/capabilities/list_models

Agent Preview

This is what an AI agent sees when it discovers this service via the Gateway:

Service: Together AI
Description: Together AI provides a fast inference platform for running open-source large language models, embedding models, and image generation models. It offers an OpenAI-compatible API for chat completions, text completions, embeddings, image generation, fine-tuning, and model management at competitive pricing.
Auth: api_key
Capabilities:
  - create_chat_completion: Generate a chat completion response given a conversation history. Supports all open-source chat models hosted on Together AI with streaming, tool calling, and JSON mode.
  - create_completion: Generate a text completion given a prompt string. Supports language models for raw text generation tasks like code completion, creative writing, and text continuation.
  - create_embeddings: Generate vector embeddings for input text. Useful for semantic search, clustering, and retrieval-augmented generation (RAG) workflows.
  - create_fine_tune_job: Create a fine-tuning job to train a custom model on your dataset. Supports LoRA and full fine-tuning on supported open-source base models.
  - create_image: Generate images from text prompts using open-source diffusion models like Stable Diffusion XL and FLUX. Supports configurable resolution, steps, and seed for reproducibility.
  - list_models: List all available models on the Together AI platform. Returns model IDs, types (chat, language, code, image, embedding), and context length information.