# Together.ai Docs

## Docs

- [Agno](https://togetherai-migration.mintlify.app/docs/agno.md): Using Agno with Together AI
- [How To Build An AI Search Engine (OSS Perplexity Clone)](https://togetherai-migration.mintlify.app/docs/ai-search-engine.md): How to build a full-stack AI search engine inspired by Perplexity with Next.js and Together AI
- [How To Build An Interactive AI Tutor With Llama 3.1](https://togetherai-migration.mintlify.app/docs/ai-tutor.md): Learn we built LlamaTutor from scratch – an open source AI tutor with 90k users.
- [AutoGen(AG2)](https://togetherai-migration.mintlify.app/docs/autogen.md): Using AutoGen(AG2) with Together AI
- [Building a RAG Workflow](https://togetherai-migration.mintlify.app/docs/building-a-rag-workflow.md): Learn how to build a RAG workflow with Together AI embedding and chat endpoints!
- [Chat](https://togetherai-migration.mintlify.app/docs/chat-overview.md): Learn how to query our open-source chat models.
- [Cluster Storage](https://togetherai-migration.mintlify.app/docs/cluster-storage.md)
- [Cluster User Management](https://togetherai-migration.mintlify.app/docs/cluster-user-management.md)
- [Code Execution (CSB SDK)](https://togetherai-migration.mintlify.app/docs/code-execution.md): Learn how to use the CodeSandbox SDK to execute code, process data, and more.
- [Composio](https://togetherai-migration.mintlify.app/docs/composio.md): Using Composio With Together AI
- [Conditional Workflow](https://togetherai-migration.mintlify.app/docs/conditional-workflows.md): Adapt to different tasks by conditionally navigating to various LLMs and tools.
- [Create Tickets In Slack](https://togetherai-migration.mintlify.app/docs/create-tickets-in-slack.md): For customers who have a shared Slack channel with us
- [CrewAI](https://togetherai-migration.mintlify.app/docs/crewai.md): Using CrewAI with Together
- [Uploading a Fine-tuned Model](https://togetherai-migration.mintlify.app/docs/custom-models.md): Run inference on your fine-tuned model
- [Building An AI Data Analyst](https://togetherai-migration.mintlify.app/docs/data-analyst-agent.md): Learn how to use code interpreter to build an AI data analyst with E2B and Together AI.
- [Dedicated Endpoints](https://togetherai-migration.mintlify.app/docs/dedicated-endpoints-1.md)
- [Deploy Dedicated Endpoints In The Web](https://togetherai-migration.mintlify.app/docs/dedicated-endpoints-ui.md): Deploy your own GPUs
- [Dedicated Inference](https://togetherai-migration.mintlify.app/docs/dedicated-inference.md): Deploy models on your own custom endpoints for improved reliability at scale
- [Dedicated Models](https://togetherai-migration.mintlify.app/docs/dedicated-models.md)
- [DeepSeek FAQs](https://togetherai-migration.mintlify.app/docs/deepseek-faqs.md)
- [DeepSeek R1 Quickstart](https://togetherai-migration.mintlify.app/docs/deepseek-r1.md): How to get the most out of reasoning models like DeepSeek-R1.
- [Deploying a Fine-tuned Model](https://togetherai-migration.mintlify.app/docs/deploying-a-fine-tuned-model.md): Once your fine-tune job completes, you should see your new model in [your models dashboard](https://api.together.xyz/models).
- [Deployment Options](https://togetherai-migration.mintlify.app/docs/deployment-options.md)
- [Deprecations](https://togetherai-migration.mintlify.app/docs/deprecations.md): We regularly update our platform with the latest and most powerful open-source models.
- [DSPy](https://togetherai-migration.mintlify.app/docs/dspy.md): Using DSPy with Together AI
- [Embeddings](https://togetherai-migration.mintlify.app/docs/embeddings-overview.md): Learn how to get an embedding vector for a given text input.
- [RAG Integrations](https://togetherai-migration.mintlify.app/docs/embeddings-rag.md)
- [Error Codes](https://togetherai-migration.mintlify.app/docs/error-codes.md): An overview on error status codes, causes, and quick fix solutions
- [Data Preparation](https://togetherai-migration.mintlify.app/docs/fine-tuning-data-preparation.md): Together Fine-tuning API accepts two data formats for training dataset files: text data and tokenized data (in the form of Parquet files). Below, you can learn about different types of those formats and the scenarios in which they can be most useful.
- [Fine Tuning FAQs](https://togetherai-migration.mintlify.app/docs/fine-tuning-faqs.md)
- [Supported Models](https://togetherai-migration.mintlify.app/docs/fine-tuning-models.md): A list of all the models available for fine-tuning.
- [Pricing](https://togetherai-migration.mintlify.app/docs/fine-tuning-pricing.md): Fine-tuning pricing at Together AI is based on the total number of tokens processed during your job.
- [Fine-tuning Guide](https://togetherai-migration.mintlify.app/docs/fine-tuning-quickstart.md): Learn the basics and best practices of fine-tuning large language models.
- [Function Calling](https://togetherai-migration.mintlify.app/docs/function-calling.md): Learn how to get LLMs to respond to queries with named functions and structured arguments.
- [How to build a Claude Artifacts Clone with Llama 3.1 405B](https://togetherai-migration.mintlify.app/docs/how-to-build-a-claude-artifacts-clone-with-llama-31-405b.md): Learn how to build a full-stack Next.js app that can generate React apps with a single prompt.
- [How to Build Coding Agents](https://togetherai-migration.mintlify.app/docs/how-to-build-coding-agents.md): How to build your own simple code editing agent from scratch in 400 lines of code!
- [How To Implement Contextual RAG From Anthropic](https://togetherai-migration.mintlify.app/docs/how-to-implement-contextual-rag-from-anthropic.md): An open source line-by-line implementation and explanation of Contextual RAG from Anthropic!
- [How To Improve Search With Rerankers](https://togetherai-migration.mintlify.app/docs/how-to-improve-search-with-rerankers.md): Learn how you can improve semantic search quality with reranker models!
- [Images](https://togetherai-migration.mintlify.app/docs/images-overview.md): Generate images with a text prompt.
- [Introduction](https://togetherai-migration.mintlify.app/docs/index.md): Introduction to Together AI and all its services.
- [Inference Models](https://togetherai-migration.mintlify.app/docs/inference-models.md): Explore all the open source models we offer.
- [Playground](https://togetherai-migration.mintlify.app/docs/inference-web-interface.md): How to run inference through our web playground.
- [Integrations](https://togetherai-migration.mintlify.app/docs/integrations.md): Use Together AI models through partner integrations.
- [Agent Integrations](https://togetherai-migration.mintlify.app/docs/integrations-2.md): Using OSS agent frameworks with Together AI
- [Iterative Workflow](https://togetherai-migration.mintlify.app/docs/iterative-workflow.md): Iteratively call LLMs to optimize task performance.
- [Structured Outputs](https://togetherai-migration.mintlify.app/docs/json-mode.md): Learn how to use JSON mode to get structured outputs from LLMs like DeepSeek V3 & Llama 3.3.
- [LangGraph](https://togetherai-migration.mintlify.app/docs/langgraph.md): Using LangGraph with Together AI
- [Code/Language](https://togetherai-migration.mintlify.app/docs/language-overview.md): Learn how to create completions from language and code models.
- [Llama 4 Quickstart](https://togetherai-migration.mintlify.app/docs/llama4-quickstart.md): How to get the most out of the new Llama 4 models.
- [Getting Started with Logprobs](https://togetherai-migration.mintlify.app/docs/logprobs.md): Learn how to return log probabilities for your output tokens & build better classifiers.
- [Serverless LoRA Inference](https://togetherai-migration.mintlify.app/docs/lora-inference.md): Deploy a fine-tuned or uploaded LoRA model on serverless for inference
- [Together Mixture Of Agents (MoA)](https://togetherai-migration.mintlify.app/docs/mixture-of-agents.md)
- [Multiple API Keys](https://togetherai-migration.mintlify.app/docs/multiple-api-keys.md)
- [Quickstart: Next.Js](https://togetherai-migration.mintlify.app/docs/nextjs-chat-quickstart.md): Build an app that can ask a single question or chat with an LLM using Next.js and Together AI.
- [How To Build An Open Source NotebookLM: PDF To Podcast](https://togetherai-migration.mintlify.app/docs/open-notebooklm-pdf-to-podcast.md): In this guide we will see how to create a podcast like the one below from a PDF input!
- [OpenAI Compatibility](https://togetherai-migration.mintlify.app/docs/openai-api-compatibility.md): Together's API is compatible with OpenAI's libraries, making it easy to try out our open-source models on existing applications.
- [Parallel Workflow](https://togetherai-migration.mintlify.app/docs/parallel-workflows.md): Execute multiple LLM calls in parallel and aggregate afterwards.
- [Preference Fine-Tuning](https://togetherai-migration.mintlify.app/docs/preference-fine-tuning.md): Learn how to use preference fine-tuning on Together Fine-Tuning Platform
- [Prompting DeepSeek R1](https://togetherai-migration.mintlify.app/docs/prompting-deepseek-r1.md): Prompt engineering for DeepSeek-R1.
- [PydanticAI](https://togetherai-migration.mintlify.app/docs/pydanticai.md): Using PydanticAI with Together
- [Quickstart](https://togetherai-migration.mintlify.app/docs/quickstart.md): Get up to speed with our API in one minute.
- [Quickstart: Flux LoRA Inference](https://togetherai-migration.mintlify.app/docs/quickstart-flux-lora.md)
- [Quickstart: Flux Tools Models](https://togetherai-migration.mintlify.app/docs/quickstart-flux-tools-models.md): Learn how to use the new Flux Tool models: Canny, Controlnet, and Remix
- [Quickstart: Retrieval Augmented Generation (RAG)](https://togetherai-migration.mintlify.app/docs/quickstart-retrieval-augmented-generation-rag.md): How to build a RAG workflow in under 5 mins!
- [Quickstart: Using Hugging Face Inference With Together](https://togetherai-migration.mintlify.app/docs/quickstart-using-hugging-face-inference.md): This guide will walk you through how to use Together models with Hugging Face Inference.
- [Rate Limits](https://togetherai-migration.mintlify.app/docs/rate-limits.md): Rate limits restrict how often a user or client can access our API within a set timeframe.
- [Reasoning Models Guide](https://togetherai-migration.mintlify.app/docs/reasoning-models-guide.md): How reasoning models like DeepSeek-R1 work.
- [Rerank](https://togetherai-migration.mintlify.app/docs/rerank-overview.md): Learn how to improve the relevance of your search and RAG systems with reranking.
- [Sequential Workflow](https://togetherai-migration.mintlify.app/docs/sequential-agent-workflow.md): Coordinating a chain of LLM calls to solve a complex task.
- [Serverless Models](https://togetherai-migration.mintlify.app/docs/serverless-models.md)
- [Slurm Management System](https://togetherai-migration.mintlify.app/docs/slurm.md)
- [Customer Ticket Portal](https://togetherai-migration.mintlify.app/docs/support-ticket-portal.md)
- [Text-to-Speech](https://togetherai-migration.mintlify.app/docs/text-to-speech.md): Learn how to use the text-to-speech functionality supported by Together AI.
- [QuickStart: LlamaRank](https://togetherai-migration.mintlify.app/docs/together-and-llamarank.md): Try out Salesforce's LlamaRank exclusively on Together's Rerank API
- [Together Code Interpreter](https://togetherai-migration.mintlify.app/docs/together-code-interpreter.md): Execute LLM-generated code seamlessly with a simple API call.
- [Quickstart: Using Vercel'S AI SDK With Together AI](https://togetherai-migration.mintlify.app/docs/using-together-with-vercels-ai-sdk.md): This guide will walk you through how to use Together models with the Vercel AI SDK.
- [Vision](https://togetherai-migration.mintlify.app/docs/vision-overview.md): Learn how to use the vision models supported by Together AI.
- [Agent Workflows](https://togetherai-migration.mintlify.app/docs/workflows.md): Orchestrating together multiple language model calls to solve complex tasks.
- [Example Apps](https://togetherai-migration.mintlify.app/example-apps.md)
- [Together Cookbooks](https://togetherai-migration.mintlify.app/example-cookbooks.md)
- [Fine-tuning Llama-3 to get 90% of GPT-4’s performance](https://togetherai-migration.mintlify.app/external-link-01.md)
- [How to build a real-time image generator with Flux and Together AI](https://togetherai-migration.mintlify.app/external-link-02.md)
- [Inference FAQs](https://togetherai-migration.mintlify.app/external-link-03.md)
- [Python Library](https://togetherai-migration.mintlify.app/python-library.md)
- [Create Audio Generation Request](https://togetherai-migration.mintlify.app/reference/audio-speech.md): Generate audio from input text
- [Authentication](https://togetherai-migration.mintlify.app/reference/authentication-1.md)
- [Chat](https://togetherai-migration.mintlify.app/reference/chat.md)
- [Create Chat Completion](https://togetherai-migration.mintlify.app/reference/chat-completions-1.md): Query a chat model.
- [Completions](https://togetherai-migration.mintlify.app/reference/complete-1.md)
- [Create Completion](https://togetherai-migration.mintlify.app/reference/completions-1.md): Query a language, code, or image model.
- [Create A Dedicated Endpoint, It Will Start Automatically](https://togetherai-migration.mintlify.app/reference/createendpoint.md): Creates a new dedicated endpoint for serving models. The endpoint will automatically start after creation. You can deploy any supported model on hardware configurations that meet the model's requirements.
- [Delete A File](https://togetherai-migration.mintlify.app/reference/delete-files-id.md): Delete a previously uploaded data file.
- [Delete Endpoint](https://togetherai-migration.mintlify.app/reference/deleteendpoint.md): Permanently deletes an endpoint. This action cannot be undone.
- [Create Embedding](https://togetherai-migration.mintlify.app/reference/embeddings-2.md): Query a language, code, or image model.
- [Endpoints](https://togetherai-migration.mintlify.app/reference/endpoints-1.md): Create, update and delete endpoints via the CLI
- [Files](https://togetherai-migration.mintlify.app/reference/files.md)
- [Fine Tuning](https://togetherai-migration.mintlify.app/reference/finetune.md): The  function of the Together Python Library is used to create, manage, and monitor fine-tune jobs.
- [List All Files](https://togetherai-migration.mintlify.app/reference/get-files.md): List the metadata for all uploaded data files.
- [List File](https://togetherai-migration.mintlify.app/reference/get-files-id.md): List the metadata for a single uploaded data file.
- [Get File Contents](https://togetherai-migration.mintlify.app/reference/get-files-id-content.md): Get the contents of a single uploaded data file.
- [List All Jobs](https://togetherai-migration.mintlify.app/reference/get-fine-tunes.md): List the metadata for all fine-tuning jobs.
- [List Job](https://togetherai-migration.mintlify.app/reference/get-fine-tunes-id.md): List the metadata for a single fine-tuning job.
- [List checkpoints](https://togetherai-migration.mintlify.app/reference/get-fine-tunes-id-checkpoint.md): List the checkpoints for a single fine-tuning job.
- [List Job Events](https://togetherai-migration.mintlify.app/reference/get-fine-tunes-id-events.md): List the events for a single fine-tuning job.
- [Download Model](https://togetherai-migration.mintlify.app/reference/get-finetune-download.md): Download a compressed fine-tuned model or checkpoint to local disk.
- [Get job Status](https://togetherai-migration.mintlify.app/reference/get-jobs.md): Get the status of a specific job
- [Get Endpoint By ID](https://togetherai-migration.mintlify.app/reference/getendpoint.md): Retrieves details about a specific endpoint, including its current state, configuration, and scaling settings.
- [Images](https://togetherai-migration.mintlify.app/reference/image-1.md)
- [Inference](https://togetherai-migration.mintlify.app/reference/inference.md): Legacy /inference endpoint. We recommend using the newer completions or chat completions endpoints.
- [Installation](https://togetherai-migration.mintlify.app/reference/installation.md)
- [List all Jobs](https://togetherai-migration.mintlify.app/reference/list-jobs.md): List all jobs and their statuses
- [List All Endpoints, Can Be Filtered By Type](https://togetherai-migration.mintlify.app/reference/listendpoints.md): Returns a list of all endpoints associated with your account. You can filter the results by type (dedicated or serverless).
- [List Available Hardware Configurations](https://togetherai-migration.mintlify.app/reference/listhardware.md): Returns a list of available hardware configurations for deploying models. When a model parameter is provided, it returns only hardware configurations compatible  with that model, including their current availability status.
- [List All Models](https://togetherai-migration.mintlify.app/reference/models-1.md): Lists all of Together's open-source models
- [Models](https://togetherai-migration.mintlify.app/reference/models-5.md)
- [Create Job](https://togetherai-migration.mintlify.app/reference/post-fine-tunes.md): Use a model to create a fine-tuning job.
- [Cancel Job](https://togetherai-migration.mintlify.app/reference/post-fine-tunes-id-cancel.md): Cancel a currently running fine-tuning job.
- [Create Image](https://togetherai-migration.mintlify.app/reference/post-images-generations.md): Use an image model to generate an image for a given prompt.
- [Create A Rerank Request](https://togetherai-migration.mintlify.app/reference/rerank-1.md): Query a reranker model
- [/tci/execute](https://togetherai-migration.mintlify.app/reference/tci-execute.md): Executes the given code snippet and returns the output. Without a session_id, a new session will be created to run the code. If you do pass in a valid session_id, the code will be run in that session. This is useful for running multiple code snippets in the same environment, because dependencies and…
- [/tci/sessions](https://togetherai-migration.mintlify.app/reference/tci-sessions.md): Lists all your currently active sessions.
- [Update Endpoint, This Can Also Be Used To Start Or Stop A Dedicated Endpoint](https://togetherai-migration.mintlify.app/reference/updateendpoint.md): Updates an existing endpoint's configuration. You can modify the display name, autoscaling settings, or change the endpoint's state (start/stop).
- [Upload a custom model or adapter](https://togetherai-migration.mintlify.app/reference/upload-model.md)

## OpenAPI Specs

- [together-ai-v2](https://togetherai-migration.mintlify.app/together-ai-v2.json)
- [deprecated-spec](https://togetherai-migration.mintlify.app/deprecated-spec.json)

## Optional

- [Contact Us](https://www.together.ai/contact)
- [Status](http://status.together.ai/?_gl=1*1rli0u6*_gcl_au*MTgxMTcxNDI4OS4xNzQyOTc3MTMx)
- [Blog](https://www.together.ai/blog)