# Together

> Cancel a batch job by ID

## Pages

- [Cancel a batch job](batch-cancel.md): Cancel a batch job by ID
- [Create a batch job](batch-create.md): Create a new batch job with the given input file and endpoint
- [Get a batch job](batch-get.md): Get details of a batch job by ID
- [List all batch jobs](batch-list.md): List all batch jobs for the authenticated user
- [Billing and Usage Limits](billing.md): Understand usage limits, credit packs, build tiers, and billing settings on Together AI.
- [Building a RAG Workflow](building-a-rag-workflow.md): Learn how to build a RAG workflow with Together AI embedding and chat endpoints!
- [Changelog](changelog.md): **Model Redirects Now Active**
- [Create Chat Completion](chat-completions-1.md): Query a chat model.
- [Chat](chat-overview.md): Learn how to query our open-source chat models.
- [Cluster Storage](cluster-storage.md): A Together GPU Cluster has 3 types of storage:
- [Cluster User Management](cluster-user-management.md): Prior to adding any user to your cluster, please make sure the user has created an account and added an SSH key in th...
- [Create Completion](completions-1.md): Query a language, code, or image model.
- [Composio](composio.md): Using Composio With Together AI
- [Conditional Workflow](conditional-workflows.md): Adapt to different tasks by conditionally navigating to various LLMs and tools.
- [Create Evaluation](create-evaluation.md): openapi: 3.1.0
- [Create Tickets In Slack](create-tickets-in-slack.md): For customers who have a shared Slack channel with us
- [Create Video](create-videos.md): Create a video
- [Create A Dedicated Endpoint](createendpoint.md): Creates a new dedicated endpoint for serving models. The endpoint will automatically start after creation. You can de...
- [CrewAI](crewai.md): Using CrewAI with Together
- [Upload a Custom Model](custom-models.md): Run inference on your custom or fine-tuned models
- [Building An AI Data Analyst](data-analyst-agent.md): Learn how to use code interpreter to build an AI data analyst with E2B and Together AI.
- [Dedicated Endpoints FAQs](dedicated-endpoints-1.md): Dedicated endpoints support horizontal scaling. This means that it scales linearly with the additional replicas speci...
- [Deploying Dedicated Endpoints](dedicated-endpoints-ui.md): Guide to creating dedicated endpoints via the web UI.
- [Dedicated Inference](dedicated-inference.md): Deploy models on your own custom endpoints for improved reliability at scale
- [Dedicated Models](dedicated-models.md): export const ModelTable = ({type}) => {
- [DeepSeek V3.1 QuickStart](deepseek-3-1-quickstart.md): How to get started with DeepSeek V3.1
- [DeepSeek FAQs](deepseek-faqs.md): Together AI hosts DeepSeek R1 and V3 models on Serverless. Find them in our playground: [DeepSeek R1](https://api.tog...
- [DeepSeek R1 Quickstart](deepseek-r1.md): How to get the most out of reasoning models like DeepSeek-R1.
- [Delete A File](delete-files-id.md): Delete a previously uploaded data file.
- [Delete A Fine-tuning Event](delete-fine-tunes-id.md): Delete a fine-tuning job.
- [Delete Endpoint](deleteendpoint.md): Permanently deletes an endpoint. This action cannot be undone.
- [Deploying a Fine-tuned Model](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/...
- [Deployment Options Overview](deployment-options.md): Compare Together AI's deployment options: fully-managed cloud service vs. secure VPC deployment for enterprises.
- [Deprecations](deprecations.md): We regularly update our platform with the latest and most powerful open-source models. This document outlines our mod...
- [DSPy](dspy.md): Using DSPy with Together AI
- [Create Embedding](embeddings-2.md): Query an embedding model for a given string of text.
- [Embeddings](embeddings-overview.md): Learn how to get an embedding vector for a given text input.
- [RAG Integrations](embeddings-rag.md): See [this tutorial blog](https://www.together.ai/blog/rag-tutorial-mongodb) for the RAG implementation details using ...
- [Endpoints](endpoints-1.md): Create, update and delete endpoints via the CLI
- [Error Codes](error-codes.md): An overview on error status codes, causes, and quick fix solutions
- [Supported Models](evaluations-supported-models.md): Supported models for Evaluations
- [Together Cookbooks & Example Apps](examples.md): Explore our vast library of open-source cookbooks & example apps
- [Files](files.md): To upload a new data file:
- [Fine-tuning BYOM](fine-tuning-byom.md): Bring Your Own Model: Fine-tune Custom Models from the Hugging Face Hub
- [Data Preparation](fine-tuning-data-preparation.md): Together Fine-tuning API accepts two data formats for training dataset files: text data and tokenized data (in the fo...
- [Fine Tuning FAQs](fine-tuning-faqs.md): It depends. Factors that affect waiting time include the number of pending jobs from other customers, the number of j...
- [Supported Models](fine-tuning-models.md): A list of all the models available for fine-tuning.
- [Pricing](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](fine-tuning-quickstart.md): Learn the basics and best practices of fine-tuning large language models.
- [Fine Tuning](finetune.md): The function of the Together Python Library is used to create, manage, and monitor fine-tune jobs.
- [Function Calling](function-calling.md): Learn how to get LLMs to respond to queries with named functions and structured arguments.
- [Get Evaluation Status](get-evaluation-status.md): openapi: 3.1.0
- [Get Evaluation](get-evaluation.md): openapi: 3.1.0
- [Get File Contents](get-files-id-content.md): Get the contents of a single uploaded data file.
- [List File](get-files-id.md): List the metadata for a single uploaded data file.
- [List All Files](get-files.md): List the metadata for all uploaded data files.
- [List checkpoints](get-fine-tunes-id-checkpoint.md): List the checkpoints for a single fine-tuning job.
- [List Job Events](get-fine-tunes-id-events.md): List the events for a single fine-tuning job.
- [List Job](get-fine-tunes-id.md): List the metadata for a single fine-tuning job.
- [List All Jobs](get-fine-tunes.md): List the metadata for all fine-tuning jobs. Returns a list of FinetuneResponseTruncated objects.
- [Download Model](get-finetune-download.md): Receive a compressed fine-tuned model or checkpoint.
- [Get Video](get-videos-id.md): Fetch video metadata
- [Get Endpoint By ID](getendpoint.md): Retrieves details about a specific endpoint, including its current state, configuration, and scaling settings.
- [OpenAI GPT-OSS Quickstart](gpt-oss.md): Get started with OpenAI's GPT-OSS, open-source reasoning model duo.
- [Guides Homepage](guides.md): Quickstarts and step-by-step guides for building with Together AI.
- [How to build a Lovable clone with Kimi K2](how-to-build-a-lovable-clone-with-kimi-k2.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](how-to-build-coding-agents.md): How to build your own simple code editing agent from scratch in 400 lines of code!
- [How to build an AI audio transcription app with Whisper](how-to-build-real-time-audio-transcription-app.md): Learn how to build a real-time AI audio transcription app with Whisper, Next.js, and Together AI.
- [How To Implement Contextual RAG From Anthropic](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](how-to-improve-search-with-rerankers.md): Learn how you can improve semantic search quality with reranker models!
- [How to use Cline with DeepSeek V3 to build faster](how-to-use-cline.md): Use Cline (an AI coding agent) with DeepSeek V3 (a powerful open source model) to code faster.
- [How to use OpenCode with Together AI to build faster](how-to-use-opencode.md): Learn how to combine OpenCode, a powerful terminal-based AI coding agent, with Together AI models like DeepSeek V3 to...
- [How to use Qwen Code with Together AI for enhanced development workflow](how-to-use-qwen-code.md): Learn how to configure Qwen Code, a powerful AI-powered command-line workflow tool, with Together AI models to superc...
- [Images](images-overview.md): Generate high-quality images from text + image prompts.
- [Inference FAQs](inference-faqs.md): Together hosts a wide range of open-source models and you can view the latest inference models [here](https://docs.to...
- [Playground](inference-web-interface.md): Guide to using Together AI's web playground for interactive AI model inference across chat, image, video, audio, and ...
- [Installation](installation.md): The Together Python library comes with a command-line interface you can use to query Together's open-source models, u...
- [Instant Clusters](instant-clusters.md): Create, scale, and manage Instant Clusters in Together Cloud
- [Agent Integrations](integrations-2.md): Using OSS agent frameworks with Together AI
- [Integrations](integrations.md): Use Together AI models through partner integrations.
- [Overview](intro.md): Welcome to Together AI’s docs! Together makes it easy to run, finetune, and train open source AI models with transpar...
- [Iterative Workflow](iterative-workflow.md): Iteratively call LLMs to optimize task performance.
- [Structured Outputs](json-mode.md): Learn how to use JSON mode to get structured outputs from LLMs like DeepSeek V3 & Llama 3.3.
- [Kimi K2 QuickStart](kimi-k2-quickstart.md): How to get the most out of models like Kimi K2.
- [Kimi K2 Thinking QuickStart](kimi-k2-thinking-quickstart.md): How to get the most out of reasoning models like Kimi K2 Thinking.
- [LangGraph](langgraph.md): Using LangGraph with Together AI
- [Code/Language](language-overview.md): Learn how to create completions from language and code models.
- [List Evaluation Models](list-evaluation-models.md): openapi: 3.1.0
- [List All Evaluations](list-evaluations.md): openapi: 3.1.0
- [List All Endpoints](listendpoints.md): Returns a list of all endpoints associated with your account. You can filter the results by type (dedicated or server...
- [List Available Hardware Configurations](listhardware.md): Returns a list of available hardware configurations for deploying models. When a model parameter is provided, it retu...
- [Llama 4 Quickstart](llama4-quickstart.md): How to get the most out of the new Llama 4 models.
- [Getting Started with Logprobs](logprobs.md): Learn how to return log probabilities for your output tokens & build better classifiers.
- [LoRA Fine-Tuning and Inference](lora-training-and-inference.md): Fine-tune and run inference for a model with LoRA adapters
- [Together Mixture Of Agents (MoA)](mixture-of-agents.md): Mixture of Agents (MoA) is a novel approach that leverages the collective strengths of multiple LLMs to enhance perfo...
- [List All Models](models-1.md): Lists all of Together's open-source models
- [Models](models-5.md): To list all the available models, run`together models list`:
- [Multiple API Keys](multiple-api-keys.md): Under [Settings](https://api.together.ai/settings/api-keys) you will find a list of all the API keys associated with ...
- [How to run nanochat on Instant Clusters⚡️](nanochat-on-instant-clusters.md): Learn how to train Andrej Karpathy's end-to-end ChatGPT clone on Together's on-demand GPU clusters
- [Quickstart: Next.Js](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](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](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 ap...
- [Parallel Workflow](parallel-workflows.md): Execute multiple LLM calls in parallel and aggregate afterwards.
- [Cancel Job](post-fine-tunes-id-cancel.md): Cancel a currently running fine-tuning job. Returns a FinetuneResponseTruncated object.
- [Create Job](post-fine-tunes.md): Create a fine-tuning job with the provided model and training data.
- [Create Image](post-images-generations.md): Use an image model to generate an image for a given prompt.
- [Preference Fine-Tuning](preference-fine-tuning.md): Learn how to use preference fine-tuning on Together Fine-Tuning Platform
- [Prompting DeepSeek R1](prompting-deepseek-r1.md): Prompt engineering for DeepSeek-R1.
- [PydanticAI](pydanticai.md): Using PydanticAI with Together
- [Python v2 SDK Migration Guide](pythonv2-migration-guide.md): Migrate from Together Python v1 to v2 - the new Together AI Python SDK with improved type safety and modern architect...
- [Quickstart: FLUX.2](quickstart-flux-2.md): Learn how to use FLUX.2, the next generation image model with advanced prompting capabilities
- [Quickstart: Flux Kontext](quickstart-flux-kontext.md): Learn how to use Flux's new in-context image generation models
- [Quickstart: Flux LoRA Inference](quickstart-flux-lora.md): Together AI now provides a high-speed endpoint for the FLUX.1 \[dev] model with integrated LoRA support. This enables...
- [Quickstart: How to do OCR](quickstart-how-to-do-ocr.md): A step by step guide on how to do OCR with Together AI's vision models with structured outputs
- [Quickstart: Retrieval Augmented Generation (RAG)](quickstart-retrieval-augmented-generation-rag.md): How to build a RAG workflow in under 5 mins!
- [Quickstart: Using Hugging Face Inference With Together](quickstart-using-hugging-face-inference.md): This guide will walk you through how to use Together models with Hugging Face Inference.
- [Quickstart](quickstart.md): Get up to speed with our API in one minute.
- [Rate Limits](rate-limits.md): Rate limits restrict how often a user or client can access our API within a set timeframe.
- [Reasoning Models Guide](reasoning-models-guide.md): How reasoning models like DeepSeek-R1 work.
- [Recommended Models](recommended-models.md): Find the right models for your use case
- [Create A Rerank Request](rerank-1.md): Query a reranker model
- [Rerank](rerank-overview.md): Learn how to improve the relevance of your search and RAG systems with reranking.
- [Sequential Workflow](sequential-agent-workflow.md): Coordinating a chain of LLM calls to solve a complex task.
- [Serverless Models](serverless-models.md): In the table below, models marked as "Turbo" are quantized to FP8 and those marked as "Lite" are INT4. All our other ...
- [Slurm Management System](slurm.md): Slurm is a cluster management system that allows users to manage and schedule jobs on a cluster of computers. A Toget...
- [Speech-to-Text](speech-to-text.md): Learn how to transcribe and translate audio into text!
- [Single Sign-On (SSO)](sso.md): SSO is only available for Scale and Enterprise accounts. If you would like to upgrade your account to use SSO please ...
- [Customer Ticket Portal](support-ticket-portal.md): The Customer Ticket Portal allows you to view all your support tickets and their status.
- [/tci/execute](tci-execute.md): Executes the given code snippet and returns the output. Without a session_id, a new session will be created to run th...
- [/tci/sessions](tci-sessions.md): Lists all your currently active sessions.
- [Text-to-Speech](text-to-speech.md): Learn how to use the text-to-speech functionality supported by Together AI.
- [QuickStart: LlamaRank](together-and-llamarank.md): Try out Salesforce's LlamaRank exclusively on Together's Rerank API
- [Together Code Interpreter](together-code-interpreter.md): Execute LLM-generated code seamlessly with a simple API call.
- [Together Code Sandbox](together-code-sandbox.md): Level-up generative code tooling with fast, secure code sandboxes at scale
- [Update, Start or Stop Endpoint](updateendpoint.md): Updates an existing endpoint's configuration. You can modify the display name, autoscaling settings, or change the en...
- [Upload a file](upload-file.md): Upload a file with specified purpose, file name, and file type.
- [Upload a custom model or adapter](upload-model.md): Upload a custom model or adapter from Hugging Face or S3
- [Quickstart: Using Mastra with Together AI](using-together-with-mastra.md): This guide will walk you through how to use Together models with Mastra.
- [Quickstart: Using Vercel AI SDK With Together AI](using-together-with-vercels-ai-sdk.md): This guide will walk you through how to use Together models with the Vercel AI SDK.
- [Videos](videos-overview.md): Generate high-quality videos from text and image prompts.
- [Vision](vision-overview.md): Learn how to use the vision models supported by Together AI.
- [Agent Workflows](workflows.md): Orchestrating together multiple language model calls to solve complex tasks.