OpenAI API llms.txt

The actual file

Source Markdown

The saved llms.txt text, displayed as source. The file belongs to its publisher; the live endpoint may change.

Showing the first 18000 characters. Load the complete file to read the remainder.

# OpenAI API docs

> Guides and conceptual documentation for building with the OpenAI API.

Each entry has a Markdown twin at `/api/docs/<slug>.md`.

## Documentation sets
- [Combined API docs](https://developers.openai.com/api/docs/llms-full.txt): Single-file Markdown export of API guides and docs.

## Actions
- [Data retrieval with GPT Actions](https://developers.openai.com/api/docs/actions/data-retrieval.md): Learn about performing data retrieval using APIs, relational databases, and vector databases with GPT Actions.
- [Getting started with GPT Actions](https://developers.openai.com/api/docs/actions/getting-started.md): Learn how to set up and test GPT actions from scratch with the OpenAI API.
- [GPT Action authentication](https://developers.openai.com/api/docs/actions/authentication.md): Learn about authentication options for GPT actions, including no authentication, API key, and OAuth methods.
- [GPT Actions](https://developers.openai.com/api/docs/actions/introduction.md): Learn about GPT Actions for customizing ChatGPT and interacting with external applications via APIs.
- [GPT Actions library](https://developers.openai.com/api/docs/actions/actions-library.md): Learn how to build and integrate GPT Actions for common applications using OpenAI's guidance.
- [Production notes on GPT Actions](https://developers.openai.com/api/docs/actions/production.md): Guidelines for deploying GPT Actions in a production environment, including rate limits, timeouts, and security measures.
- [Sending and returning files with GPT Actions](https://developers.openai.com/api/docs/actions/sending-files.md): Learn how to send and return files using GPT Actions in the OpenAI API.

## Assistants
- [Assistants migration guide](https://developers.openai.com/api/docs/assistants/migration.md): Migrate from the retired Assistants API to the Responses API, with side-by-side comparisons and updated patterns.

## Bots
- [Overview of OpenAI Crawlers](https://developers.openai.com/api/docs/bots.md)

## Changelog
- [API changelog](https://developers.openai.com/api/docs/changelog.md): Customer-visible changes to the OpenAI API and models.

## Concepts
- [Key concepts](https://developers.openai.com/api/docs/concepts.md): Key concepts to understand when working with the OpenAI API.

## Deprecations
- [Deprecations](https://developers.openai.com/api/docs/deprecations.md): Find information about OpenAI API deprecations and recommended replacements.

## Gpts
- [GPT Release Notes](https://developers.openai.com/api/docs/gpts/release-notes.md): Keep track of updates to OpenAI GPTs and explore new features and capabilities in the release notes.

## Guides
- [Actions in ChatKit](https://developers.openai.com/api/docs/guides/chatkit-actions.md): Embed a widget to build your own chat experiences.
- [Add custom MCP server](https://developers.openai.com/api/docs/guides/custom-mcp-server.md): Connect an MCP server to ChatGPT as a plugin with read and write tools.
- [Admin APIs](https://developers.openai.com/api/docs/guides/admin-apis.md): Use Admin APIs and Admin API keys to automate organization management tasks such as invitations and audit log retrieval.
- [Advanced integrations with ChatKit](https://developers.openai.com/api/docs/guides/custom-chatkit.md): Use your own server with ChatKit to integrate agent workflows into your product with more customization.
- [Advanced usage](https://developers.openai.com/api/docs/guides/advanced-usage.md): Discover advanced usage techniques for OpenAI's API, including reproducible outputs, token management, and parameter settings.
- [Agent Builder](https://developers.openai.com/api/docs/guides/agent-builder.md): Use the OpenAI Agent Builder to start from templates, compose nodes, preview runs, and export workflows to code.
- [Agent definitions](https://developers.openai.com/api/docs/guides/agents/define-agents.md): Learn how to define an agent's instructions, model, tools, and local context in the OpenAI Agents SDK.
- [Agents](https://developers.openai.com/api/docs/guides/agents.md): Compare the Agents API, Agents SDK, and Responses API, then choose the guide for your application.
- [Agents API](https://developers.openai.com/api/docs/guides/agents-api/overview.md): Build durable cloud agents with a managed Codex harness.
- [Agents API quickstart](https://developers.openai.com/api/docs/guides/agents-api/quickstart.md): Create an agent that writes and runs a script in an OpenAI-hosted sandbox.
- [Agents SDK](https://developers.openai.com/api/docs/guides/agents/sdk.md): Learn how the OpenAI Agents SDK fits together and which docs to read next.
- [API deployment checklist](https://developers.openai.com/api/docs/guides/deployment-checklist.md): Review commonly underused Responses API design choices that improve deployment quality, speed, cost, and reliability.
- [API organization blocking](https://developers.openai.com/api/docs/guides/organization-blocking.md): Configure an allowlist of API organizations through your proxy or Secure Access Service Edge (SASE) service.
- [Apply Patch](https://developers.openai.com/api/docs/guides/tools-apply-patch.md): Allow models to propose structured diffs that your integration applies.
- [Architecture](https://developers.openai.com/api/docs/guides/agents-api/architecture.md): Understand the harness, environment, and application server, from agents without an environment to agents that use your own compute.
- [Async tool calling](https://developers.openai.com/api/docs/guides/async-tool-calling.md): Start asynchronous tool calls, deliver results later, and let the model wait for specific results when needed.
- [Audio and voice](https://developers.openai.com/api/docs/guides/audio.md): Start with GPT-Live for conversational voice, or choose an API for another audio task.
- [Audio in Chat Completions](https://developers.openai.com/api/docs/guides/audio-chat-completions.md): Add audio input and output to an existing Chat Completions application.
- [AWS Lambda MicroVMs](https://developers.openai.com/api/docs/guides/agents-api/environments/providers/aws.md): Connect an AWS Lambda MicroVM to an Agents API session with runtime credentials from AWS Secrets Manager.
- [Background mode](https://developers.openai.com/api/docs/guides/background.md): Run long running tasks asynchronously in the background.
- [Batch API](https://developers.openai.com/api/docs/guides/batch.md): Learn how to use OpenAI's Batch API for processing jobs with asynchronous requests, increased rate limits, and cost efficiency.
- [Bedrock Managed Agents](https://developers.openai.com/api/docs/guides/agents-api/bedrock-managed-agents.md): Understand how Bedrock Managed Agents uses the Agents API on AWS, and compare execution environments and authentication.
- [Blaxel](https://developers.openai.com/api/docs/guides/agents-api/environments/providers/blaxel.md): Run an Agents API session in a Blaxel sandbox.
- [Browser and desktop drivers](https://developers.openai.com/api/docs/guides/tools-computer-use-sdk-drivers.md): Implement browser reads, actions, approval, and desktop screenshots. Learn which methods the SDK calls and how to recover after an interrupted run.
- [ChatKit](https://developers.openai.com/api/docs/guides/chatkit.md): Embed a widget to build your own chat experiences.
- [ChatKit widgets](https://developers.openai.com/api/docs/guides/chatkit-widgets.md): Learn how to design widgets in your chat experience with ChatKit.
- [Citation Formatting](https://developers.openai.com/api/docs/guides/citation-formatting.md): Learn practical citation formatting patterns that help models generate reliable citations.
- [Cloudflare](https://developers.openai.com/api/docs/guides/agents-api/environments/providers/cloudflare.md): Use OpenAI webhooks to start and reconnect Cloudflare sandbox containers.
- [Code generation](https://developers.openai.com/api/docs/guides/code-generation.md): Learn how to use OpenAI models and Codex to generate code.
- [Code Interpreter](https://developers.openai.com/api/docs/guides/tools-code-interpreter.md): Allow models to write and run Python to solve problems.
- [Codex federation rule reference](https://developers.openai.com/api/docs/guides/workload-identity-federation/federation-rules.md): Reference for Codex workload identity subjects, audiences, exact claims, CEL conditions, scopes, token lifetimes, and lifecycle behavior.
- [Compaction](https://developers.openai.com/api/docs/guides/compaction.md): Manage long-running conversations with server-side and standalone compaction.
- [Completions API](https://developers.openai.com/api/docs/guides/completions.md)
- [Computer use](https://developers.openai.com/api/docs/guides/agents-api/tools/computer-use.md): Run a browser task, handle website approvals and sign-in, and recover an Agents API session.
- [Computer use](https://developers.openai.com/api/docs/guides/tools-computer-use.md): Use the Python or Node SDK to run a browser or desktop task, or connect your own runtime through the Responses API.
- [Computer use integration recipes](https://developers.openai.com/api/docs/guides/tools-computer-use-integration.md): Environment setup, action handlers, custom execution services, and consent guidance for computer use integrations.
- [Configure workload identity federation with X.509 certificates](https://developers.openai.com/api/docs/guides/workload-identity-federation/x509.md): Configure an X.509 workload identity provider and exchange a TLS client certificate for a short-lived OpenAI access token.
- [Configuring Agents](https://developers.openai.com/api/docs/guides/agents-api/configuration.md): Define an agent, reuse its configuration, and customize each session.
- [Configuring workload identity federation for AWS](https://developers.openai.com/api/docs/guides/workload-identity-federation/aws.md): Configure AWS outbound identity federation or Amazon EKS as a workload identity federation token provider.
- [Configuring workload identity federation for GitHub Actions](https://developers.openai.com/api/docs/guides/workload-identity-federation/github-actions.md): Configure GitHub Actions as a workload identity federation token provider.
- [Configuring workload identity federation for Google Cloud](https://developers.openai.com/api/docs/guides/workload-identity-federation/google-cloud.md): Configure Google workload identity or GKE as a workload identity federation token provider.
- [Configuring workload identity federation for Idira](https://developers.openai.com/api/docs/guides/workload-identity-federation/idira.md): Authenticate Idira Secure Workload Access workloads to the OpenAI API with SPIFFE JWT-SVIDs.
- [Configuring workload identity federation for Kubernetes](https://developers.openai.com/api/docs/guides/workload-identity-federation/kubernetes.md): Configure Kubernetes as a workload identity federation token provider.
- [Configuring workload identity federation for Microsoft Azure](https://developers.openai.com/api/docs/guides/workload-identity-federation/microsoft-azure.md): Configure Azure managed identity or AKS as a workload identity federation token provider.
- [Configuring workload identity federation for Oracle Cloud Infrastructure](https://developers.openai.com/api/docs/guides/workload-identity-federation/oracle-cloud.md): Configure Oracle Cloud Infrastructure instance principals as a workload identity federation token provider.
- [Configuring workload identity federation for SPIFFE](https://developers.openai.com/api/docs/guides/workload-identity-federation/spiffe.md): Configure SPIFFE JWT-SVIDs as workload identity federation subject tokens.
- [Connect voice to Decisions](https://developers.openai.com/api/docs/guides/decisions-voice.md): Use the native Decisions integration in GPT-Live to choose an action or react to an input or output transcript.
- [Content provenance](https://developers.openai.com/api/docs/guides/content-provenance.md): Learn how to verify images and audio and use provenance results responsibly.
- [Conversation state](https://developers.openai.com/api/docs/guides/conversation-state.md): Learn how to manage conversation state during a model interaction with the OpenAI API.
- [Cost optimization](https://developers.openai.com/api/docs/guides/cost-optimization.md): Lower your OpenAI model costs by trying our tools and strategies.
- [Cost optimization](https://developers.openai.com/api/docs/guides/voice-latency-cost.md): Understand voice usage and manage costs for GPT-Live and the Realtime API.
- [Counting tokens](https://developers.openai.com/api/docs/guides/token-counting.md): Use the Responses API to count input tokens for text, images, files, tools, and more—without estimation or tiktoken.
- [CSAM guidance](https://developers.openai.com/api/docs/guides/csam-guidance.md): Learn practical guidance for addressing CSAM risks in products built with OpenAI.
- [Custom voices](https://developers.openai.com/api/docs/guides/custom-voices.md): Create a voice from a text prompt for GPT-Live, or use an approved recording for speech generation and voice agents.
- [Cybersecurity checks](https://developers.openai.com/api/docs/guides/safety-checks/cybersecurity.md): Learn about API cybersecurity safeguards, authorized access, request-level checks, access restrictions, and appeals.
- [Data controls in the OpenAI platform](https://developers.openai.com/api/docs/guides/your-data.md): Your data is your data. An overview of how OpenAI uses your data, including retention and usage policies.
- [Daytona](https://developers.openai.com/api/docs/guides/agents-api/environments/providers/daytona.md): Run an Agents API session in a Daytona Sandbox.
- [Decisions](https://developers.openai.com/api/docs/guides/decisions.md): Use the Decisions API to check conditions, select from fixed options, and score text and images against a rubric.
- [Deep research](https://developers.openai.com/api/docs/guides/deep-research.md): Use deep research models for complex analysis and research tasks.
- [Delegation and tools in GPT-Live](https://developers.openai.com/api/docs/guides/live-delegation.md): Configure GPT-Live client or Responses delegation, use hosted tools, return tool results and approvals, and reduce backend latency.
- [DigitalOcean](https://developers.openai.com/api/docs/guides/agents-api/environments/providers/digitalocean.md): Connect a DigitalOcean sandbox to an Agents API session.
- [Direct preference optimization](https://developers.openai.com/api/docs/guides/direct-preference-optimization.md): Fine-tune models for subjective decision-making by comparing model outputs.
- [E2B](https://developers.openai.com/api/docs/guides/agents-api/environments/providers/e2b.md): Connect an E2B sandbox to an Agents API session.
- [Error codes](https://developers.openai.com/api/docs/guides/error-codes.md): An overview of error codes from the OpenAI API and Python library, including solutions and guidance.
- [Errors and recovery](https://developers.openai.com/api/docs/guides/agents-api/errors.md): Identify Agents API request, turn, session, and environment errors, and choose when to fix input, retry, or start a new session.
- [Evaluate agent workflows](https://developers.openai.com/api/docs/guides/agent-evals.md): Learn how to evaluate agent workflows with traces, graders, datasets, and evaluation runs on the OpenAI platform.
- [Evaluate external models](https://developers.openai.com/api/docs/guides/external-models.md): Learn how to run evals on non-OpenAI models, using the OpenAI platform.
- [Evaluation best practices](https://developers.openai.com/api/docs/guides/evaluation-best-practices.md): Learn best practices for designing evals to test and improve model performance in production.
- [Events and items](https://developers.openai.com/api/docs/guides/agents-api/sessions/events.md): Consume live updates and retrieve saved work.
- [Fast mode](https://developers.openai.com/api/docs/guides/fast-mode.md): Get up to 2.5× faster speeds in the API while retaining flexible pay-as-you-go pricing.
- [File inputs](https://developers.openai.com/api/docs/guides/file-inputs.md): Learn how to use files as file inputs in the OpenAI API.
- [File search](https://developers.openai.com/api/docs/guides/tools-file-search.md): Allow models to search your files for relevant information before generating a response.
- [File transcription](https://developers.openai.com/api/docs/guides/speech-to-text.md): Learn how to transcribe recorded audio files, stream file transcripts, and use specialized speech-to-text features.
- [Files and artifacts](https://developers.openai.com/api/docs/guides/agents-api/environments/files.md): Retrieve files from your environment and preserve published outputs.
- [Fine-tuning best practices](https://developers.openai.com/api/docs/guides/fine-tuning-best-practices.md): Improve results with practical tips for fine-tuning.
- [Flex processing](https://developers.openai.com/api/docs/guides/flex-processing.md): Learn how to optimize costs for asynchronous tasks with flex processing.
- [Frontend prompt instructions](https://developers.openai.com/api/docs/guides/frontend-prompt.md): Example prompt instructions for frontend work, written for GPT-5.5.
- [Function calling](https://developers.openai.com/api/docs/guides/function-calling.md): Learn how function calling enables large language models to connect to external data and systems.
- [Functions](https://developers.openai.com/api/docs/guides/agents-api/tools/functions.md): Define functions, handle pending calls, and return results.
- [Get started with Promptfoo](https://developers.openai.com/api/docs/guides/promptfoo-codex.md): Evaluate AI applications with Promptfoo. Run a sample eval in the CLI or set one up with Codex.
- [Getting started with datasets](https://developers.openai.com/api/docs/guides/evaluation-getting-started.md): Learn how to get started with evals using datasets.
- [Getting started with GPT-Live](https://developers.openai.com/api/docs/guides/live.md):