OpenAI 开发者 API 博客文章汇总

Quickstart; Using GPT-6; Key concepts

Core concepts

Responses API; Decisions API; Conversation state; Background mode; Streaming; WebSocket mode; Mid-turn steering; Multi-agent; Webhooks; File inputs; Compaction; Counting tokens

Changelog; Deprecations; Supported countries; OpenAI Crawlers; Terms and policies

Legacy APIs

Agent Builder Overview; Migration guide; Node reference; Safety in building agents; Evals Getting started; Working with evals; Prompt optimizer; External models; Best practices; Graders; Fine-tuning Optimization cycle; Supervised fine-tuning; Vision fine-tuning; Direct preference optimization; Reinforcement fine-tuning; RFT use cases; Best practices; Assistants API Migration guide

Text generation; Code generation; Structured output

Prompting

Overview; Prompt engineering; Citation formatting; Migration guide; Prompt generation; Frontend prompting

Reasoning

Reasoning models; Reasoning best practices

Images

Images and vision Image input cost calculator; Image generation Overview; Image prompting

Realtime and audio

Audio and speech; Getting started; Voice agents

Specialized models

Deep research; Embeddings; Moderation

Overview

Agents API

Overview; Quickstart; Architecture; Configuring Agents; Sessions Run and continue sessions; Events and items; Manage sessions; Webhooks; Environments and sandboxes OpenAI-hosted sandboxes; Self-hosted sandboxes; Sandbox lifecycle; Pre-warm sandboxes; Sandbox security; Files and artifacts; Tools and integrations Web search; Computer use; Functions; MCP connections; Plugins; Vaults; Multi-agent; Observability and usage; Tracing; Errors and recovery; API reference; Bedrock Managed Agents

Agents SDK

Overview; Quickstart; Agent definitions; Models and providers; Running agents; Sandbox agents; Orchestration; Guardrails; Results and state; Integrations and observability; Evaluate agent workflows

Web search; File search; Retrieval

Connect tools and data

MCP servers; Secure MCP Tunnel

Build tool workflows

Skills; Tool search; Programmatic tool calling; Async tool calling

Computer and code

Shell; Computer use; Apply Patch; Local shell; Code interpreter

Getting started; Prompting; Managing sessions; Delegation and tools; Migrate to GPT-Live; Partner integrations

Realtime API

Getting started; Prompting; Managing conversations; Voice activity detection; Tools and MCP

Build with voice

Voice agents; Connect voice to Decisions; Custom voices; Cost optimization

Connections

WebRTC; WebRTC with WARP; WebSockets; Telephony and SIP; Server-side controls

Audio processing

File transcription; Live transcription; Live translation; Text to speech; Audio in Chat Completions

Go live

Production best practices; Deployment checklist

Performance and quality

Fast mode; Ultrafast mode; Latency optimization; Predicted Outputs; Accuracy optimization

Cost and throughput

Cost optimization; Prompt caching Prompt cache diagnostics; Batch; Flex processing

Safety and governance

Safety best practices; Red teaming; Daybreak; Safety checks Safety classifiers; Cybersecurity checks; Misalignment monitoring; Enforcement notifications; Under-18 guidance; CSAM guidance; Content provenance; Your data; Private Safety Processing; Permissions

Infrastructure and access

Terraform provider Overview; Projects and access; Service accounts; Rate limits and spend; Model, tool, and data controls; Import and reconciliation; Private Link; IP allowlist; Organization blocking; Mutual TLS; Workload identity federation Federation rules; X.509 certificates; Kubernetes; AWS; Microsoft Azure; Google Cloud; Oracle Cloud Infrastructure; GitHub Actions; SPIFFE; IP egress ranges; Amazon Bedrock

Operations

Rate limits; Spend limits; Admin APIs; Error codes

Home; Quickstart

Core concepts

Plugin architecture; Skills; MCP server

Plan

Brainstorm use cases; Define tools

Build

Build an MCP server; Add UI to your MCP server (optional); Add events to your MCP server (optional); Extensions; Authenticate users; Build skills; Package your plugin; Examples

Test and publish

Connect and test your plugin; Submit and publish; Submission error reference

Conversion specs

Restaurant reservation spec; Get Quote spec; Product checkout spec

Guides

Changelog; Plugin guidelines; MCP server review requirements; Plugin UI reference; Checkout API reference

Home; Quickstart; Request a client ID

Identity

On your website; In your ChatGPT plugin

ChatGPT plan usage

Overview; UI/UX guidelines; Registration and sign-in; Accounts and sessions; Models and inference; Codex app-server; Self-hosted VMs; Token reference; Errors and recovery; Preview limitations

Overview; Feeds; Products; Promotions

Trigger workspace agent runs; Authenticate with Workspace Agent access tokens

Foundations

Explore

What's new; Models; Pricing; Glossary

Available on

ChatGPT desktop app; ChatGPT mobile app; ChatGPT on the web; Codex CLI; Codex IDE extension; Codex Cloud

Releases

Changelog; Feature Maturity; Open Source

Overview

Workflows

Projects and chats; Sites; Build plugins; Visualizations; Scheduled tasks; Long-running work; Notifications; Pets; Codex Micro

Capabilities

Browser; Computer use; Voice; Plugins; Sign in with ChatGPT; Web search; Image generation; Image inputs; Appshots; Browser extension; Work with files

dots

Meet dots; Getting started; Messaging; Tasks and memory; Computers and apps; Controls

ChatGPT Space

Overview; Getting started; Pages; Work with agents; Collaboration

Reference

Commands; Slash commands; Settings; Troubleshooting

Overview

Customization

Overview; Memories; Computer History

Config file

Agent configuration

AGENTS.md; Subagents; Speed; Rules

Desktop app; Windows sandbox; WSL

Overview

Development workflows

Code review; Integrated terminal

Extend and automate

Environments

Modes; Local environments; Git worktrees

Third-party integrations

GitHub; GitLab (Beta); Slack; Linear

Reference

CLI customization; Developer commands; Developer settings

Overview

Permissions

Profiles; Sandboxing; Auto-review; Agent approvals & security

Codex Security

Overview; Codex Security plugin Quickstart; Run a security scan; Run a deep scan; Review code changes; Use the Security workbench; Triage a backlog; Fix findings; Propose security hardening; Write vulnerability reports; Export and track findings; Changelog; Codex Security CLI Quickstart; Run bulk scans; Run scans in CI; GitLab CI/CD; Reference; FAQ; TypeScript SDK; Codex Security Cloud Setup; Security Review; Improving the threat model; FAQ

Cyber safety

Models & Trusted Access; Recommended configuration

Overview

Getting started

Admin rollout guide; Admin plugin

Feature setup Dots; Space; Teams and Team Tasks; ChatGPT in Slack and Teams; Workspace connections; Local computer access for Work Cloud and dots; Sites

Identity and access

Authentication overview; Groups and provisioning; Dynamic groups; User lifecycle management; Roles and workspace permissions; Personal access tokens; Service accounts

Deployment and configuration

Windows app deployment; Manage app updates; Managed configuration; Remote connections; Workspace model availability; Amazon Bedrock; Bedrock GovCloud configuration; Connect to a gateway Sign in with ChatGPT; Use API/provider credentials; Roll out a gateway; Gateway compatibility; Bedrock through LiteLLM

ChatGPT Work

Overview; Cloud security; Local security; Usage and cost; Admin FAQ

Plugin controls; Plugin management; Skill controls; Migrate custom GPTs to plugins

Usage and analytics

Security and compliance

Governance; Agent security; Prisma AIRS; HIPAA configuration; Compliance API and audit events

Explore use cases; Collections

Blog

Company blog; Developer blog

Explore use cases; Collections

Blog

Company blog; Developer blog

All posts

Recent

Bringing my LED display to life with GPT-Live-1 and Codex; Rethinking skills and prompts for GPT-6 Astra; Architectural visualization with Astra; Building games with Astra; Meet Rosalind Workbench: Empowering every scientist to be their own research team

Codex Ambassadors Meet the ambassadors; Codex for Students; Codex for Open Source; OpenAI for Startups

Five stories from developers building agentic products with the Responses API in its first year.

Practical patterns for building with skills, hosted shell, and server-side compaction in the Responses API.

How the Responses API unlocks persistent reasoning, hosted tools, and multimodal workflows for GPT-5.

Loading docs agent...