Search the API docs
Suggested
Suggested
Get started
Core concepts
SDKs and CLI
Resources
Legacy APIs
Fine-tuning Optimization cycle
Direct preference optimization
Assistants API Migration guide
Choose a model
Text and code
Prompting
Reasoning
Images
Images and vision Image input cost calculator
Realtime and audio
Specialized models
Agents API
Sessions Run and continue sessions
Environments and sandboxes OpenAI-hosted sandboxes
Tools and integrations Web search
Agents SDK
Integrations and observability
ChatKit
Search and retrieval
Connect tools and data
Build tool workflows
Computer and code
Computer use Integration recipes
Media
GPT-Live
Realtime API
Build with voice
Connections
Audio processing
Go live
Performance and quality
Evaluation
Cost and throughput
Prompt caching Prompt cache diagnostics
Safety and governance
Safety checks Safety classifiers
Infrastructure and access
Model, tool, and data controls
Workload identity federation Federation rules
Operations
Core concepts
Plan
Build
Add UI to your MCP server (optional)
Add events to your MCP server (optional)
Test and publish
Conversion specs
Guides
Resources
MCP server review requirements
Identity
ChatGPT plan usage
Guides
File Upload
API
Measurement
Advertiser API
API Reference
Get started
Authenticate with Workspace Agent access tokens
Get started
Foundations
Explore
Available on
Releases
Workflows
Capabilities
Sites
dots
ChatGPT Space
Reference
Customization
Config file
Agent configuration
Extend ChatGPT and Codex
Linux
Windows
Development workflows
Extend and automate
Environments
Codex Cloud
Build with Codex
Third-party integrations
Reference
Permissions
Codex Security
Codex Security plugin Quickstart
Cyber safety
Getting started
Feature Configuration
Local computer access for Work Cloud and dots
Identity and access
Roles and workspace permissions
Deployment and configuration
Windows app and CLI deployment
Bedrock GovCloud configuration
Connect to a gateway Sign in with ChatGPT
ChatGPT EDU
ChatGPT Work
Collaboration and sharing
Plugins and connections
Migrate custom GPTs to plugins
Usage and analytics
Security and compliance
Compliance API and audit events
Community
Blog
Community
Blog
Recent
Designing failover across OpenAI model providers
Maintaining software with the GPT-6 family
Bringing my LED display to life with GPT-Live-1 and Codex
Rethinking skills and prompts for GPT-6 Astra
Architectural visualization with Astra
Topics
Topics
Contribute
Categories
Topics
Programs
Codex Ambassadors Meet the ambassadors
Spaces
Use GPT-6.1 Terra to match product photos to catalog entries, interpret technical drawings, act on application screens, or draft and revise text.
reasoning.effort supports none , low , medium (default), high , xhigh , and max .
Tool calling requires the Responses API.
See the GPT-6 guide for prompting and migration guidance.
Cached input tokens are priced at 5% of the uncached input token rate.
Cache-write prices shown use 30-minute retention. Standard cache writes cost $1.25 per million tokens for 30-minute retention and $2.50 for 12-hour retention, before long-context adjustments.
Prompts with more than 272K input tokens are priced at 2x input and cache rates and 1.5x output for the full request.
Batch and Flex prices are 50% lower than Standard.
Regional processing adds a 10% premium where available.