For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to the page URL.
Primary navigation
Theme

Models

Meet the AI models that power ChatGPT Work and Codex

Choosing a model is about finding the right balance of speed, cost, and capability for your task. Sometimes you need a quick first draft. Other times, a complex problem calls for more careful reasoning. This guide introduces our latest models, shows where each one shines, and helps you find a starting point for your work.

Choose a model

In Work or Codex in the ChatGPT desktop app, use the model and reasoning control beneath the composer to choose an available model and adjust its reasoning effort. If you see the Power slider, open Advanced to choose a specific model, such as GPT-6.2 Astra.

Reasoning effort guides how much work the model puts into thinking through your request. Higher effort can improve results for complex tasks, but it takes longer and uses more tokens. Start with the default effort and increase it when the task needs deeper planning or analysis.

Ultra mode goes beyond a single-agent run. It uses subagents to accelerate complex work, making it useful for larger tasks that can be split across subagents.

Selections in this preview don't change your ChatGPT settings.6.2 Sol Light, 2 of 6.Use Left and Right arrow keys to adjust power.

This example shows the Power slider for a ChatGPT Work account with access to both GPT-6.2 models. New Work chats start with GPT-6.2 Sol at Light on supported consumer plans or Medium in Enterprise workspaces with the model enabled. Move the Power slider toward Smarter for deeper reasoning or Faster for faster, lower-cost work. Open Advanced to choose a specific model or reasoning effort from the options available to your account.

GPT-6.2 Astra and GPT-6.2 Sol are now available in ChatGPT Work and Codex on supported plans and clients. For demanding work across code, apps, or research, choose GPT-6.2 Astra. In Codex, try Astra to trace a bug across services, fix it, and test the change. See Prompting GPT-6.2 in Codex.

Choose GPT-6.2 Sol for everyday coding, writing, and work across several sources. It costs fewer credits per token than GPT-6.2 Astra at Standard speed. GPT-6.1 Terra is a fast, efficient choice for writing, visual understanding, and computer use. Luna suits focused, repeatable tasks.

These recommendations apply to ChatGPT Work and Codex. For Chat availability, see models in ChatGPT in the Help Center.

6.2 Astra
6.2 Astra

Choose GPT-6.2 Astra for demanding projects, such as diagnosing a bug across services or turning research into a presentation that follows your template.

codex -m gpt-6.2-astra
ChatGPT Work
Web, mobile, and desktop
Codex
App and CLI
Default context in Codex
272,000 tokens
6.2 Sol
6.2 Sol

Use GPT-6.2 Sol for everyday tasks like editing code, drafting a report, or turning project notes into a plan.

codex -m gpt-6.2-sol
ChatGPT Work
Web, mobile, and desktop
Codex
App and CLI
Default context in Codex
500,000 tokens
Astra
Astra

Combine reasoning and computer use to tackle complex work across code, apps, and research.

codex -m gpt-6-astra
Capability
Speed
ChatGPT desktop app
ChatGPT web
Codex CLI
Codex IDE extension
ChatGPT Credits
API Access
6.1 Sol
6.1 Sol

Performance close to GPT-6 Astra for complex work at a lower cost. Consider it for repeated, long-running work across code, apps, and documents.

codex -m gpt-6.1-sol
Capability
Speed
Work and Codex in the desktop app
ChatGPT Work on the web
Codex CLI
Codex IDE extension
ChatGPT Credits
API Access
6.1 Terra
6.1 Terra

A fast, efficient model for clear writing, visual understanding, and computer use. Try it for drafting proposals, interpreting charts, or working with information in an app.

codex -m gpt-6.1-terra
Capability
Speed
Work and Codex in the desktop app
ChatGPT Work on the web
Codex CLI
ChatGPT Credits
API Access
6 Luna
6 Luna

Our most efficient model for focused, high-volume tasks, including summarization, extraction, and focused coding.

codex -m gpt-6-luna
Capability
Speed
Work and Codex in the desktop app
ChatGPT Work on the web
Codex CLI
Codex IDE extension
ChatGPT Credits
API Access

To use a longer context window in Codex, set model_context_window in config.toml. GPT-6.2 Astra and GPT-6.2 Sol each support a context window of up to 1 million tokens.

GPT-6.1 Sol uses a default context window of 500,000 tokens in Codex and ChatGPT Work. See pricing for subscription usage and credit rates.

For model availability, pricing, and usage limits, see ChatGPT Work and Codex in the Help Center.

Choosing a model

Start with a task you know well and compare the result with what you need. Consider how long you’re willing to wait, how much usage the task requires, and the level of detail or judgment involved. You can change models as your work changes.

Where each model shines

  • GPT-6.2 Astra or GPT-6 Astra, for the hardest end-to-end work. Choose an available Astra model for tasks that need sustained reasoning across code, apps, or research. Give it the sources, constraints, and checks that define a useful result.
  • GPT-6.2 Sol, for everyday work. Choose Sol to edit code, draft documents, or turn several sources into a plan.
  • GPT-6.1 Terra, for everyday writing and visual work. Choose Terra for clear communication, interpreting images and screens, and completing tasks across supported apps. Try it for drafting proposals, reviewing visual materials, or filling out forms from source documents.
  • Luna, for clear, repeatable tasks. Choose Luna for specific, high-volume tasks when you know what a good result looks like, such as extraction, classification, transformation, and structured summaries.

Try an example

Use your own materials with these prompts, and tell ChatGPT what a useful result should include.

Model Task Example prompt
GPT-6.2 Astra or GPT-6 Astra Work through a complex decision. “Compare these three vendor proposals against our requirements. Explain the tradeoffs, recommend an option, and list the questions we should resolve before deciding.”
GPT-6.2 Sol Bring several sources into a working document. “Use this project brief, meeting notes, and timeline to draft an implementation plan. Identify dependencies, flag conflicting details, and list the decisions we still need to make.”
GPT-6.1 Terra Make sense of visual information. “Review these dashboard screenshots and summarize the main changes. Refer to the chart labels and values, and flag anything you can’t read confidently.”
Luna Organize information into a consistent format. “Turn these meeting notes into a table of action items, owners, and due dates. Mark any missing owner or date as unspecified.”

Review the result against your source materials, especially names, numbers, and details taken from images. For tasks on websites or in desktop apps, check the browser use and computer use setup requirements first.

Pick a reasoning effort

For example, you might use a lower effort to rewrite a short email and a higher effort to compare several proposals with competing requirements.

For GPT-6.2 Astra or GPT-6.2 Sol, start with the effort your client selects and adjust it based on the task. For Luna, start with High. For GPT-6 Astra, start with Light (low in configuration). Increase the effort for tasks that need more planning, analysis, or checking.

  • Light in the ChatGPT desktop app, ChatGPT Work on the web, and IDE extension, or Low in the CLI, suits quick, well-scoped tasks.
  • Medium balances speed and depth for tasks that need more planning.
  • High and Extra High suit difficult work with multiple steps, sources, or tradeoffs.

Know when to use Max or Ultra

Max gives the selected model more time to reason about a single task. Use it for the hardest problems, when depth matters more than speed or usage. If you don’t see Max in the ChatGPT desktop app, check your app settings.

Ultra uses subagents to handle separate parts of a complex task in parallel. Choose it when you can divide the work into meaningful parts. Most tasks do not need Max or Ultra.

GPT-6 Luna supports reasoning efforts up to Max, but not Ultra.

In the CLI, use /model, choose a model, then select More reasoning… to see its supported Max or Ultra options.

If your model supports Ultra but it doesn’t appear in the desktop app’s model slider, go to Settings > Configuration, then turn on Ultra in model picker slider.

GPT-5.5 retirement

Effective October 14, 2026, at noon PDT (19:00 UTC), GPT-5.5 retires from Codex for users signed in with ChatGPT. The OpenAI API and Codex sessions authenticated with an API key aren’t affected.

For Codex with ChatGPT sign-in, choose an available replacement:

  • On Plus, Pro, Business, Enterprise, and Edu plans, choose GPT-6.1 Sol (gpt-6.1-sol) when available.
  • On Free and Go plans, choose GPT-6 Luna (gpt-6-luna) in the desktop app when available.

Replace gpt-5.5 in workspace defaults, saved model settings, managed configurations, custom agents, scheduled tasks, and scripts that select a model.

See workspace model availability for administrator guidance.

Other models

With API-key authentication, model availability follows your API organization and project. GPT-5.5 remains available through the OpenAI API and in Codex sessions authenticated with an API key. See the API model catalog.

For a custom model provider or gateway, use a compatible Responses API endpoint. See Custom model providers for configuration and Gateway compatibility for streaming, tool, and conversation requirements. Current Codex releases don’t support wire_api = "chat" or a Chat Completions-only endpoint.

Deprecated Codex models

GPT-5.3-Codex-Spark retired on September 14, 2026, and is no longer available in the ChatGPT desktop app, Codex CLI, or IDE extension. Update saved configurations, custom agents, and scripts that select gpt-5.3-codex-spark to use an available model. See the Spark retirement notice.

GPT-5.5 retires from Codex with ChatGPT sign-in on October 14, 2026, at noon PDT (19:00 UTC). Replace gpt-5.5 with a model available to your account and client. API-key sessions aren’t affected. See GPT-5.5 retirement for plan-specific replacements and the migration checklist.

The gpt-5.4 and gpt-5.4-mini models retired from Codex with ChatGPT sign-in on August 31, 2026. Replace gpt-5.4 with gpt-6-sol and gpt-5.4-mini with gpt-6-luna when available to your plan and client. In Enterprise and Edu, an administrator must enable Luna first. Update workspace defaults, saved model settings, managed configurations, custom agents, and scheduled tasks with an available replacement.

The gpt-5.2 and gpt-5.3-codex models are already deprecated in Codex when you sign in with ChatGPT. Update scripts, configuration files, and codex exec --model commands that still reference those models.

The OpenAI API and Codex authenticated with your own API key aren’t affected by the GPT-5.4 retirement. For current API model availability, see the API models page.

Configure your default local model

The ChatGPT desktop app, Codex CLI, and IDE extension use the same config.toml configuration file. To specify a model, add a model entry to your configuration file. If you don’t specify a model, the ChatGPT desktop app, Codex CLI, or IDE extension uses a recommended model. This example selects Sol in the app or CLI. When sharing a configuration with the IDE extension, pick a model available in every client you use, such as gpt-6.1-sol.

model = "gpt-6.2-sol"