← Back to all tools
Codex Desktop logo

Codex Desktop

✓ Verified

Desktop coding experience powered by OpenAI frontier models

Updated Dec 6, 2025
AI ModelPay-per-useAPI
Last reviewed: Dec 6, 2025Details verified against vendor changelogs and hands-on usage where possible.

About

GPT-5 is OpenAI’s previous-generation reasoning model for coding and agentic tasks. It supports text and image inputs with up to 128K output tokens inside a 400K context window, runs across the Chat Completions, Responses, Realtime, and Assistants APIs, and supports tools like web search, file search, image generation, and code interpreter (no computer-use). OpenAI recommends GPT-5.1 for the newest capabilities, but GPT-5 remains available for production workloads.

Key Features

  • ✓400K token context window with up to 128K output tokens
  • ✓Text and image inputs; text outputs
  • ✓Reasoning token support with configurable effort
  • ✓Available via Chat Completions, Responses, Assistants, and Realtime APIs
  • ✓Tool support: web search, file search, image generation, code interpreter, MCP (no computer use)
  • ✓Streaming, function calling, and structured outputs
  • ✓Snapshots available (gpt-5-2025-08-07); upgrade path to GPT-5.1

Use Cases

    Technical Details

    Languages

    Any (via API)

    AI Models

    gpt-5gpt-5-2025-08-07

    Integrations

    OpenAI Chat Completions APIOpenAI Responses APIOpenAI Assistants APIOpenAI Realtime API

    Frequently Asked Questions

    What is Codex Desktop?

    GPT-5 is OpenAI’s previous-generation reasoning model for coding and agentic tasks. It supports text and image inputs with up to 128K output tokens inside a 400K context window, runs across the Chat Completions, Responses, Realtime, and Assistants APIs, and supports tools like web search, file search, image generation, and code interpreter (no computer-use). OpenAI recommends GPT-5.1 for the newest capabilities, but GPT-5 remains available for production workloads.

    How much does Codex Desktop cost?

    Codex Desktop offers pay-per-use pricing. Plans include: Standard: $1.25 / 1M input, $0.125 / 1M cached input, $10 / 1M output, Batch or Flex: $0.625 / 1M input, $0.0625 cached, $5 / 1M output, Priority: $2.50 / 1M input, $0.25 cached, $20 / 1M output.

    What programming languages does Codex Desktop support?

    Codex Desktop supports 1+ programming languages including Any (via API).

    What AI models does Codex Desktop use?

    Codex Desktop is powered by gpt-5, gpt-5-2025-08-07.

    What platforms does Codex Desktop support?

    Codex Desktop is available on API.

    What can Codex Desktop do?

    Codex Desktop provides code generation, AI chat, agentic/autonomous mode. Key features include: 400K token context window with up to 128K output tokens, Text and image inputs; text outputs, Reasoning token support with configurable effort.

    Visit Codex Desktop →

    Pricing and features change frequently—confirm on the vendor site.

    We may earn a commission if you sign up. See our disclosure.

    Pricing

    Standard

    $1.25 / 1M input, $0.125 / 1M cached input, $10 / 1M output
    • •Chat/Responses/Assistants/Realtime endpoints

    Batch or Flex

    $0.625 / 1M input, $0.0625 cached, $5 / 1M output
    • •Lower-cost higher-latency processing tiers

    Priority

    $2.50 / 1M input, $0.25 cached, $20 / 1M output
    • •Priority processing tier

    Company

    Name
    OpenAI
    Founded
    2015
    Location
    San Francisco, CA

    Links

    GitHub →Twitter →