GTWY logo
    Openai logoOpenai

    gpt-5.5

    Auto-router

    openai/gpt-5.5

    ChatVisionFilesToolsSystem promptReasoning

    Context

    1.1M

    Max output

    200K

    Input / 1M

    $5.00

    Output / 1M

    $30.00

    Cached / 1M

    $0.50

    Cutoff

    Dec 2025

    About this model

    GPT-5.5 is OpenAI's most advanced frontier model, optimized for complex real-world work including agentic reasoning, long-context workflows, tool use, and high-performance code generation. It can plan, execute, and complete multi-step tasks with minimal guidance while maintaining strong context over long durations.

    Best suited for

    • Advanced agentic workflows and long-horizon task execution
    • Enterprise-grade software development, debugging, and refactoring
    • Complex research, data analysis, and information synthesis
    • Multimodal workflows (text + image inputs) across tools
    • Automated business operations (documents, spreadsheets, reports)
    • Scientific and technical research with multi-step reasoning
    • AI agents that can plan, act, and self-correct over time

    Built-in tools

    Image generationWeb searchGtwy web search

    Hosted by the gateway — enable them per request without wiring your own endpoint.

    Capabilities

    Vision

    Accepts images alongside text in the same message.

    Files

    Accepts file attachments — PDFs, transcripts, spreadsheets.

    Tools

    Native function calling, so agents can invoke your endpoints.

    System prompt

    Honours a dedicated system role, separate from the user turn.

    Reasoning

    Emits a separate thinking pass before the answer.

    Supported parameters

    max_tokens

    Specifies the maximum number of text units (tokens) allowed in a response, limiting its length.

    tools

    Lists tool definitions or capabilities available to the model.

    tool_choice

    Decides whether to use tools or just the model for generating responses.

    response_type

    Defines the format or type of the generated response.

    parallel_tool_calls

    Enables parallel execution of tools, allowing multiple tools to run simultaneously.

    reasoning

    Controls how much reasoning effort the model applies before generating a response.

    verbosity

    Controls the level of detail and length of the generated responses.

    stream

    Sends the response in real-time as it's being generated.