GTWY logo
    Openai logoOpenai

    gpt-5.6-luna

    Auto-router

    openai/gpt-5.6-luna

    ChatVisionFilesToolsSystem promptReasoning

    Context

    1.1M

    Max output

    128K

    Input / 1M

    $0.20

    Output / 1M

    $1.20

    Cached / 1M

    Free

    Cutoff

    Feb 2026

    About this model

    GPT-5.6 Luna is OpenAI's fastest and most affordable model in the GPT-5.6 family. Built for high-volume, latency-sensitive workloads like chat, classification, and lightweight agentic tasks, it delivers strong reasoning at the lowest cost in the lineup — with a 1M+ token context window and 128K max output.

    Best suited for

    • High-volume chat & customer support — fast, low-cost responses for user-facing chatbots and support assistants at scale
    • Classification & routing — intent detection, sentiment analysis, content moderation, ticket triage, and query routing pipelines
    • Data extraction & structuring — pulling structured JSON from documents, emails, forms, and unstructured text
    • Lightweight agentic workflows — quick tool-calling steps, sub-agent tasks, and orchestration steps that don't need deep reasoning
    • Summarization at scale — condensing conversations, documents, and logs in bulk, aided by the 1M+ token context window
    • Autocomplete & real-time assistance — latency-sensitive features like suggestions, rewriting, and inline completions
    • Cost-optimized fallbacks — a default cheap tier in multi-model routing, escalating to Terra/Sol only when tasks demand it

    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

    Controls the creativity of responses. Higher values (e.g., 0.7) increase creativity; lower values (e.g., 0.2) make responses more predictable.

    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
    parallel_tool_calls
    reasoning
    verbosity
    stream

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