GPT-6 Luna

GPT-6 Luna is OpenAI's most efficient GPT-6 model for focused, high-volume work, with a long context window and broad tool support.

Platform: OpenAI

Language ModelEfficient ModelCoding AssistantLong ContextTool UseOpenAI

OpenAI API / ChatGPT Work / Codex / desktop app

$0.10/1M input, $0.01 cached input, $0.125 cache write, $0.50 output; above 272K input uses 2x input/cache and 1.5x output

Commercial

🚀Function Overview

GPT-6 Luna brings GPT-6 reasoning and tool support to high-volume workflows with the lowest token prices in the GPT-6 family.

Key Features

Official API model ID gpt-6-luna
1,050,000-token context window and 128,000 maximum output tokens
Text and image input with text output
Reasoning effort from none through max, with medium as the documented default
Responses API built-in tools including web search, file search, image generation, code interpreter, shell, apply patch, skills, computer use, MCP, and tool search
$0.10 input, $0.01 cached input, $0.125 cache write, and $0.50 output per million tokens
Prompts above 272K input tokens use 2x input/cache and 1.5x output rates for the full request
Free and Go access is documented for the desktop app, while ChatGPT Work and Codex availability has separate plan boundaries

Use Cases

•High-volume classification and extraction
•Focused coding and maintenance tasks
•Long-context document analysis
•Cost-sensitive tool-using agents
•First-pass routing before a larger model

⚙️Input Parameters

model

string

Use gpt-6-luna.

input

object

Text or supported image input for the Responses API.

reasoning.effort

string

Choose none, low, medium, high, xhigh, or max.

tools

array

Optional built-in or custom tools supported by the active endpoint.

💡Usage Examples

Example 1

Input Parameters

{
  "model": "gpt-6-luna",
  "input": "Classify these support requests, return structured labels, and flag low-confidence cases.",
  "reasoning": {
    "effort": "medium"
  }
}

Output Results

GPT-6 Luna returns structured text through the selected API surface. Measure task accuracy, long-prompt pricing, tool calls, and escalation rate.

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: OpenAI API / ChatGPT Work / Codex / desktop app
Commercial Use: Supported
Pricing: $0.10/1M input, $0.01 cached input, $0.125 cache write, $0.50 output; above 272K input uses 2x input/cache and 1.5x output
Platform: OpenAI