---
id: "openai/gpt-6-luna"
also: ["openai/gpt-6-luna-20260922", "requesty/openai/gpt-6-luna", "vercel/openai/gpt-6-luna"]
card_usd_per_m: "0.1 in, 0.5 out, at openai"
cheapest_list_usd_per_m: "0.05 in, 0.25 out, at openai/flex on openrouter"
cheapest_effective_usd_per_m: "0.0249 in, 0.5 out, at openai on requesty"
context: 1050000
max_output: 128000
input: ["file", "image", "text"]
output: ["text"]
released: "2026-09-22"
reasoning: ["max", "xhigh", "high", "medium", "low", "none"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "reasoning_effort", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "verbosity"]
endpoints: 18
gateways: "openrouter (8), requesty (7), vercel (3)"
no_training: 18
trains: 0
retains_prompts: 7
intelligence: 27.9000
---
# OpenAI: GPT-6 Luna

GPT-6 Luna is OpenAI's efficient reasoning model for focused, high-volume tasks. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools support cost-sensitive applications, coding tasks, and automated workflows.