gpt-6-luna

Limited signal
Ranked #27 in the capability rankings
Reasoning
Tools
Vision
Multimodal
1M
Files

Standard & Paid Price

The locked value is the exact Paid Price after your first top-up; the discount is derived from the two absolute prices
Unlock with a top-up
MeterStandard PricePaid PriceSave
Input price$0.1000 / 1M tokens$0.0700 / 1M tokens-30%
Completion price$0.5000 / 1M tokens$0.3500 / 1M tokens-30%
Cache read price$0.0100 / 1M tokens$0.0070 / 1M tokens-30%
Cache creation price$0.1250 / 1M tokens$0.0875 / 1M tokens-30%
Dynamic pricing · 2 tiers
Billing details
Vendor list price comparison

Description

OpenAI GPT-6 Luna — OpenAI's most efficient model, built for focused, high-volume tasks. It supports text and image input, a 1,050,000-token context window, up to 128,000 output tokens, and reasoning effort from none to max, with medium as the default. Use /v1/responses for tool calling: on /v1/chat/completions, function calling works only with reasoning_effort set to none. On /v1/responses, send the whole conversation in the input array on every turn; requests that carry previous_response_id or conversation are refused.

Capabilities

Input modalities
text, image
Output modalities
text
Tasks
chat, reasoning, vision, file-video-understanding

Decision evidence

GPT-6 Luna is OpenAI's closed-weight model for focused, high-volume tasks, released on 2026-09-22 alongside GPT-6 Sol, with a 1,050,000-token context window (922,000 input), 128,000 output tokens and text and image input. In the one reviewed test it was the quickest and lightest on quota of four GPT-6 and GPT-5.6 models given the same prompt, but the author judged its output a flop.

2026-09-24 · Markdown evidence · JSON data

API endpoints

  • POST /v1/chat/completions (openai)
  • POST /v1/responses (openai-response)