GPT-5.6 Luna

Provider: OpenAI US Official API price

Input price
$0.10
/ 1M tokens
Output price
$0.60
/ 1M tokens
Cache price
$0.01
/ 1M tokens (read)
Batch API
$0.10 / $0.60
input / output per 1M tokens
Context
1.05M tokens
Max output 128K tokens

Overview

OpenAI's GPT-5.6 Luna is a mid-tier reasoning model built for high-volume, latency-sensitive production pipelines.

Strengths

  • 1,050,000 token context window with 128k output limit
  • Native support for vision, function-calling, and json-mode
  • Input cost of $0.1 and output cost of $0.6 per million tokens
  • Cached input drops significantly to $0.01 per million tokens

Best use cases

  • High-volume customer chat and intent classification
  • Lightweight multi-step agentic automation workflows
  • Processing large payloads with vision capabilities

Pricing position

Input matches GPT-5.4 Nano ($0.1/M), but output is twice as expensive as GPT-6 Luna at $0.6/M vs $0.25/M.

Caveats

GPT-5.6 Luna Pro matches this model's exact pricing and context size, making capability overlap high.

Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
128K tokens
Knowledge cutoff
2026-02-16
Listed on OpenRouter
2026-07-09
Tracked since
2026-07-09
Last updated
2026-11-10

Features

Image inputFunction callingJSON outputReasoning

Price history

  • 2026-07-09 Added

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.04
1M (small app) 1 0.5 $0.40
10M (mid scale) 10 5 $4.00
100M (large) 100 50 $40.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from OpenAI

Similar-priced models

Source: OpenRouter API (openai/gpt-5.6-luna)