GPT 5.6 Luna

Name: GPT 5.6 Luna
Price: 0.0600 USD
Availability: InStock
Author: openai

gpt-5.6-lunaopenaiAvailableReleased 2026-07-09

GPT-5.6 cost-optimized tier for high-volume, latency-sensitive workloads — roughly the former nano class. Best for batch jobs, tight tool loops, and affordable agentic coding at scale.

To keep the service available, Claude Sonnet 5 and GPT-5.6 Luna each have their own concurrency limit. Sonnet 5 allows up to 10 in-flight requests and may queue briefly during busy periods; Luna allows up to 15 and returns 429 immediately once they are all in use, so retry after a moment.

TextToolsThinkingThinking: low, medium, high, xhigh, max

Context

372K

This is the context limit available through the shared pool and may differ from the provider’s full API window.

Max output

128K

Input pricing

Official $0.200/M

Our price $0.060/M

70% off

Pricing comparison

Official vs pool price (rate 0.3x)

Tier	Official	Our price	Discount
Input	$0.200/M	$0.060/M	-70%
Output	$1.20/M	$0.360/M	-70%
Cache read	$0.020/M	$0.0060/M	-70%
Cache write	$0.250/M	$0.075/M	-70%

Providers

Token Codex pool

Available

/v1/responses

Provider	Route	Status
Token Codex pool	/v1/responses	Available

GPT 5.6 Luna