Readme

GPT-5.6 Luna

GPT-5.6 Luna is the fastest and most affordable tier of OpenAI’s GPT-5.6 family. It’s built for high-volume, latency-sensitive, or budget-conscious workloads like classification, extraction, routing, and first-pass drafting. Cheapest doesn’t mean weakest — Luna holds its own on plenty of tasks.

The GPT-5.6 family

GPT-5.6 ships as three tiers. The number is the generation; the name is the capability tier, so each tier can advance on its own schedule.

Sol — the flagship, for the hardest work.
Terra — balanced, for everyday production. GPT-5.5-level quality at roughly half the cost.
Luna (this model) — fast and affordable, for high-volume, latency-sensitive work.

Reasoning effort

Control how long the model reasons before answering with the reasoning_effort parameter:

Level	Description
`none` (default)	Fast, low-latency responses
`low`	Light reasoning with minimal overhead
`medium`	Balanced reasoning and speed
`high`	Thorough multi-step reasoning
`xhigh`	Maximum reasoning depth for the hardest problems

For higher reasoning efforts, you may need to increase max_completion_tokens to avoid empty responses where all tokens are used on reasoning.

Verbosity

Control output length with the verbosity parameter:

low: Concise, to-the-point answers
medium (default): Balanced responses
high: Detailed, comprehensive explanations

Input and output

Input: Text, images
Output: Text

Pricing

	Per 1M tokens
Input	$1.00
Cached input	$0.10
Output	$6.00