GPT-5.6 Luna

Going away soon

by OpenAI

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.

Best for: High-volume GPT-5.6 chat, classification, and light agents.

262K context

Text
Reasoning
Tool use

Try it in the playground

Pricing

USD per 1M tokens.

Window	Input	Cached input	Output
asap	$0.20	$0.02	$1.20

What one request costs

Prompt24Ktokens

Cached prefix17Ktokens

Reply2Ktokens

$0.0036

per request to GPT-5.6 Luna

Prompt: 40.3%
Cached: 9.4%
Reply: 50.3%

The same request, across other models