GPT-5.5 vs GPT-5.6 Luna

OpenAI's GPT-5.5 against OpenAI's GPT-5.6 Luna — price, context and what each is best at. Both are available through one OpenAI-compatible API.

AnyModel — you pay	GPT-5.5	GPT-5.6 Luna
Vendor	OpenAI	OpenAI
Input / 1M	$0.05	$0.025
Output / 1M	$0.05	$0.025
Context	1M	400K
Best for	Complex coding	Sub-agents

GPT-5.5

OpenAI's flagship for coding, agents and research-grade reasoning.

GPT-5.5 is OpenAI's top general-purpose model and the engine behind modern Codex: state-of-the-art coding, computer use and multi-step reasoning with a ~1M-token window. The default pick when you want one model that handles everything.

More about GPT-5.5 →

GPT-5.6 Luna

The fast, light GPT-5.6 — cheap agents and high-volume coding.

GPT-5.6 Luna is the fast, low-cost tier of the GPT-5.6 line: keeps solid coding ability for sub-agents, high-volume tasks and latency-sensitive work where Sol/Terra would be overkill.

More about GPT-5.6 Luna →

Quick take: pick GPT-5.6 Luna when cost matters most; pick GPT-5.5 when you need the largest context. With AnyModel you don't have to choose up front — switch the model id any time.

FAQ

Which is cheaper, GPT-5.5 or GPT-5.6 Luna?

GPT-5.6 Luna is cheaper on output tokens ($0.025 vs $0.05 per 1M).

Which has a larger context window, GPT-5.5 or GPT-5.6 Luna?

GPT-5.5 has the larger context window (1M).