GPT-5.6 Luna
⧉GPT-5.6 Luna is the fast, economical model of the GPT-5.6 family, focused on low latency and cost efficiency for high-volume, low-latency chat and agent workloads. Fully OpenAI-SDK compatible: set model to gpt-5.6-luna and you are connected.
Live Test · Playground
Try out GPT-5.6 Luna right here (available after login).
Input
Advanced
The upstream for this model does not accept temperature / top_p / max_tokens (they are silently ignored). Use reasoning_effort below for thinking depth, and prompt wording for length.
Conversation
About GPT-5.6 Luna
GPT-5.6 Luna is the fast, economical model of the GPT-5.6 family, focused on low latency and cost efficiency for high-volume, low-latency chat and agent workloads. Fully OpenAI-SDK compatible with streaming and reasoning_effort; set model to gpt-5.6-luna and you are connected. Pay-as-you-go, failed calls never billed.
Use cases
Support answers, intent detection and tag extraction at scale, where cost and latency come first.
The many simple judgement and formatting steps inside an agent flow: Luna saves both time and budget.
Get the flow working on Luna first, then move the critical steps up to Terra or Sol.
How to choose
Simple, high-volume, latency-sensitive work goes to Luna; switch to Terra for stronger reasoning and Sol for the hardest tasks, changing only the model field.
FAQ
How does it differ from Terra?
Does it support streaming?
How large is the context window?
Am I charged for failed calls?
Related Models
Explore other models you can integrate.
