CrossModel
Back to model catalog

openai · Model guide

GPT-5.6 Luna

openai/gpt-5.6-luna
Modalities
TextImageText
Context
1M
Max output
128K
GPT-5.6 Luna

High-throughput, low-latency tier at about one-fifth of Sol’s price

Context window
1.05M
tokens
Max output
128K
tokens
Price vs. Sol
~20%
Same context and modality specs
Sol
Flagship tier, near-frontier reasoning
Terra
Balanced tier for everyday agentic tasks
Luna (this page)
High-throughput tier, cost and speed first

Luna targets voice agents, chat, and real-time automation at high request volume.

Overview

GPT-5.6 Luna is the fastest, most cost-efficient tier in OpenAI's GPT-5.6 family, designed for low-latency, high-throughput workloads such as voice agents, chatbots, and real-time automation. It launched alongside Sol and Terra — limited preview June 26, 2026, broad API access July 9, 2026 — as the entry point into the GPT-5.6 lineup.

Luna keeps the same 1.05M-token context window and 128K max output as its siblings, at roughly one-fifth of Sol's per-token price, making it the natural default for high-volume requests where per-call cost and speed matter more than peak reasoning depth.

Key capabilities

DimensionDetail
Context window1,050,000 tokens
Max output128,000 tokens
Input modalitiesText, image
Output modalitiesText
Reasoning effortnone, low, medium, high, xhigh, max (default: medium)

Inputs above 272K tokens enter a higher long-context tier (2x input, 1.5x output). Cached input reads get the standard ~90% discount. See live pricing in the model catalog.

Benchmarks and boundaries

High-Throughput Tier

The cheapest tier, still usable for everyday coding tasks

Intelligence Index
51
Sol: 59 · Terra: 55
Coding Agent Index
75
Sol: 80 · Terra: 77
Cost per task
$0.21
About one-fifth of Sol

Source: Artificial Analysis Intelligence Index and Coding Agent Index.

On Artificial Analysis's Intelligence Index (max reasoning effort), Luna scores 51 — behind Terra's 55 and Sol's 59 — at roughly one-fifth of Sol's per-task cost (about $0.21). On the Coding Agent Index inside Codex, Luna reaches 75, still usable for routine coding help even though the hardest, longest-horizon tasks are better routed to Terra or Sol.

When to use it

  • High-volume, latency-sensitive workloads: voice agents, chat interfaces, and real-time automation where speed and per-call cost dominate.
  • Simple to moderate coding and reasoning tasks: routine edits, short scripts, and classification-style work.
  • First-pass routing layer: handle the bulk of easy requests and escalate only the hard cases to Terra or Sol.

CrossModel exposes GPT-5.6 Luna through an OpenAI-compatible /v1/chat/completions API. Current pricing is available in the model catalog.