← All models

GPT 5.6 Luna: current reasoning model on Okou

A current reasoning model with Built-in access through Okou.

400K tokens · Text / Vision / Code · Prompt cache

A current reasoning model from OpenAI, available in Okou's public model catalog.

What is GPT 5.6 Luna?

July 2026 preview (economy tier of the GPT-5.6 family)

Okou currently offers GPT 5.6 Luna in its public reasoning model catalog. Select it with model ID gpt-5.6-luna; its relative Built-in cost is tier $.

Specs at a glance

ProviderOpenAI
Model IDgpt-5.6-luna
ModalitiesText, Code
Okou price tier$

GPT 5.6 Luna benchmarks

Preview figures from OpenAI's GPT-5.6 materials, shown against the public GPT-5.4 Mini numbers Luna succeeds. Treat all percentages as directional: the family is in preview and OpenAI has flagged SWE-bench Verified contamination across frontier models.

SWE-bench Verifiedpreview; economy tier
~70%
Terminal-Bench 2.0preview tool use
~58%
AIME 2025 (no tools)preview competition math
~89%
GPQA Diamondpreview graduate science
~80%
OSWorld (computer use)preview
~62%
MMMU (multimodal)preview
Entry GPT-5.6 family
Speedmedium effort, early estimate
~130 tokens/sec

GPT 5.6 Luna pricing

Relative Built-in credit cost. Actual charges depend on usage and settings; check the app for current prices.

Price tier$

Best agent tasks for GPT 5.6 Luna

Latency-sensitive chat replies

For a user-facing assistant where response time is felt directly, Luna's ~130 tokens/sec keeps replies snappy while still handling tool calls and structured outputs.

The base layer under Terra and Sol

In a layered agent, Luna handles the many cheap, fast steps — fetching, formatting, simple tool calls — while Terra runs the everyday logic and Sol takes the hardest planning. The layering keeps the whole pipeline affordable.

Draft-then-refine loops

Let Luna produce fast first drafts — outlines, candidate code, summaries — and promote only the ones that need polishing to Terra or Sol. You pay the frontier rate on a fraction of the volume.

Frequently asked questions

What is GPT 5.6 Luna's context window?

400,000 tokens, with up to 128K tokens of output per response. The full window bills at standard rates.

When should I use Luna instead of Terra?

When speed and cost matter more than reasoning depth: high-volume classification and extraction, latency-sensitive chat, and the cheap base layer of a layered agent. Step up to Terra the moment a task needs real multi-step reasoning or hard tool-routing.

Using GPT 5.6 Luna on Okou

Choose GPT 5.6 Luna in the chat model selector when it is enabled for your workspace. Available provider connections and billing are shown in model settings.

Credits and the $ price tier

Relative Built-in credit cost. Actual charges depend on usage and settings; check the app for current prices.

Available on Okou since July 2026 (preview).