GPT 5.6 Luna

proprietary

GPT-5.6 Luna is designed for cost-sensitive, high-volume workloads. It roughly corresponds to the nano model tier used in earlier GPT-5 families. Reasoning.effort supports: none, low, medium (default), high, xhigh, and max.

Intelligence
Reasoning
Speed
Context
1.1M
Max output
128K
Input price
$0.2/1M tokens
Output price
$1.2/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Batch Processing

Details

Model IDgpt-5.6-luna
Provider OpenCode Zen
Creator OpenAI
Familygpt-5.6
Licenseproprietary
Statusactive
Typechat
Input modalitiestext
Output modalitiestext
Open weightNo
Parameters—
Architecture—
Context window1.1M tokens
Max input922K tokens
Max output128K tokens
Reasoning tokensYes
Knowledge cutoff
Release date—
Sourceofficial

Pricing

Context lengthPer 1M tokens
InputOutputCached ReadCached Write
≤ 272K tokens$0.2$1.2$0.02$0.25
> 272K tokens$0.4$1.8$0.04$0.5

Family Comparison: gpt-5.6

ModelContextMax outPricing
GPT 5.6 Luna1.1M128K$0.2$1.2
GPT 5.6 Terra1.1M128K$2$12
GPT 5.6 Sol1.1M128K$4$20

API

GET/v1/models/opencode/gpt-5.6-luna