GPT-5.6 Luna

by OpenAI

All OpenAI releases

The lightest member of OpenAI's GPT-5.6 generation, GPT-5.6 Luna launched alongside Sol and Terra on July 9, 2026 and is tuned for speed and volume rather than maximum depth. It keeps the family traits, a 1.05 million token context window, 128K max output, reasoning support, vision, and structured output, in a much quicker package, and on agentic terminal benchmarks it performs on par with the previous GPT-5.5 generation. Luna is built for high-throughput work such as classification, summarization, extraction, and batch processing, where per-request speed compounds across millions of calls. Recall over very long inputs is where the bigger tiers pull ahead, so it fits best as the workhorse for shorter-context tasks at scale and as the fast layer in multi-model pipelines.

Key info

Input
Output
Features
Context window
1.1M
Max output
128K
Input price
$0.20 /1M
Output price
$1.20 /1M
Released
  • onchain settlement available
  • US residency available
  • Zero data retention on pay-as-you-go
  • No training by default
  • no-KYC deposit available

Available routes

GPT-5.6 Luna runs on 6 different routes through the qynio gateway. Compare residency, zero retention, and training posture at a glance β€” full data-handling detail per route below.

ProviderRegionZero data retentionTrainingInputOutput
MultiZero data retentionNo$0.20$1.20
EUZero data retentionNo$0.20$1.20
MultiZero data retentionNo$0.20$1.20
EUNot by defaultNo$0.20$1.20
MultiNot by defaultNo$0.20$1.20
USNot by defaultNo$0.20$1.20

Uptime and availability

GPT-5.6 Luna runs on 3 independently monitored routes through the qynio gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.

100%effective uptime, last 30 days
Averaged across these routes on their own, a single provider reached 98.69% over the same window.
Daily status through the gateway, which serves each request from whichever route is healthy.
3 monitored providers serve GPT-5.6 Luna.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider qynio monitors.

Data handling per route

Each route hosting GPT-5.6 Luna has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.

AWS Bedrock β€” Multi-region

Zero data retention is on by default on Pay-as-you-go β€” no action required. No training on customer data. GLOBAL; wallets; deposit available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
None
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
no-KYC deposit
deposit available
Transfer mechanism
wallets

Azure β€” SwedenπŸ‡ΈπŸ‡ͺ

Zero data retention is on by default on Pay-as-you-go β€” no action required. No training on customer data. EU; deposit available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
None
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
no-KYC deposit
deposit available
Transfer mechanism
Not applicable β€” data stays in EU

Azure β€” Multi-region

Zero data retention is on by default on Pay-as-you-go β€” no action required. No training on customer data. GLOBAL; wallets; deposit available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
None
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
no-KYC deposit
deposit available
Transfer mechanism
wallets

Azure β€” SwedenπŸ‡ΈπŸ‡ͺ

Zero data retention is not on by default β€” abuse monitoring, 30-day retention. No training on customer data. EU; deposit available.

Zero data retention
Not by default β€” abuse monitoring, 30-day retention. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
Abuse monitoring (30-day retention)
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
no-KYC deposit
deposit available
Transfer mechanism
Not applicable β€” data stays in EU

Azure β€” Multi-region

Zero data retention is not on by default β€” abuse monitoring, 30-day retention. No training on customer data. GLOBAL; wallets; deposit available.

Zero data retention
Not by default β€” abuse monitoring, 30-day retention. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
Abuse monitoring (30-day retention)
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
no-KYC deposit
deposit available
Transfer mechanism
wallets

OpenAI β€” United StatesπŸ‡ΊπŸ‡Έ

Zero data retention is not on by default β€” abuse monitoring, 30-day retention. No training on customer data. US; wallets; deposit available.

Zero data retention
Not by default β€” abuse monitoring, 30-day retention. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
Abuse monitoring (30-day retention)
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
no-KYC deposit
deposit available
Transfer mechanism
wallets

Benchmarks

Independent benchmark scores β€” composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#50 of 630 LLMs
TierFrontier
Output speed110 tok/s
First token97.53s
Intelligence Index52.3
Coding Index71.4
Reasoning & knowledge
GPQA Diamond
91%
Humanity's Last Exam
40%
Long-context reasoning
78%
Coding
SciCode
53%

Get started

Call GPT-5.6 Luna through the qynio gateway with one API key. Let your coding agent set it up, or call it directly β€” qynio is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.

Or call it directly

import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.QYN_API_KEY,
baseURL: "https://api.qyn.io/v3/compat",
});
const completion = await client.chat.completions.create({
model: "openai/gpt-5.6-luna",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Compare GPT-5.6 Luna with…

Side-by-side on privacy, crypto rails, pricing, and benchmarks.

Other models from OpenAI

Start building with 700+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation