OpenAI

GPT-5.6 Luna

GPT-5.6 Luna is a GPT-5 model from OpenAI, released in 2026-07. It costs $1 / $6 per 1M, has a 1.1M-token context window, and is best for chatbot, extraction, cheap-production. Last verified 2026-07-11.

Try GPT-5.6 Luna Docs Take the picker quiz

Spec sheet

Pricing

Input
$1 / 1M
Output
$6 / 1M
Cached input
$0.1 / 1M
Batch discount
50%
Free tier
No

Context & speed

Context window
1.1M tokens
Max output
128k tokens
Throughput
~180 tok/s
Time to first token
~320 ms
Speed tier
fast

Capabilities

Tool use
Yes
Structured output
Yes
Prompt caching
Yes
Extended thinking
Yes
Vision input
Yes
Audio in / out
No
Fine-tuning
Yes

Deployment

Open weights
No
On-prem
No
HIPAA eligible
Yes
Zero retention
Yes
Regions
us, eu

Estimated monthly cost

Assumes typical token shape: 2k input, 600 output per call. Prompt caching is excluded from these figures.

10k calls/mo
$56.00
per month
100k calls/mo
$560.00
per month
1M calls/mo
$5.6k
per month

When to use GPT-5.6 Luna

Sweet spot

  • chatbot
  • extraction
  • cheap production
  • high throughput

Known trade-offs

  • below flagship on hardest tasks

Best use cases

Best LLM for Data extraction

Strong structured-output reliability at low cost

Best LLM for Classification

Reliable for JSON-labeled tasks at scale

Best LLM for Cheap production

Best quality-for-price at OpenAI

Works with

OpenAI SDKAzure OpenAICursorVercel AI SDKLangChainLlamaIndexOpenRouter

Compare GPT-5.6 Luna to other models

vs Grok 4.5vs Claude Haiku 4.5vs Qwen3.7-Maxvs GLM-5.2vs Gemini 3 Flashvs Gemini 3.5 Flash

FAQ — GPT-5.6 Luna

How much does GPT-5.6 Luna cost?

GPT-5.6 Luna costs $1 / $6 per 1M tokens on the OpenAI API. Cached input reads cost $0.1 per 1M, cutting the input bill by roughly 90% on repeat system prompts. The batch API offers a 50% discount for async workloads.

What is the context window of GPT-5.6 Luna?

GPT-5.6 Luna has a 1.1M-token context window with up to 128k tokens of output. That's enough for entire codebases, long transcripts, or multi-document RAG.

Does GPT-5.6 Luna have a free tier?

No — Low-cost at $1/$6 per 1M; starter credits only.

Is GPT-5.6 Luna HIPAA / EU / on-prem friendly?

GPT-5.6 Luna is HIPAA-eligible, available in EU regions, and is API-only. Zero data retention is available for enterprise customers.

What is GPT-5.6 Luna best for?

GPT-5.6 Luna is best for chatbot, extraction, cheap production, high throughput. Trade-offs to be aware of: below flagship on hardest tasks.

Which tools and SDKs work with GPT-5.6 Luna?

GPT-5.6 Luna integrates with OpenAI SDK, Azure OpenAI, Cursor, Vercel AI SDK, LangChain, LlamaIndex, OpenRouter. Most major AI frameworks support it either natively or through OpenAI-compatible endpoints.