Skip to main content

openai/gpt-5.6-luna/chat

GPT 5.6 Luna targets large queues of classification, extraction and short text transformations. Give each item a small, stable output contract and reserve ambiguous records for a separate review path.

Input $0.16Output $0.96per 1 million tokens20% below the publisher's list priceCached input $0.016Cache write $0.20Prompts over 272K tokensInput $0.32Cached input $0.032Cache write $0.40Output $1.44OpenAI official priceInput $0.20Output $1.20

Workbench

GPT 5.6 Luna

What can GPT 5.6 Luna help with?

Related models and next tasks

Missing the model you need?

GPT 5.6 Luna targets large queues of classification, extraction and short text transformations. Give each item a small, stable output contract and reserve ambiguous records for a separate review path.

Key numbers

Context (tokens)
1.05M

Token budget

Input window
922,000
tokens in one request
Longest reply
128,000
14% of the window

reasoning_effort

  • none
  • low
  • mediumdefault
  • high
  • xhigh
  • max
messages
up to 256
tools
up to 128

What it does

Product coding

Luna supports structured output for labels, extracted fields and compact transformations that another program will consume. A constrained result is easier to validate and retry when a record is incomplete. A successful parse still needs content checks: an allowed category or a correctly typed amount can be wrong for the source. Reasoning can be disabled or set to low, medium, high, xhigh or max, with medium as the default. This gives a queue a way to spend more effort on difficult records without changing its result structure. Function calls can retrieve application-owned details when needed, while the application decides whether the requested operation is permitted.

What a call to GPT 5.6 Luna looks like

Request bodies from this family's own examples: roles, parameters and attachments exactly as they are sent. Each one is checked against the model's input schema before it is published.

  • Applied task

    user

    Assign one category as JSON: missing_item, damaged_item or unknown. Report: The outer carton is intact but the second shelf bracket is absent. Answer in at most 75 words.

    max_tokens384reasoning_effortnone
  • Write an email subject

    user

    Write one helpful email subject line for a notification that a monthly CSV export is ready to download. Answer in at most 75 words.

    max_tokens384reasoning_effortnone
  • Extract a quantity

    user

    Return JSON with quantity and item: We need twelve blue notebooks. Preserve the color in the item name. Answer in at most 75 words.

    max_tokens384reasoning_effortnone

Where it fits

  • Use cases

    For a support intake queue, define the categories, urgent conditions and an explicit unknown outcome. Include a few boundary cases in the instructions. Route unclear messages to review rather than allowing a mandatory label to conceal missing evidence. For invoice preparation, provide a readable document image and ask Luna to preserve the invoice identifier, currency and line amounts in separate fields. Compare totals and source identifiers in code before writing a record to the accounting system.

Model reference

GPT 5.6 Luna API reference

How to call the GPT 5.6 Luna API

  1. Prompt guide & Pro tips

    Design one stable contract for the queue and include only examples that teach a difficult distinction. State which source field supplies each output and how absent information should be represented. Keep identifiers as strings when leading zeroes matter. For a rewrite, specify the maximum length and the facts that must survive unchanged. Begin with a representative labeled evaluation set and measure accepted results, retries and review volume together. A smaller output cap limits generation but includes reasoning, so an exhausted cap may leave no usable answer. Use reasoning none for explicit temperature or top_p adjustments, and inspect the terminal status before accepting an item. Separate independent requests with bounded concurrency in your own worker; do not treat a model's high-volume positioning as a guarantee of a particular rate limit or response time.

GPT 5.6 Luna API questions

All GPT models18