Skip to main content

openai/gpt-6-luna/chat

GPT 6 Luna fits focused tasks that repeat often. Define a narrow output contract, supply representative examples and route ambiguous items for review.

Input $0.10Output $0.50per 1 million tokensCached input $0.01Cache write $0.125Prompts over 272K tokensInput $0.20Cached input $0.02Cache write $0.25Output $0.75

Workbench

GPT 6 Luna

What can GPT 6 Luna help with?

Related models and next tasks

Missing the model you need?

GPT 6 Luna fits focused tasks that repeat often. Define a narrow output contract, supply representative examples and route ambiguous items for review.

Key numbers

Context
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

Six reasoning settings

Luna supports none, low, medium, high, xhigh and max reasoning effort, with medium as the default. The none option suits short decisions with clear rules; a reasoning setting can help when several details must be compared. Its output limit is 128,000 tokens, including reasoning, though a compact classification normally benefits from a much smaller explicit allowance. Sampling controls apply only with reasoning set to none.

Typed review handoffs

Function calling lets Luna request a defined operation, such as handing an uncertain item to a review queue with a typed reason. The application checks the requested arguments and authorization before performing that operation, then returns the result under the matching call identifier. Keep the available function set small enough that the intended handoff remains unambiguous.

What a call to GPT 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.

  • Classify a support request

    user

    Classify this request as account_access, billing or other and include an uncertainty flag: I cannot reset my account password. Return JSON. Answer in at most 75 words.

    max_tokens384reasoning_effortnone
  • One-sentence summary

    user

    Summarize in one sentence: The delivery window changed from Tuesday morning to Wednesday afternoon because the bridge is closed. Answer in at most 75 words.

    max_tokens384reasoning_effortnone
  • Extract order details

    user

    Extract order number and quantity as JSON: Please send three replacement clips for order A-410. Do not infer missing fields. Answer in at most 75 words.

    max_tokens384reasoning_effortnone

Where it fits

  • Support-ticket triage

    For support-ticket intake, give Luna the routing categories and the evidence that separates them. Ask for a category, the relevant phrase and an uncertainty flag. Preserve a review branch for missing information or a ticket spanning several topics, then compare its assigned routes against a labeled sample.

  • Document-field extraction

    For document-field extraction, list the required fields, accepted types and representation of absent values. Test scanned layouts, alternate date formats and conflicting totals before using the output in a workflow. A well-formed JSON object proves that parsing succeeded; it does not establish that every extracted value matches the document.

Model reference

GPT 6 Luna API reference

GPT 6 Luna API specifications

Context
1,050,000 tokens

How to call the GPT 6 Luna API

  1. Prompt guide & Pro tips

    Give Luna concise instructions with examples that expose difficult category boundaries, rather than many nearly identical easy cases. Ask it to preserve identifiers exactly and separate a quoted observation from an inferred label. When the input does not support a required answer, allow the result to record that uncertainty. For repeated requests, keep stable instructions and schemas consistent so reusable prefixes remain useful. Regenerate document updates only when their contents change, and submit independent items with bounded concurrency in your application. Count reasoning in the output allowance when it is enabled. Inputs above 272,000 tokens use the long-prompt pricing tier for the entire request. Compare accuracy and the cost per accepted result before selecting an effort level for a production queue.

GPT 6 Luna API questions

All GPT models18