GPT-6 Luna API
openai/gpt-6-lunaGPT-6 Luna turns text into summaries, classifications, extracted information, and concise rewrites for focused, high-volume tasks. Guide each response with system instructions, carry context through follow-up messages, and set the output budget to suit your workflow.
GPT-6 Luna
OpenAI · chat-completions
Quick start
Send a POST request to /v1/chat/completions with openai/gpt-6-luna. Choose JSON or SSE with stream, and receive generated content and usage.
- Endpoint
- POST /v1/chat/completions
- Model ID
- openai/gpt-6-luna
- Protocol
- Chat Completions
Request fields
| Field | Requirement | Description |
|---|---|---|
| model | Required | openai/gpt-6-luna |
| messages | Required | A non-empty array with role and text content; use system, user, or assistant roles. |
| max_tokens | Optional | A positive integer setting the response output limit; playground range: 1–65,536, default 4,096. |
| temperature | Optional | Sampling temperature from 0 to 2; defaults to 1. |
| top_p | Optional | Nucleus sampling probability from 0 to 1; defaults to 1. |
| stream | Optional | Defaults to false for complete JSON; true returns SSE events. The playground streams replies. |
Response and usage
Successful responses include generated content and usage. Billing settles from actual input, output, and cache tokens.
Streaming
Set stream: true to read SSE. Finalize usage accounting from the terminal usage event.
curl --request POST \
--url "https://api.vidgo.ai/v1/chat/completions" \
--header "Authorization: Bearer $VIDGO_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "openai/gpt-6-luna",
"temperature": 1,
"top_p": 1,
"stream": false,
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Summarize this customer request in one sentence: Please change my delivery address before the order ships."
}
],
"max_tokens": 4096
}'Keep API keys on the server. Never expose them in browser code or public repositories.
Continue with
Related Models
GPT-6 Luna API frequently asked questions
What is the GPT-6 Luna API?
GPT-6 Luna is an OpenAI model for focused, high-volume text tasks. It turns source text into summaries, classification labels, extracted information, and rewritten drafts. System instructions, ordered conversation history, and an output-token budget guide the response toward the requested task and scope. You can call it programmatically or try it from the playground above.
How does GPT-6 Luna summarize documents?
GPT-6 Luna condenses supplied text into a summary for a specified audience and length. Include the source passage, identify the facts to retain, and request a format such as one paragraph or a short list of action items.
How can GPT-6 Luna classify support messages?
GPT-6 Luna can assign a message to a defined category set. Put the labels and their definitions in the system instructions, include representative examples, and ask for the selected label as the text answer.
How does GPT-6 Luna extract information?
GPT-6 Luna identifies requested details in supplied text, such as names, dates, amounts, and action items. Specify the fields, their order, and the text to use for an empty value so the answer follows a consistent pattern.
How can GPT-6 Luna rewrite a draft?
GPT-6 Luna revises supplied text to a requested tone, audience, and length. Identify the names, figures, and commitments to retain, then describe the style of the revised draft.
How can GPT-6 Luna explain code?
GPT-6 Luna can explain a function or suggest a focused change to a short code fragment. Supply the code, intended behavior, and relevant error or test result to keep the explanation tied to the task.
How does GPT-6 Luna retain conversation context?
GPT-6 Luna uses the ordered messages included in each request as conversation context. The playground carries the current conversation into follow-up messages, letting you refine a summary or draft against the same source material.
How long can GPT-6 Luna replies be?
The GPT-6 Luna model specification lists 128,000 output tokens. The playground provides a 1–65,536-token output budget with a default of 4,096. Set Max Tokens for Chat Completions or Max Output Tokens for Responses to match the length of the requested answer.