VidgoAI

GPT 5.6 Luna API

openai/gpt-5.6-luna
1M tokens · 11.2 input credits / 1M tokens

GPT 5.6 Luna converts prompts and conversation history into answers, labels, extracted fields, summaries, and rewrites. Its lower Vidgo token rates make it the GPT 5.6 option for routine chat and high-volume text processing where cost per request is a primary constraint.

GPT 5.6 Luna

OpenAI · responses

Chat with GPT 5.6 Luna

Each model has its own conversation. Switching never sends another model's history, and switching back resumes where you left off. Requests are billed from actual token usage.

Ctrl / ⌘ + Enter to send0 / 32,000

Continue with

GPT 5.6 SolGPT 5.6 TerraKimi K3

GPT 5.6 Luna

GPT 5.6 Luna accepts a text string or ordered message array and returns generated text plus usage in synchronous JSON or SSE. Narrow prompts, explicit labels, and compact relevant context make it suitable for repeatable routine operations.

Why Choose This?

  • Lowest GPT 5.6 ratesProcess routine text at 11.2 input and 67.2 output credits per 1M tokens.

  • High-volume text operationsApply narrow prompts and explicit schemas to classification, extraction, rewriting, and routing workloads.

  • Routine conversational workflowsUse compact conversation history for support answers, product guidance, and common internal requests.

Parameters

ParameterRequirementDescription
inputRequired

A text string or ordered message array containing the task, supporting context, and conversation history.

max_output_tokensOptional

Sets the maximum number of tokens the model may return for this response.

streamOptional

Set false for synchronous JSON or true for an ordered SSE event stream.

Defaultfalsetrue

How to Use

  1. Narrow the operationDefine one classification, extraction, rewrite, summary, or conversation task per prompt.

  2. Constrain the answerProvide allowed labels, required fields, tone, or a compact format for the returned text.

  3. Keep context relevantInclude only the conversation turns and source text needed for the current operation.

  4. Sample and validateTest representative inputs and review labels or fields before scaling the prompt to higher volume.

Pricing

Vidgo AI meters input, output, cache-read, and cache-write tokens separately, then settles their sum in credits. Rates below are per 1M tokens.

UsageRateDetails
Input tokens11.2 credits / 1M tokensInput usage that does not hit prompt cache.
Output tokens67.2 credits / 1M tokensTokens generated by the model.
Cache read1.12 credits / 1M tokensInput tokens read from prompt cache.
Cache write14 credits / 1M tokensInput tokens written to prompt cache.

Best Use Cases

  • Request classification pipelineTurn support tickets or product events into bounded labels for routing and reporting.

  • Support reply draftingCombine a customer question and relevant policy excerpt into a concise draft for agent review.

  • Content normalizationConvert notes, listings, or form submissions into a required style, summary, or field set.

Pro Tips

  • Use a closed label set and define how to handle ambiguous inputs when Luna powers classification or routing.
  • Request only the fields downstream code consumes and set a compact output-token cap for routine operations.
  • Validate a sample from each important input category before applying one prompt to a high-volume workload.

Notes

  • The context window is 1M tokens, and the maximum output is 128K tokens.
  • GPT 5.6 Luna uses /v1/responses on Vidgo AI.
  • The minimum positive charge for a successful request is 0.001 credit; requests without valid output are not charged.
  • If a provider returns valid content without usage, the backend estimates token usage for settlement.

Related Models

GPT 5.6 SolOpenAI · 1M tokensGPT 5.6 Sol text generation API from 280 credits per 1M input tokens.
GPT 5.6 TerraOpenAI · 1M tokensGPT 5.6 Terra text generation API from 112 credits per 1M input tokens.
Kimi K3Moonshot AI · 1,048,576 tokensKimi K3 text generation API from 456 credits per 1M input tokens.
Claude Opus 5Anthropic · 1M tokensClaude Opus 5 text generation API from 400 credits per 1M input tokens.
Claude Sonnet 5Anthropic · 1M tokensClaude Sonnet 5 text generation API from 170 credits per 1M input tokens.

GPT 5.6 Luna API — Frequently asked questions

What is the GPT 5.6 Luna API?

GPT 5.6 Luna is developed by OpenAI. It accepts text or conversation messages and returns generated text plus usage through Vidgo AI.

How do I call the GPT 5.6 Luna API?

Send a Bearer-authenticated POST request to /v1/responses with model gpt-5-6-luna and valid input. Use stream: false for JSON or stream: true for SSE.

How much does GPT 5.6 Luna cost?

Per 1M tokens, Vidgo charges 11.2 credits for input, 67.2 for output, 1.12 for cache reads, and 14 for cache writes. The minimum positive charge for a successful request is 0.001 credit.

What inputs does GPT 5.6 Luna accept?

The Responses endpoint accepts input as a text string or message array. You can also set max_output_tokens and choose synchronous JSON or SSE with stream.

Which GPT 5.6 tier should I choose?

Choose Luna for routine chat, classification, extraction, and rewriting at high volume. Choose Terra for broader recurring production work or Sol for the most demanding multi-step reasoning and software tasks.