Unstructured text data
AI Models & Assistants / Knowledge library
GPT-6 Luna
Our most efficient model for focused, high-volume tasks.
Why learn GPT-6 Luna?
Offers the documented OpenAI model capabilities through hosted.
The problem it solves
Provides model inference for supported text / image inputs.
Where it came from
GPT-6 Luna: Our most efficient model for focused, high-volume tasks. Published aliases: gpt-6-luna. Input: text, image. Output: text. Checked 2026-10-13. Model capabilities are distinct from tools available in a particular agent.
Build your understanding
Work through these exercises in order. Try the task before opening a reference.
- Explain what GPT-6 Luna does.
- Identify a use case for GPT-6 Luna.
- Describe a limitation of GPT-6 Luna.
- Name a compatible tool for GPT-6 Luna.
- Compare GPT-6 Luna against an alternative.
Documentation and sources
- Primary source / model card (developers.openai.com)
Catalog research notes
- See the AI Workbench for source dates, pricing evidence and configuration details.
Connect the ideas
Built on
Real World Example
High-Volume Regulatory Document Synthesis
Global financial compliance firms processing thousands of daily transaction audit logs.
The business problem
Legacy systems struggle with the high-volume ingestion and structured extraction of audit logs, leading to delayed compliance reporting and increased operational overhead.
How this topic solves it
GPT-6 Luna provides an efficient architecture for high-volume tasks by utilizing the Responses API to perform structured data extraction directly from raw audit logs, minimizing latency and maximizing throughput.
- Ingest raw transaction logs into the system as text input.
- Configure the Responses API to utilize built-in tools for structured data parsing.
- Set reasoning_effort to none to enable function calling for rapid, deterministic extraction.
- Execute batch processing requests to handle large volumes of logs efficiently.
- Validate extracted entities against regulatory schema requirements.
The flow shows how raw logs are processed through the model to reach a structured compliance output.
Processing engine
Tool-enabled interface
Compliance-ready data
- Raw Audit Logs → Ingestion → GPT-6 Luna
- GPT-6 Luna → Tool invocation → Responses API
- Responses API → Extraction → Structured Report
Expected business outcome
Improved consistency in regulatory reporting and reduced manual review time for compliance officers.
Limitations and checks
Setting reasoning_effort to none disables advanced chain-of-thought processing, which may reduce accuracy on highly ambiguous or complex interpretive tasks; verify output quality by comparing samples against human-audited benchmarks.