MODELS
by OpenAI
OpenAI’s fastest, lowest-cost GPT-5.6 model for cost-sensitive, high-volume text, coding, reasoning, and tool-use workloads via the OpenAI API.
GPT-5.6 Luna is an OpenAI API model in the GPT-5.6 family. Supplied OpenAI sources describe it as the fastest, lowest-cost or most cost-efficient GPT-5.6 model and position it for cost-sensitive, high-volume workloads. The model-specific API page identifies GPT-5.6 Luna as a fast, high-reasoning model with text and image input, text output, a 1,050,000-token context window, 128,000 max output tokens, and Responses API tools. OpenAI’s GPT-5.6 guidance says to use gpt-5.6-luna for efficient high-volume workloads, and the preview system card covers safety evaluations, risk designations, and safeguards for Sol, Terra, and Luna.
Use for cost-sensitive or high-volume API workloads where OpenAI’s GPT-5.6 family is appropriate. Use for text coding reasoning or tool-use tasks where speed and lower cost are priorities. Use when OpenAI’s API guidance recommends gpt-5.6-luna for efficient high-volume workloads.
Last updated Jul 10, 2026