LLMPrice
Updated daily
OpenAI · Direct API

GPT-5.6 Luna pricing

Low-cost GPT model; prompts over 272K input tokens use long-context pricing.

DirectOfficial provider
Input$0.2per 1M tokens
Cached input$0.02per 1M tokens
Output$1.2per 1M tokens
Context1.05Mmaximum window
Endpoint and source

Direct API

Open Official provider source ↗

This is a first-party rate checked against the model provider's official pricing page.

Caching
2,000 input + 500 output tokens$0.001 / request
Calculate a complete workload →