GPT-5.6 Luna is the smallest and lowest-cost model in OpenAI’s GPT-5.6 family. Use it for high-volume, latency-sensitive, or cost-sensitive agent work where Sol or Terra would be more than you need.

Strengths

  • Lowest GPT-5.6 pricing; good for prototyping, subagents, and high-volume loops.
  • Fast responses relative to larger GPT-5.6 variants.
  • Same family tool-calling and agent support as Sol and Terra.

Limitations

  • Not a frontier model. For harder problems where peak intelligence matters, GPT-5.6 Sol or GPT-5.6 Terra is the better pick.
  • Smaller capacity for long, open-ended reasoning chains.

Tools

GPT-5.6 Luna has access to all agent tools when used with Cursor including:

Learn more about how tools work and tool calling fundamentals.

Pricing

Cursor plans include two usage pools. GPT-5.6 Luna draws from the third-party Other Models pool, which charges at the rates below. All prices are per million tokens.

A Fast mode tier (gpt-5.6-luna-fast) is available for priority processing at 2x the standard rates.

When input exceeds 272k tokens (long context), input pricing doubles and output pricing is 1.5x the standard rate. The same multipliers apply in Fast mode: long-context requests bill at 2x the Fast input, cache write, and cache read rates, and 1.5x the Fast output rate.