model comparison

vs

GPT 5.6 Luna vs GPT 5.6 Terra

two OpenAI models, compared on listed price, real workload cost, context and capabilities.

the short answer

  • GPT 5.6 Luna lists lower input and output prices.
  • GPT 5.6 Luna reads cached input for less ($0.02/M against GPT 5.6 Terra's $0.2/M), which decides the bill for agents that resend long context.
  • GPT 5.6 Luna retired on 6 October 2026; its numbers are kept for reference.
  • GPT 5.6 Terra retired on 10 November 2026; its numbers are kept for reference.

side-by-side specs

specGPT 5.6 LunaGPT 5.6 Terra
providerOpenAIOpenAI
input price$0.2/M$2/M
output price$1.2/M$12/M
cached input$0.02/M$0.2/M
blended price (3:1)$0.45/M$4.5/M
context window1M tokens1M tokens
max output128k tokens128k tokens
inputtext, imagestext, images
structured outputyesyes
weightsclosedclosed
availabilityretired 6 October 2026retired 10 November 2026

same work, both models

workloadGPT 5.6 LunaGPT 5.6 Terra
one chat reply3,000 tokens in, 500 outGPT 5.6 Terra costs 10× as much as GPT 5.6 Luna$0.0012$0.01
summarise a 100-page report50,000 tokens in, 1,500 out, one request$0.01$0.12
1,000 classification calls500 tokens in, 20 out, per call$0.12$1.24
coding-agent session2M tokens in across ~60 turns, 60,000 out, no cache$0.47$4.72
same session, cached85% of input read from the prompt cache, the rest written to it$0.18$1.81

at listed rates. token counts are typical sizes, not measurements.

GPT 5.6 Luna pricing notes

  • requests over 272K input tokens billed at 2x input and 1.5x output for the whole request; the listed price is the standard rate.

GPT 5.6 Terra pricing notes

  • once a request passes 272K input tokens, the whole request bills at 2x input and cache rates and 1.5x output; the listed price is the standard rate.
  • cache writes bill at $2.50 per 1M tokens (1.25x input); cache reads at $0.20 per 1M (0.1x input).

when to pick which

GPT 5.6 Luna

GPT 5.6 Luna was the lowest-priced tier of OpenAI's GPT-5.6 family, below Terra and Sol, which OpenAI says roughly matches the earlier nano tier. it retired on 2026-10-06, replaced by the cheaper GPT-6 Luna.

pick it if

  • you needed the cheapest GPT-5.6 tier for high-volume text and image work
  • you reused long prompts, since cached reads billed at a tenth of input
  • you wanted adjustable reasoning effort, from none up to max

skip it if

  • GPT-6 Luna is available: same window, half the input price

GPT 5.6 Terra

the middle tier of OpenAI's GPT-5.6 family (Sol, Terra, Luna), which OpenAI positions for workloads that balance intelligence and cost. Sol and Luna are retired here; GPT-6.1 Sol matches its input price with cheaper output.

pick it if

  • you want the tier OpenAI called GPT-5.5-competitive at 2x lower cost
  • your prompts repeat: cached input bills at $0.20 per million
  • you need image input and up to 128K output tokens

skip it if

  • output dominates your bill: GPT-6.1 Sol charges $10 versus $12
  • prompts routinely pass 272K tokens, where every rate in the request rises

faq

which is cheaper, GPT 5.6 Luna or GPT 5.6 Terra?

GPT 5.6 Luna lists lower input and output prices. on a coding-agent session (2M tokens in, 60,000 out) GPT 5.6 Luna costs $0.47 and GPT 5.6 Terra $4.72.

try either model

switch between models inside the same octomind session.

prices from the catalog of 2026-11-18