model comparison

vs

GPT 5.6 Luna vs GPT 5.6 Sol

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 Sol's $0.4/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 Sol retired on 6 October 2026; its numbers are kept for reference.

side-by-side specs

specGPT 5.6 LunaGPT 5.6 Sol
providerOpenAIOpenAI
input price$0.2/M$4/M
output price$1.2/M$20/M
cached input$0.02/M$0.4/M
blended price (3:1)$0.45/M$8/M
context window1M tokens1M tokens
max output128k tokens128k tokens
inputtext, imagestext, images
structured outputyesyes
weightsclosedclosed
released—July 9, 2026
availabilityretired 6 October 2026retired 6 October 2026

same work, both models

workloadGPT 5.6 LunaGPT 5.6 Sol
one chat reply3,000 tokens in, 500 outGPT 5.6 Sol costs 18× as much as GPT 5.6 Luna$0.0012$0.02
summarise a 100-page report50,000 tokens in, 1,500 out, one requestGPT 5.6 Sol costs 19× as much as GPT 5.6 Luna$0.01$0.23
1,000 classification calls500 tokens in, 20 out, per call$0.12$2.40
coding-agent session2M tokens in across ~60 turns, 60,000 out, no cache$0.47$9.20
same session, cached85% of input read from the prompt cache, the rest written to it$0.18$3.38

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 Sol pricing notes

  • listed rate is OpenAI's promotional price (down from $5 / $30 on 2026-08-21), offered at least through 2026-11-21.
  • requests over 272K input tokens bill 2x input and cache rates and 1.5x output for the whole request.

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 Sol

GPT 5.6 Sol was the frontier tier of OpenAI's GPT-5.6 family, above Terra and Luna, billed at OpenAI's promotional rate. it retired from the catalog on 2026-10-06 in favour of GPT-6 Sol, which costs half as much.

pick it if

  • you needed the GPT-5.6 family's frontier tier above Terra and Luna
  • you reused long prompts: cached input billed at 0.1x the input rate
  • you needed image input with up to 128K output tokens

skip it if

  • GPT-6 Sol covers the work at half the promotional rate
  • GPT-5.6 Terra covered your workload at a lower price

faq

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

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 Sol $9.20.

try either model

switch between models inside the same octomind session.

prices from the catalog of 2026-11-18