About GPT-5.6 Luna
GPT-5.6 Luna is the smallest member of the GPT-5.6 family, built for cost-sensitive, high-volume work: classification, extraction, routing and summarisation at scale. It inherits the traits that define the family — text-and-image input, a million-token-class context window, adjustable reasoning effort and the standard tool set — so a pipeline prototyped on a bigger sibling ports down without code changes.
What distinguishes Luna is economics rather than features: OpenAI places it where the nano tier sat in earlier GPT-5 generations, the default choice when the task is simple and the request count is enormous.
Luna is priced for volume: input is cheap and cached input is close to free, so high-traffic services with a shared system prompt run at per-request costs that round to fractions of a cent. Output is the line to watch — as everywhere in the family it costs a multiple of input, and chatty responses erode the advantage quickly. The long-prompt multiplier applies here too, which can surprise: filling the giant context window on the budget tier raises the bill precisely where you were counting pennies. Spot-check hard cases against Terra before committing a pipeline.
Frequently asked questions
How much does the GPT-5.6 Luna API cost?
GPT-5.6 Luna costs $0.2 per million input tokens and $1.2 per million output tokens, with cached input at $0.02 per million (90% off). Note: Prompts over 272K input tokens are billed at 2× input and 1.5× output for the whole request.
How much does a typical chat message cost with GPT-5.6 Luna?
A short chat message (about 500 input and 250 output tokens) costs roughly $0.0004 with GPT-5.6 Luna. At 1,000 such requests a day, that is about $12.00 per month.
Is GPT-5.6 Luna cheap compared to similar models?
GPT-5.6 Luna has the #5 cheapest input rate of the 29 models we track. On a mixed workload (10K input / 2K output), it costs $0.0044 per request, versus $0.0018 for Gemini 2.5 Flash-Lite and $0.0070 for DeepSeek V4 Flash.
What does GPT-5.6 Luna cost per 1,000 tokens?
Per 1,000 tokens, GPT-5.6 Luna costs $0.00020 for input and $0.0012 for output, or $0.00002 for cached input. Providers quote rates per million tokens ($0.2/M in, $1.2/M out here), so divide by a thousand for the per-1K figure older pricing pages used.
How large a prompt can GPT-5.6 Luna take?
GPT-5.6 Luna accepts up to 1025K tokens of input context and can generate up to 125K tokens of output per request. At its input rate, filling the entire 1025K-token window costs about $0.210 per request before any output.
Related
Compare all models at once ·Count tokens in your prompt
All OpenAI model costs: GPT-5.6 Sol · GPT-5.6 Terra · GPT-5.4 · GPT-5 · GPT-5 mini · GPT-5 nano · GPT-4o · GPT-4o mini · o3 · o4-mini
Last updated 2026-09-03. Prices verified against OpenAI's official pricing page; see the methodology.