GPT-5.6 Luna · OpenAI

What does GPT-5.6 Luna cost to run in a coding agent?

GPT-5.6 Luna costs about $0.0084 per average coding-agent request on our measured traffic, at list prices of $0.20 per million input and $1.20 per million output tokens. It scores 37 on the Artificial Analysis Intelligence Index, 23rd of the 48 models we track. Source: Artificial Analysis (artificialanalysis.ai)

List prices: OpenAI API pricing, checked 2026-10-13. Request costs: Standard Compute gateway data, 79,301 coding-agent requests from 75 users, Sep 13 to Oct 12, 2026. How we compute this

A newer version is out. GPT-6 Luna →

Run GPT-5.6 Luna in your agent from $19/month

See plans

What GPT-5.6 Luna costs per coding-agent request

Cost at list price	GPT-5.6 Luna
Prompt under 100K tokens50% of requests, 87% of input cached	$0.0032
Prompt of 100K to 272K39% of requests, 88% of input cached	$0.0080
Prompt over 272K tokens11% of requests, 86% of input cached	$0.034
Average request	$0.0084
100 requests	$0.84
Median session16 requests; a session ends after 10 idle minutes	$0.092
A month of regular usemedian of 20 users active on 5+ days	$11.83

Each logged request priced at the vendor’s list rates for its own token counts, including cache reads and any higher rate for long prompts. Average output: 698 tokens per request.

GPT-5.6 Luna benchmarks, speed and latency

Artificial Analysis	Value	Rank
Intelligence Index10 evaluations, 0 to 100	37	23 of 48
Terminal-Bench 4.0agentic coding in a terminal	11.6%	23 of 39
Output speedmedian	123 tokens/s	12 of 44
Time to first answer tokenincludes thinking time	117 s	32 of 44

Source: Artificial Analysis (artificialanalysis.ai). Measured variant: GPT-5.6 Luna (Max), speed on OpenAI. Fetched October 13, 2026. Rank is among the models on this site, older versions included. Artificial Analysis runs Terminal-Bench 4.0 in its own setup, so its scores differ from the tbench.ai leaderboard.

About GPT-5.6 Luna

GPT-5.6 Luna is the low-cost tier of OpenAI's GPT-5.6 family, released July 9, 2026 for summarization, drafting, routing and the many small calls agents make. It lists at $0.20/$1.20 per million tokens with a 1,050,000-token context and an optional pro reasoning mode. GPT-6 Luna replaced it in September 2026 at half the price and scores slightly higher: 38 against 37 on the Artificial Analysis Intelligence Index, and 12.6% against 11.6% in Artificial Analysis's Terminal-Bench 4.0 run.

Sources: Artificial Analysis

GPT-5.6 Luna FAQ

How much does GPT-5.6 Luna cost per coding-agent request?

$0.0084 on average at list price, $0.84 per 100 requests, and $0.092 for a median 16-request session. That is 79,301 real coding-agent requests (Sep 13 to Oct 12, 2026) priced at OpenAI's list rates; the median request sent 99,534 input tokens, 87% of input was read from cache, and requests returned 698 output tokens on average.

Does GPT-5.6 Luna charge more for long prompts?

Yes. Prompts over 272K tokens are billed at $0.40 per million input and $1.80 per million output tokens, on every token in the request including cache reads. 11% of the coding-agent requests we measured were that large.

How fast is GPT-5.6 Luna?

Artificial Analysis measures GPT-5.6 Luna (Max) at 123 output tokens per second, with 117 seconds to the first answer token, thinking time included, on OpenAI's API. Source: Artificial Analysis (artificialanalysis.ai).

Is GPT-5.6 Luna good for AI agents?

Cheap subtasks in existing GPT-5.6 setups. On our scoring, which is calibrated to public benchmarks, it rates 5.9/10 for agentic ability and 7.4/10 for output quality. 1M-token context at $0.20/$1.20 per million.

What is GPT-5.6 Luna's context window?

GPT-5.6 Luna has a 1.1M-token context window, large enough to hold sizeable codebases or document sets in a single run. OpenAI is the maker.

Can I self-host GPT-5.6 Luna?

No. GPT-5.6 Luna is a proprietary, hosted-only model from OpenAI. You access it through an API, such as OpenRouter, rather than running the weights yourself.

What are the downsides of GPT-5.6 Luna?

The main trade-offs: Superseded by GPT-6 Luna, which costs half as much per request ($0.0041 vs $0.0084); Weak on long agentic tasks (11.6% in Artificial Analysis's Terminal-Bench 4.0 run). It's strongest for cheap subtasks in existing GPT-5.6 setups.