CorX Labs
Open the chat
Open the chat

GPT-6 Luna

by OpenAI · United States
ProprietaryReasoningVisionTool calling1.1M context

The smallest GPT-6, at ten cents per million input tokens — half what GPT-5.6 Luna cost on its promotional rate. OpenAI reports 66.6% on DeepSWE v1.1 at maximum effort, a coding benchmark this index does not track.

Specification

The numbers

Maker
OpenAI
Released
2026-09
Parameters
Not reported
Architecture
Not reported
Context window
1,050,000 tokens
Max output
Not reported
Input
Text, Image
Output
Text
Reasoning
Yes
Tool calling
Yes
Knowledge cutoff
Not reported
Licence
Proprietary
Availability
Not reported
Weights
Not released

API model ID: gpt-6-luna

Cost

Price per million tokens

Input
$0.10 / M tokens
Output
$0.50 / M tokens
Cached input
$0.01
Blended 3:1
$0.20

Standard first-party API rate, excluding batch discounts. Reasoning models bill thinking tokens as output, so cost per answer can far exceed the cost per token suggests.

Published scores

Benchmarks

Figures published by OpenAI or taken from a public leaderboard. Row last checked 2026-10.

Every reported test

No published benchmark scores yetIts maker has not published benchmark figures for this model, and nothing has been estimated in their place.

Where these numbers come from

Every score on this page is a published figure, taken from the model's own card, system card, technical report or release post, or from a public leaderboard. CorX Labs did not run these evaluations. Most are self-reported by the lab that built the model, which means they were produced under that lab's own choice of prompt, scaffold and number of attempts — so treat them as a starting point for a shortlist, not as a settled ranking.

A score someone other than the model's maker measured is marked Independent and names its measurer. Those are the stronger numbers on this page — an outside harness has no reason to flatter anyone — and there are not many of them.

Where a figure has not been published, the cell reads Not reported rather than an estimate. Nothing here is inferred, interpolated or guessed. Each model records the month its row was last checked. Full method and caveats.

Head to head

GPT-6 Luna compared

vs Claude Haiku 5.5Anthropic
Compare with something else

Same maker

Other models from OpenAI
GPT-6 AstraOpenAIOpenAI1.1M$10.00$50.00—96%——Proprietary
GPT-6.1 SolOpenAIOpenAI1.1M$2.00$10.00————Proprietary
GPT-5.6 SolOpenAIOpenAI1.1M$4.00$20.00—94.6%——Proprietary
GPT-5.6 TerraOpenAIOpenAI—$2.00$12.00—92.9%——Proprietary
GPT-5.6 LunaOpenAIOpenAI—$0.20$1.20—92.3%——Proprietary
GPT-5.5OpenAIOpenAI1.1M$5.00$30.00—93.6%——Proprietary
GPT-5.2OpenAIOpenAI400K$1.75$14.00—92.4%100%80%Proprietary
GPT-5OpenAIOpenAI400K$1.25$10.00—85.7%94.6%74.9%Proprietary
GPT-5 miniOpenAIOpenAI400K$0.25$2.00—82.3%91.1%71%Proprietary
GPT-5 nanoOpenAIOpenAI400K$0.05$0.40—71.2%85.2%—Proprietary
gpt-oss-120bOpenAIOpenAI131K$0.10$0.5080.9%80.1%92.5%—Apache 2.0
gpt-oss-20bOpenAIOpenAI131K$0.05$0.2073.2%71.5%90%—Apache 2.0
o3OpenAIOpenAI200K$2.00$8.00—83.3%88.9%69.1%Proprietary
o4-miniOpenAIOpenAI200K$1.10$4.40—81.4%92.7%68.1%Proprietary
GPT-4.1OpenAIOpenAI1M$2.00$8.0080.5%66.3%—54.6%Proprietary
GPT-4.1 miniOpenAIOpenAI1M$0.40$1.60—65%—23.6%Proprietary
GPT-4.1 nanoOpenAIOpenAI1M$0.10$0.40—50.3%——Proprietary
o3-miniOpenAIOpenAI200K$1.10$4.40—79.7%87.3%49.3%Proprietary
o1OpenAIOpenAI200K$15.00$60.00—78%79.2%48.9%Proprietary
o1-miniOpenAIOpenAI128K$1.10$4.40—60%63.6%—Proprietary
GPT-4o miniOpenAIOpenAI128K$0.15$0.6063.1%40.2%——Proprietary
GPT-4oOpenAIOpenAI128K$2.50$10.0074.7%53.6%——Proprietary
GPT-4 TurboOpenAIOpenAI128K$10.00$30.0063.7%48%——Proprietary
GPT-3.5 TurboOpenAIOpenAI16K$0.50$1.5038%———Proprietary
OpenAI