# GPT-6 Luna

GPT-6 Luna is an AI model released by OpenAI on Sep 22 2026. It has a 1.05M context window. Tracked results include 59% on BullshitBench v2, 59.3% on ARC-AGI-2 and 66.6% on DeepSWE 1.1.

## Facts

| Field | Value |
| --- | --- |
| Model | GPT-6 Luna |
| Developer | OpenAI |
| Release date | Tuesday, Sep 22 2026 |
| Licensing | Closed |
| Context window | 1.05M |

## API pricing

All rates in USD per 1,000,000 tokens, pay-as-you-go.

| Tier | Input | Cached input | Cache write | Output |
| --- | --- | --- | --- | --- |
| Up to 272K input tokens | $0.10 | $0.01 | $0.125 | $0.50 |
| Over 272K input tokens | $0.20 | $0.02 | $0.25 | $0.75 |

OpenAI also publishes a Fast mode for this model at exactly twice the standard rate in every column — $0.20 per million input tokens and $1.00 per million output at short context.
Verified October 19, 2026 against the first-party source: https://developers.openai.com/api/docs/models/gpt-6-luna

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| BullshitBench v2 | 59% | [BullshitBench](https://github.com/petergpt/bullshit-benchmark) | Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. |
| DeepSWE 1.1 | 66.6% | Lab | Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. |
| Next.js Evals | 86% | [Next.js Evals](https://nextjs.org/evals) | Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. |
| Supabase Evals (with skills) | 75.4% | [Supabase Evals](https://supabase.com/evals) | Supabase's own open benchmark: a coding agent is dropped into a real Supabase project and asked to do real work — set up a schema, fix a broken security policy, debug an Edge Function — and every run is checked against a live Supabase stack. This is the headline number, where the agent has Supabase's own skills loaded, as most people building on Supabase would. The score is the share of scenarios it got right. Higher is better. |
| Supabase Evals (no skills) | 63.8% | [Supabase Evals](https://supabase.com/evals) | The same Supabase scenarios, but with none of Supabase's skills loaded — so it measures what the model already knows about building on Supabase, rather than how well it follows Supabase's supplied instructions. Higher is better. |
| Terminal-Bench 4.0 | 16.36% | [Terminal-Bench](https://github.com/harbor-framework/terminal-bench), retrieved 2026-10-12 | Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Version 4.0 recalibrated how much time, CPU and memory each task gets, removed eight tasks and fixed nineteen, so fewer runs fail for reasons that have nothing to do with the model. Scores are not comparable with earlier versions. Higher is better. |
| ARC-AGI-2 | 59.3% | [BenchLM](https://benchlm.ai), retrieved 2026-09-28 | Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. |
| threejseval | 1365 | [threejseval](https://threejseval.com/ranking) | Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better. |

## About GPT-6 Luna

GPT-6 Luna was introduced in September 2026 as the smaller, efficiency-focused model in OpenAI's GPT-6 family, alongside Sol. OpenAI positioned it for frequent, focused tasks and offered it through the API and selected ChatGPT experiences. At launch, Free and Go users could access Luna in the desktop app, while access through other plans and interfaces followed the announced product rules.

The API documented text and image inputs, text output and a 1,050,000-token context window, with adjustable reasoning effort. Its smaller-tier role did not imply a short context limit or downloadable weights. The release emphasized lower operating cost for repeated work; performance and latency still depended on the chosen reasoning setting and surrounding application.

## Questions and answers

### When was GPT-6 Luna released?

GPT-6 Luna was released by OpenAI on Tuesday, Sep 22 2026.

### Who made GPT-6 Luna?

GPT-6 Luna was built by OpenAI. Creators of ChatGPT and the GPT series of models. Pioneered large-scale language model research.

### How much does GPT-6 Luna cost?

GPT-6 Luna costs $0.10 per million input tokens and $0.50 per million output tokens through the OpenAI API. Cached input is $0.01 per million tokens. Those are the rates for the “Up to 272K input tokens” tier; 1 other pricing tier is published for this model. Rates are pay-as-you-go API prices verified against OpenAI's published pricing on October 19, 2026.

### What benchmark scores did GPT-6 Luna get?

GPT-6 Luna reports 8 tracked benchmark scores — BullshitBench v2: 59%; DeepSWE 1.1: 66.6%; Next.js Evals: 86%; Supabase Evals (with skills): 75.4%; Supabase Evals (no skills): 63.8%; Terminal-Bench 4.0: 16.36%; ARC-AGI-2: 59.3%; threejseval: 1365. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### What is the context window of GPT-6 Luna?

GPT-6 Luna has a context window of 1.05M. Providers may specify separate input and output token limits.

### Is GPT-6 Luna open source?

No. GPT-6 Luna is a closed model. The weights are not published — it is available only through the provider's own API, apps, or partner platforms.

### What came before and after GPT-6 Luna?

OpenAI's previous tracked release was GPT-6 Sol on Sep 22 2026. It was followed by GPT-6.1 Sol on Sep 29 2026.


---

Canonical page: https://aireleasetracker.com/model/openai/gpt-6-luna
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.