# gpt-6-luna decision evidence

GPT-6 Luna is OpenAI's closed-weight model for focused, high-volume tasks, released on 2026-09-22 alongside GPT-6 Sol, with a 1,050,000-token context window (922,000 input), 128,000 output tokens and text and image input. In the one reviewed test it was the quickest and lightest on quota of four GPT-6 and GPT-5.6 models given the same prompt, but the author judged its output a flop.

Verified: 2026-09-24; snapshot: 2026-09-24.

## Published model card

As the vendor publishes it for the model and its weights; these are not the limits of a hosted endpoint.

- Context window: 1,050,000 tokens (up to 922,000 input)
- Maximum output: 128,000 tokens
- Modalities: Text and image input; text output
- Parameter count: Not disclosed

## Open weights and deployment

Status: Unavailable. OpenAI publishes no GPT-6 Luna weights. The model is served through the OpenAI API (Responses, Chat Completions and Batch) and on Amazon Bedrock in us-east-1.

Open-weight alternatives: [deepseek-flash](https://dash.chinaapi.ai/models/deepseek-flash/deploy), [mimo-v2.6-flash](https://dash.chinaapi.ai/models/mimo-v2.6-flash/deploy)

## Real-task reports

### [GPT-6 Astra, Sol and Luna on one SVG animation prompt](https://x.com/xueyu1125/status/2102692499710193960)

By [雪瑜](https://x.com/xueyu1125) (@xueyu1125). Programmer and AI-tools builder on X who posted the timings and quota readings

Published: 2026-09-23; retrieved: 2026-09-24; verified: 2026-09-24.

- Task: Generate an SVG animation of a pelican riding a bicycle, shown in H5
- Method: Same prompt on GPT-6 Astra, GPT-6 Sol, GPT-6 Luna and GPT-5.6 Sol; the author recorded time taken and the share of a five-hour subscription quota each used.
- Finding: GPT-6 Luna was the quickest and lightest of the four at 2 min 18 s and 1% of the five-hour quota, but the author dismissed its result as a flop (“拉完了”), ranking it alongside MiMo-V2.6-Flash.
- Limitation: One prompt judged by the author without a score; the quota shares are a subscription meter, not API cost. X's automatic translation renders the verdict as its opposite, so read the original Chinese.
- Time: 2 min 18 s
- Five-hour quota used: 1%

## Public leaderboard coverage

A board missing from this list has no figure for this model in this snapshot; missing coverage is not a zero.

- Artificial Analysis Intelligence Index — Intelligence Index: 37 (retrieved 2026-09-22) [source](https://artificialanalysis.ai/leaderboards/models)
- Artificial Analysis · Output Speed — Median output tokens/s: 157 (retrieved 2026-09-22) [source](https://artificialanalysis.ai/leaderboards/models)
- Artificial Analysis · GDPval-AA v2.1 — Agentic Real-World Work Tasks, (Elo-500)/2000 (%): 43 (retrieved 2026-09-22) [source](https://artificialanalysis.ai/leaderboards/models)
- Artificial Analysis · Terminal-Bench v4.0 — Agentic Coding & Terminal Use (%): 13 (retrieved 2026-09-22) [source](https://artificialanalysis.ai/leaderboards/models)

## Curated comparisons

- [gpt-6-astra vs gpt-6-luna](https://dash.chinaapi.ai/models/compare/gpt-6-astra-vs-gpt-6-luna)
- [gpt-6-luna vs gpt-6-sol](https://dash.chinaapi.ai/models/compare/gpt-6-luna-vs-gpt-6-sol)

## Official sources

- [GPT-6 Luna model documentation](https://developers.openai.com/api/docs/models/gpt-6-luna) — OpenAI, retrieved 2026-09-24
- [OpenAI API changelog](https://developers.openai.com/api/docs/changelog) — OpenAI, retrieved 2026-09-24
- [GPT-6 Astra System Card (appendix on GPT-6 Sol and GPT-6 Luna)](https://deploymentsafety.openai.com/gpt-6-astra) — OpenAI, retrieved 2026-09-24