As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/gpt-6-luna/

# GPT-6 Luna

OpenAI, GPT-6 family. Status: current. Type: reasoning model. Released: 2026-09-22. Training cutoff: 2026-05.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| OpenAI API | `gpt-6-luna` | https://api.openai.com/v1/responses | https://developers.openai.com/api/docs/models/gpt-6-luna |
| Azure OpenAI (Microsoft Foundry) | `gpt-6-luna` |  | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure |
| OpenRouter | `openai/gpt-6-luna` |  | https://openrouter.ai/openai/gpt-6-luna |
| Web app |  |  | https://chatgpt.com |

## Pricing

- Input: $0.10 per 1M tokens
- Cached input: $0.01 per 1M tokens
- Output: $0.50 per 1M tokens
- Cache write: $0.125 per 1M tokens
- Unit as published: per 1M tokens (USD), standard tier
- Source: https://developers.openai.com/api/docs/pricing
- Last checked: 2026-10-08

## Specs

- Input: text, image
- Output: text
- Context window: 1,050,000 tokens
- Max output: 128,000 tokens
- Open weights: no
- Licence: proprietary

## What it has not seen

- Published training cutoff: 2026-05 (May 2026).
- AI events after it on Post-Cutoff: 1,829 (419 major, 82 historic), as of 2026-11-13.
- Already missing at launch: 406.
- Briefings of the news since May 2026: https://postcutoff.com/briefings/cutoff-2026-05-s.md (short), https://postcutoff.com/briefings/cutoff-2026-05-m.md (medium), https://postcutoff.com/briefings/cutoff-2026-05.md (full).
- Its card, with five things it has never heard of: https://postcutoff.com/you/gpt-6-luna/

## What stands out

- 1M context at $0.10/M: Cheapest OpenAI reasoning model with the full 1.05M context window and 128K output. Source: https://developers.openai.com/api/docs/models/gpt-6-luna
- Agentic tools on the budget tier: Supports computer use, hosted shell, MCP and tool search like the larger models. Source: https://developers.openai.com/api/docs/models/gpt-6-luna
- Free-tier ChatGPT model: Rolled out to ChatGPT free users and the desktop app at launch. Source: https://techcrunch.com/2026/09/22/openai-launches-gpt-6-sol-and-luna/
- Decisions API model (found after launch): Only model behind OpenAI's Decisions API (POST /v1/decisions, public beta since 2026-10-06): typed predicate/choice/score answers from text and images, about 10x faster than the Responses API, billed at $0.10 per 1M input tokens with no output charge. Source: https://developers.openai.com/api/docs/guides/decisions
- Intelligent UI in ChatGPT (October 2026 update) (found after launch): On Oct 7 2026 an October update of this model replaced GPT-5.6 in the ChatGPT Chat tab for Free and Go users; it composes answers with native streamable UI components (charts, maps, forms, buttons, calculators, small games) and can start answering while still thinking. The API and Codex/Work keep the September version; the chat-latest snapshot tracks the ChatGPT model. Source: https://openai.com/index/gpt-6-for-everyone/

## Notes

Most efficient GPT-6 model for focused, high-volume tasks; successor to GPT-5.6 Luna (the mini/nano tier). OpenRouter also lists openai/gpt-6-luna-pro.

High-volume classification, extraction, routing, sub-agents.

```bash
curl https://api.openai.com/v1/responses \
 -H "Authorization: Bearer $OPENAI_API_KEY" -H "Content-Type: application/json" \
 -d '{"model":"gpt-6-luna","input":"Hello"}'
```

Sources:
- https://developers.openai.com/api/docs/models/gpt-6-luna
- https://developers.openai.com/api/docs/pricing
- https://developers.openai.com/api/docs/changelog
- Models overview: https://developers.openai.com/api/docs/models

Model page: https://postcutoff.com/m/gpt-6-luna/