{"slug": "llm-openai-decisions-0-1a0", "title": "llm-openai-decisions 0.1a0", "summary": "Simon Willison released llm-openai-decisions 0.1a0, an LLM plugin for OpenAI's new Decisions API, which OpenAI announced at last week's DevDay. The plugin, built by GPT-6 Astra reading the OpenAI API documentation and inspired by Willison's llm-typesafe plugin for Jev, supports the same three question types as Jev (yes/no, choices, scores) and adds image input via the gpt-6-luna decision model. OpenAI charges 10 cents per million input tokens and nothing for output, versus Jev's 4.2 cents per million input tokens.", "body_md": "**Release:** [llm-openai-decisions 0.1a0](https://github.com/simonw/llm-openai-decisions/releases/tag/0.1a0)\n\nOpenAI released their new Jev-style [Decisions API](https://developers.openai.com/api/docs/guides/decisions), as previously announced at last week's DevDay.\n\nSince I already have an [llm-typesafe](https://github.com/simonw/llm-typesafe) plugin for talking to Jev, I had GPT-6 Astra read the new OpenAI API documentation and build an `llm-openai-decisions` plugin inspired by `llm-typesafe`.\n\nUnlike Jev, the new `gpt-6-luna` decision model supports image input in addition to text. Both models charge for input it and not for output: OpenAI's is 10 cents per million input tokens, Jev's is 4.2 cents per million.\n\nOtherwise the API shape is *very* similar to Jev, at least conceptually. Jev [supports three question types](https://simonwillison.net/2026/Sep/21/jev/#three-types) for yes/no, choices, or scores. OpenAI Decisions supports the same three types.\n\nInstall the plugin like this:\n\n```\nllm install llm-openai-decisions\n```\n\nHere's an example query against an image attachment:\n\n```\nllm -m openai-decisions/gpt-6-luna \\\n  -a https://static.simonwillison.net/static/2025/two-pelicans.jpg \\\n  -s 'Does this image contain any mammals?'\n```\n\nAnd example output:\n\n```\n{\"type\": \"predicate\", \"name\": \"evaluation\", \"probability\": 0.0}\n```\n\nConsult [the README](https://github.com/simonw/llm-openai-decisions/blob/main/README.md) for full details of how to run the other types of questions.\n\nTags: [openai](https://simonwillison.net/tags/openai), [llm](https://simonwillison.net/tags/llm), [coding-agents](https://simonwillison.net/tags/coding-agents), [jev](https://simonwillison.net/tags/jev)", "url": "https://wpnews.pro/news/llm-openai-decisions-0-1a0", "canonical_source": "https://simonwillison.net/2026/Oct/6/llm-openai-decisions/", "published_at": "2026-10-06 23:04:13+00:00", "updated_at": "2026-10-07 05:18:49.181915+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools", "large-language-models", "ai-products"], "entities": ["Simon Willison", "OpenAI", "llm-openai-decisions", "Decisions API", "GPT-6 Astra", "gpt-6-luna", "Jev", "llm-typesafe"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/llm-openai-decisions-0-1a0", "markdown": "https://wpnews.pro/news/llm-openai-decisions-0-1a0.md", "text": "https://wpnews.pro/news/llm-openai-decisions-0-1a0.txt", "jsonld": "https://wpnews.pro/news/llm-openai-decisions-0-1a0.jsonld"}}