llm-openai-decisions 0.1a0
- ID
- 32586
- Status
- summarized
- Published
- 07 Oct 2026, 7:04 AM
- Fetched
- 07 Oct 2026, 9:07 AM
- Provider
- Simon Willison
- Category
- developer-ai
- Original URL
- https://simonwillison.net/2026/Oct/6/llm-openai-decisions/
- Source URL
- https://simonwillison.net/atom/everything/
Summary
- Score
- 6.0
- Created
- 07 Oct 2026, 9:08 AM
- Tags
- Audience
- developersai_ml_learnersai_agent_users
What happened
Simon Willison published llm-openai-decisions 0.1a0, an LLM CLI plugin for OpenAI's newly released Decisions API, which he describes as Jev-style and previously announced at DevDay. The gpt-6-luna decision model accepts image input as well as text, and both it and Jev bill only for input: OpenAI at 10 cents per million input tokens versus Jev's 4.2 cents, with identical support for the three question types (yes/no, choices, scores). The plugin was built by having GPT-6 Astra read the new OpenAI API docs, and installs with `llm install llm-openai-decisions`, returning outputs like {"type": "predicate", "name": "evaluation", "probability": 0.0}.
Why it matters
If you use an LLM for classification or scoring, input-only billing changes the cost math: output tokens (labels, JSON, verbose reasoning fields) are free, so the only price lever to compare is the input rate — 10c vs Jev's 4.2c per million input tokens is roughly 2.4x. Anyone already using the llm CLI can add predicate-style questions against images or text with one install rather than new API glue; there is nothing Malaysia- or SEA-specific in this text, so treat it as a general tooling and pricing data point.
Discussion angle
Compare a dedicated decisions/predicate API against prompting a chat model for classification: with input-only billing, is the deciding factor output-format convenience and the 10c vs 4.2c input rate, or does the narrow API shape (yes/no, choices, scores) actually constrain what you can build?