OpenAI launches Decisions API that reduces complex evaluations to yes, no, or pick one
Quick Answer
OpenAI has launched the Decisions API, which evaluates text and images ten times faster than the Responses API, currently in public beta at $0.10 per million input tokens.
Quick Take
It supports yes/no probabilities, category picks, and scale ratings, with applications in damage detection and document classification, while also ensuring HIPAA compliance.
Key Points
- Decisions API runs ten times faster than the Responses API.
- Supports yes/no probabilities, category selections, and scale ratings.
- Currently in public beta, with general availability coming soon.
- Costs $0.10 per million input tokens; output tokens are free.
- OpenAI reduced its paid API tiers from five to three.
📖 Reader Mode
~1 min readOpenAI announced two updates to its API platform. The new Decisions API evaluates text, images, or both, running about ten times faster than the Responses API. It's in public beta now, with general availability coming soon. Only gpt-6-luna is supported so far, at $0.10 per million input tokens. Output tokens are free.
The API handles three response types: yes/no probabilities, picks from predefined categories, and scale-based ratings. Use cases include damage detection in photos, automatic customer inquiry routing, and document classification, OpenIA says. It supports zero-data retention and HIPAA-compliant use in the US and Europe. The Decisions API is likely OpenAI's response to the mini-trend of "decision models" that Jev kicked off in mid-September.
OpenAI also cut its paid API tiers from five down to three: Build, Launch, and Grow. Organizations move up automatically when their total credit purchases hit the next threshold. Monthly usage limits sit at $500, $5,000, and $200,000.
— Originally published at the-decoder.com
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from The Decoder
See more →
An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to run
Epoch AI's MirrorCode benchmark reveals Claude Opus 4.7 as the leader with a 56% solve rate, reconstructing a 16,000-line toolkit in 14 hours. Despite this, all models tested struggle with the most complex tasks, highlighting limitations in current AI capabilities. The single task consumed $2,600 over 19 days, raising questions about cost-effectiveness in AI development.
