@heyshrutimishra: The best thing about Parallel's new API is that it admits when it's guessing. Ask it a yes or no question and it checks…

X AI KOLs Timeline Products

Summary

Parallel Web Systems launched its Decisions API, a web-grounded decision engine that returns confidence scores (e.g., 98% or 55%) for yes/no answers, letting apps auto-trust confident responses and route uncertain ones to humans at $0.001 per request.

The best thing about Parallel's new API is that it admits when it's guessing. Ask it a yes or no question and it checks the live web, then answers with a number for how sure it is, like 98% or 55%. Most AI would just give an answer and sound certain. That's what makes it usable at scale. An app can run it across thousands of companies or claims, trust the confident answers and send only the shaky ones to a person. #ParallelPartner
Original Article
View Cached Full Text

Cached at: 10/28/26, 05:37 AM

The best thing about Parallel’s new API is that it admits when it’s guessing.

Ask it a yes or no question and it checks the live web, then answers with a number for how sure it is, like 98% or 55%. Most AI would just give an answer and sound certain.

That’s what makes it usable at scale. An app can run it across thousands of companies or claims, trust the confident answers and send only the shaky ones to a person.

#ParallelPartner

Parallel Web Systems (@p0): Introducing the Parallel Decisions API: the first web-grounded decisions engine.

Decision models like Jev can answer in an instant, but they lack the recency of current news. Now you can get both in a single call.

Decisions API is live today at $0.001 per request.

Try it with

Similar Articles

Decisions API is now available in Public Beta (1 minute read)

TLDR AI

OpenAI 发布 Decisions API 公测版,宣称决策速度比 GPT-6 Luna 通过 Responses API 快最多 10 倍,支持文本与图像输入以及 predicates、choices、scores 三种输出,定价为每 100 万输入 token 0.10 美元且无缓存与输出 token 费用。

Decisions API is in public beta

Hacker News Top

OpenAI 的 Decisions API 进入公开测试版,可对文本、图像或两者进行评估并返回类型化答案,速度约为 Responses API 的 10 倍,目前仅支持 gpt-6-luna 模型,预计数周内正式发布。