Skip to content
All tool news

Tool desk · Updated daily

Tool news·Vercel·

Vercel Adds OpenAI Decisions API to AI Gateway.

Vercel now routes the OpenAI Decisions API through AI Gateway, returning structured answers for classification, routing, triage and scoring.

CW

Create With tool desk

3 sources checked · 2 min read · 2 sections

ShareLinkedIn
Vercel Adds OpenAI Decisions API to AI Gateway

The OpenAI Decisions API is now available through Vercel’s AI Gateway at /v1/decisions, according to the Vercel changelog. It uses OpenAI’s request and response format, so existing OpenAI SDK integrations can move across without adopting a different API structure.

Builders need to change three parts of an existing integration: the base URL, credentials and model ID. The endpoint can then handle classification, routing, triage and rubric-based scoring through the same SDK setup.

How the OpenAI Decisions API structures answers

Decision models answer typed questions about shared input. Instead of returning generated text, they return structured answers that an application can pass into the next step of a workflow.

Question typeWhat the model returnsExample task
predicateThe probability that a condition is trueCheck whether a support request needs escalation
choiceA selection from supplied optionsRoute a request to a named queue
scoreA rating against an ordered rubricGrade an application against set criteria

A single request can contain shared input and ask the model one or more of these question types. The structured output can then drive application logic without extracting a decision from a block of generated prose.

The endpoint works with any decision model available through AI Gateway. The models named in the release are Jev, Liquid d1, Laya and OpenAI’s GPT-6 Luna Decisions. That lets an integration keep the same endpoint while changing the selected decision model.

JavaScript projects can call decisions.create with OpenAI SDK version 7.30.0 or later. Python projects need OpenAI SDK version 3.26.0 or later. Existing integrations retain the OpenAI SDK method while pointing requests at AI Gateway.

This release follows Vercel’s addition of confidence-based decision fallbacks to AI Gateway, which can route a request to another model when a decision falls below a configured confidence threshold.

The API is available now through the /v1/decisions endpoint for supported decision models on AI Gateway.

Frequently asked questions

What is the OpenAI Decisions API on Vercel?

It is an AI Gateway endpoint for asking decision models typed questions about shared input. Models return structured predicate, choice or score answers rather than generated text.

How do I move an existing OpenAI SDK integration to Vercel AI Gateway?

Change the base URL, credentials and model ID in the existing integration. Use OpenAI SDK 7.30.0 or later for JavaScript, or 3.26.0 or later for Python, to call decisions.create.

Which Vercel plan includes the OpenAI Decisions API?

The changelog does not state pricing or plan requirements. It confirms that the endpoint is available through AI Gateway at /v1/decisions.

Sources

3 checked

How we cover tool news: Create With's tool desk drafts these reports with AI from the sources listed above and checks them against those sources before publishing.

Worth passing on?

ShareLinkedIn

Go deeper on Vercel

Related reading, watching and going.

Everything on Vercel →

The briefing

19 May 2026

How to Migrate Your App from Lovable to Claude Code in 2025

Step-by-step guide to migrating your Lovable app to Claude Code. Learn how to move from Lovable's managed platform to a stack you own and control.

Read →

The briefing

10 Feb 2026

OpenClaw Review: 2 Weeks With This AI Agent

Honest 2-week review of OpenClaw — an autonomous AI agent powered by Claude. We test setup, safety, autonomy, and real value to see if it's worth using.

Read →
34 min

Podcast

My Daughter Built a Website Business, Claude Design First Look & Going All-In on Cloudflare

James and Kieran discuss practical AI-powered development through real-world examples, including a seven-year-old building a website business with Claude Code voice mode, Anthropic's new Claude Design tool, API security challenges in the AI agent era, and Cloudflare's expanding AI infrastructure offerings. The episode covers hands-on experiences with vibe coding, emerging design tools, and the evolving landscape of AI-assisted development.

Watch now ↗

Podcast

53. Why Your Vibe Code Needs Tests, Ditching SaaS & AI Agents That Work While You Sleep

James and Kieran discuss the practical realities of building AI-powered software, emphasizing the importance of testing in vibe-coded applications, exploring alternatives to traditional SaaS tools, and implementing autonomous AI agents for business operations. The episode covers technical topics like Convex databases, app store bottlenecks from AI-generated submissions, and using OpenClaw as a marketing automation agent.

Watch now ↗
38 min

Podcast

52. Your AI Co-Founder: OpenClaw, Manus & the Zero-Person Business

In this Create With podcast episode, James and Kieran are joined by Matt Roberts from Happy Operators for an in-depth discussion on using autonomous AI agents in production. The conversation covers practical experiences with OpenClaw, security considerations, comparison with emerging tools like Manus, and the broader shift toward AI-assisted development. They also discuss the VibeCoding Olympics results, Bubble's new AI capabilities, and research on Claude.MD file effectiveness.

Watch now ↗

Latest tool news

What else changed this week.

All tool news

The Create With Briefing

Don't watch forty changelogs. Read one email.

Every Tuesday: the tool changes worth knowing, real business use cases, and what's on near you. Free, unsubscribe any time.