Article
CommunityJev Integrations & Adapters
TypeSafe Jev in Netlify AI Gateway
Netlify's AI Gateway serves TypeSafe's Jev with zero configuration: install @typesafe-ai/sdk, keep no API keys, and let usage bill to Netlify credits, with the SDK defaulting to the jev-latest alias (jev-1.13.0).
- Format
- Article
- Reading time
- 2 min
- Published by
- Community
- Author
- Netlify
- Last verified
- Oct 2026
- Languages
- TypeScript
Highlights
- Install @typesafe-ai/sdk and call it from a Netlify Function; AI Gateway supplies credentials with no keys, provider config, or base URLs.
- Three question primitives: choice picks a declared option, score rates ordered levels, and noul returns a yes/no probability from 0 to 1.
- Every question in a request runs in parallel against the same state, so batching a dozen questions costs little more than asking one.
- State and questions share about 32,000 tokens, roughly 150,000 characters of English, at TypeSafe-reported 70-500 ms response times.
- The SDK defaults to the jev-latest alias, currently jev-1.13.0, and requires Node.js 20 or newer.
Watch out
A Netlify changelog entry, last updated 15 October 2026. Credentials are handled server-side, so the page shows no key handling, licence, per-call price, or rate limits beyond the shared token budget, and the latency and version details are TypeSafe's claims rather than independent measurements.
Questions about this entry
Short answers drawn from the linked project or page.
A zero-configuration integration: Jev is available through the gateway, and you install @typesafe-ai/sdk and call it directly in Netlify Functions without creating API keys, configuring a provider, or wiring up base URLs.
Install @typesafe-ai/sdk and deploy a Netlify Function. AI Gateway supplies credentials automatically, usage is billed to your Netlify credits like every other model in the gateway, and the SDK requires Node.js 20 or newer.
choice picks one option from a declared set, score rates against ordered levels, and noul returns a yes/no probability between 0 and 1. Answers are constrained to the options you declare, so no JSON parsing or schema coercion is needed.
Every question in a request is evaluated in parallel against the same state, so batching a dozen questions into one call costs little more than asking one. State and questions share a budget of roughly 32,000 tokens.
The SDK defaults to the jev-latest alias, currently jev-1.13.0. Each answer also carries a probability distribution and a confidence value, and TypeSafe reports end-to-end response times of 70 to 500 milliseconds.
Only that usage is billed to Netlify credits like every other gateway model. No per-call price, token rate limit, or licence is stated, and there is no accuracy data; the entry is Netlify's changelog rather than independent testing.
A Function routes an incoming contact form submission to sales, support, or spam: choice declares the three destinations, answers.team.choice returns one of them, and the response is safe to branch on directly.
More Jev resources like this
TanStack AI's TypeSafe adapter covers evaluate only and talks to TypeSafe over fetch, wiring jev-latest into decide() with choice, score, and boolean question helpers and a required TYPESAFE_API_KEY.
Jev Integrations & AdaptersDocs#community#tanstack#typescript
Community
Mastra's classifier primitive defines choice, score, and boolean questions against an evaluation model such as jev-latest, returning a probability for each criteria key so workflow branch logic can act on the answer.
Jev Integrations & AdaptersArticle#community#typescript#mastra
Community
An official Mastra template that checks pricing, changelog, and documentation pages against saved captures, has Jev classify each change with its evidence, and routes it to ignore, record, request review, or alert.
Jev Integrations & AdaptersDocs#community#typescript#mastra
Community
Open-source TypeScript agentic operating system: a core runtime, app for web and mobile, CLI, cloud services and first-party plugins. The directory's curated summary reports it integrates TypeSafe System One decision services for sub-100ms intent classification, action dispatching and confidence-gated tool execution.
Jev Integrations & Adapters#community#agents#framework
Community
elizaOS/elizaTypeScript
elizaOS/elizaTypeScriptOpen-source AI email assistant (Next.js, Postgres, 12k+ stars) with a decision-model layer that can run on openrouter:typesafe/jev-1.13: Jev-backed questions cover rule selection, cold-email detection, thread status, recurring patterns, unsubscribe pages, and sender categorization, each with evals.
Jev Integrations & Adapters#community#email#gmail
Community
elie222/inbox-zeroTypeScript
elie222/inbox-zeroTypeScriptThe Vercel AI SDK provider for OpenRouter, including openrouter.decisionModel for typesafe/jev-1.13 evaluations with providerMetadata answers.
Jev Integrations & Adapters#community#typescript#openrouter
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.