How to Get a Jev API Key (4 Ways, Tested)

Last checked Sep 19, 2026 · Independent guide, not affiliated with TypeSafe AI

ANSWER

You can get a key from TypeSafe's own console (early access, so your account may have to wait for approval), or use a key from Vercel AI Gateway, OpenRouter or Cloudflare Workers AI, which all list Jev. Vercel requires a card on file before Jev works, and OpenRouter needs prepaid credits.

Jev launched as early access. TypeSafe’s launch post says it is letting developers in from the waitlist as fast as it can, so a brand-new TypeSafe account may not be able to create keys right away. Three platforms that resell model access listed Jev within four days of launch, and their keys work with no TypeSafe approval.

The four routes at a glance

Route	Where the key comes from	Model name	What it takes to start	Catch
TypeSafe (official)	TypeSafe console, API keys page	`jev-1.13.0` / `jev-latest`	An approved TypeSafe account	Early access; approval is not instant for everyone
Vercel AI Gateway	Vercel dashboard, AI Gateway	`typesafe-ai/jev`	A Vercel account with a card on file	Without a card, calls fail with `customer_verification_required`; free tier is heavily rate-limited
OpenRouter	openrouter.ai, Keys	`typesafe/jev-1.13`	An OpenRouter account with credits	No free tier for Jev; empty balance returns HTTP 402
Cloudflare Workers AI	Cloudflare dashboard, API token with Workers AI access	`typesafe/jev`	A Cloudflare account	Listed on Sep 19, 2026; we have not tested it yet, and pricing is only shown in the dashboard

If you just want to try Jev today, OpenRouter is the fastest route: add a few dollars of credit and you can call it immediately. If you plan to build on Jev, get on TypeSafe’s list as well, since the official API has the largest context window (64k tokens versus 32,000 on OpenRouter and Cloudflare) and the official SDKs.

Route 1: TypeSafe’s own console

Sign in at console.typesafe.ai. The sign-in page is open to everyone.
If your account has not been let in yet, you will be on the waitlist. TypeSafe has not published how long approval takes.
Once approved, open the API keys page in the console settings and create a key. TypeSafe’s quick start also points to a browser Playground in the console, where you can paste a state and try questions without code.
Export it so the SDKs can find it:

export TYPESAFE_API_KEY="paste-your-key-here"

Make a first call with curl or an SDK; Your first Jev call has copy-paste versions.

Official pricing is $0.042 per million input tokens with free output. See Jev pricing.

Route 2: Vercel AI Gateway

In the Vercel dashboard, open AI Gateway and create an API key.
Add a payment card to the team. This is the step people miss: until a card is on file, requests to Jev fail with a customer_verification_required error, even though Jev is covered by the free tier. See customer_verification_required.
Call Jev with the AI SDK (version 7 or later) using experimental_evaluate and the model name typesafe-ai/jev. Vercel does not offer Jev through an OpenAI-compatible endpoint.

Vercel gives every team $5 of AI Gateway credit per month on the free tier, with lower per-model rate limits. In our testing the free tier let a handful of Jev questions through and then throttled for a while; 131 questions took about an hour and a half. Buying credits moves the team to the paid tier, which lifts the limits, but Vercel’s docs note that the monthly free credit then stops.

On September 19, 2026, Vercel’s Jev page listed input and output as free, with a note that the promotional pricing ends on September 25, 2026. Full walkthrough: Jev on Vercel AI Gateway.

Route 3: OpenRouter

Create an OpenRouter account and an API key.
Add credits. OpenRouter lists Jev at $0.042 per million input tokens and $0 for output, the same rates as TypeSafe. With no balance you get HTTP 402, “Insufficient credits”.
Send requests to OpenRouter’s Decisions endpoint, POST https://openrouter.ai/api/alpha/decisions, with the model typesafe/jev-1.13. The regular chat completions endpoint does not serve Jev, and Jev does not appear in the /api/v1/models list because that list covers text-output models.

Details and a working request: Jev on OpenRouter.

Route 4: Cloudflare Workers AI

Cloudflare added Jev to its model catalog as typesafe/jev, labeled third-party, with a 32,000-token context window. You call it from a Worker with env.AI.run('typesafe/jev', {...}) or through the Workers AI REST API with a Cloudflare API token. Pricing is shown only inside the Cloudflare dashboard. We have not run it yet; see Jev on Cloudflare Workers AI for what the documentation says.

Keep the key out of the browser

A Jev key is billed per token. Call Jev from your server, a serverless function or a Worker, not from front-end code. The official JavaScript SDK refuses to run in a browser unless you set an option named dangerouslyAllowBrowser, which exists for a reason. Never commit the key to a repository; load it from an environment variable.

Troubleshooting a new key

You see	It means	Page
HTTP 401, “Cannot authenticate with the server”	The key is wrong or revoked	401
HTTP 403, “Must supply an API key!”	The request had no `Authorization` header	403
`customer_verification_required`	Vercel team has no card on file	Vercel error
HTTP 402, “Insufficient credits”	OpenRouter balance is empty	402
HTTP 400, “Unknown model”	Wrong model name for that route	400