Jev Channels Compared: TypeSafe, Vercel, OpenRouter, Cloudflare
Last checked · Independent guide, not affiliated with TypeSafe AI
Jev is available on TypeSafe's own API and, as of September 25, 2026, through Vercel AI Gateway, OpenRouter and Cloudflare. They serve the same Jev 1.13 model, and Vercel and OpenRouter now charge TypeSafe's price of $0.042 per million input tokens. They still differ in model name, request format, context window and what you need before the first call.
Within four days of launch, Jev could be called in four places. They all run Jev 1.13. Since September 21, 2026, Vercel and OpenRouter also accept TypeSafe’s own request format, so the official SDKs can switch between them by changing the base URL and key. Each channel still has its own model name, native request shape and limits.
Side-by-side
Section titled “Side-by-side”| Feature | TypeSafe API | Vercel AI Gateway | OpenRouter | Cloudflare Workers AI |
|---|---|---|---|---|
| Model name | jev-1.13.0, jev-latest, jev-preview |
typesafe-ai/jev |
typesafe/jev-1.13 |
typesafe/jev |
| Model name (alias) | — | — | ~typesafe/jev-latest |
— |
| How you call it | POST https://api.typesafe.ai/v1/systemone or the official SDKs |
AI SDK 7+ experimental_evaluate, or TypeSafe format at https://ai-gateway.vercel.sh/typesafe |
POST https://openrouter.ai/api/alpha/decisions, or TypeSafe format at https://openrouter.ai/api/v1/systemone |
env.AI.run() in a Worker, or the REST API |
| Yes/no question type | noul, answer field noul |
boolean, answer field probability |
noul |
noul |
| Context window | 64k per request; 32k for state + longest question | 32,000 tokens | 32,000 tokens | 32,000 tokens |
| Price (input / output) | $0.042 per 1M / free | $0.042 per 1M / $0 (launch promotion ended Sep 25, 2026) | $0.042 per 1M / $0 | In the Cloudflare dashboard, paid from AI Gateway credits |
| Before your first call | An existing account (new signups paused since Sep 22, 2026) | Card on file for the Vercel team | Prepaid credits | Cloudflare account, AI Gateway credits and an API token with Workers AI Read |
| Listed since | Sep 15, 2026 | Sep 15, 2026 | Sep 18, 2026 | Sep 19, 2026 |
| Tested by us | Yes, Sep 19 and Sep 25 | Yes, Sep 18 | Endpoint checked, no paid call | Not yet |
Which one should you use?
Section titled “Which one should you use?”- To try Jev in the next ten minutes: OpenRouter. Top up a few dollars and send a request; the official request format is almost identical.
- To build something you will keep: the TypeSafe API. It has the biggest context window, model version pinning and TypeSafe’s status page. New signups are paused for now, so you can start on OpenRouter or Vercel with the official SDK and move over later by changing the base URL.
- If your app already runs on Vercel and the AI SDK: Vercel AI Gateway, as long as you add a card. Jev is no longer free there, and the free tier’s rate limits are tight.
- If you run on Cloudflare Workers: the
env.AIbinding keeps the call inside Cloudflare’s network. You pay from prepaid AI Gateway credits; check the price in your dashboard first.
The differences that break code
Section titled “The differences that break code”1. The yes/no type has two names. Vercel’s AI SDK calls it boolean and returns probability. TypeSafe’s API calls it noul and returns noul. Sending "type": "boolean" to TypeSafe’s endpoint returns HTTP 400 “Invalid request.” See 400 Invalid request.
2. Context is halved on two channels. OpenRouter and Cloudflare both list a 32,000-token context window. TypeSafe documents 64k per request, with the same 32k cap on the state plus the longest question. In our tests, TypeSafe rejected a state of about 33,600 tokens with max_tokens_exceeded, so in practice the usable state size is similar everywhere.
3. Model names are not portable. jev-1.13 (without the patch number) is rejected by TypeSafe with “Unknown model”, while typesafe/jev-1.13 is the correct name on OpenRouter. OpenRouter’s API reference shows responses reporting a dated version, such as typesafe/jev-1.13-20260917.
4. Errors look different. TypeSafe returns {"detail": ...}; OpenRouter returns {"error": {"code": ..., "message": ...}}; Vercel’s SDK throws gateway errors. The errors index lists each one with its channel.
Each channel in detail
Section titled “Each channel in detail”- Jev API (TypeSafe): request format, responses, errors
- Jev on OpenRouter
- Jev on Vercel AI Gateway
- Jev on Cloudflare Workers AI
- How to get a Jev API key: the sign-up side of each route