Jev Router

Typesafetypesafe/jev-router
Inputi—per 1M tokens
Outputi—per 1M tokens
Contexti1M1,000,000 tokens
ReleasedSep 25, 2026

About this model

Jev Router is an AI model from Typesafe, made available through the API on September 25, 2026. It can read up to 1,000,000 tokens in one request, roughly 1,875 pages of text, which covers most documents and conversations. Besides text, it accepts audio, files such as PDFs, images and video as input.

Quality scores

Rankings →

Not rated yet. Independent test results usually appear a few weeks after a model is released.

Benchmark data: Epoch AI, licensed CC BY 4.0

Where to use it

No provider data yet.

Use it in your code

Call Jev Router through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "typesafe/jev-router", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'

The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.

What it costs in practice

  • 1,000 chat replies
    ≈ 500 tokens in, 300 out each
    —
  • Summarise a 100-page document
    ≈ 50,000 tokens in, 1,000 out
    —
  • An app with 10,000 requests a day for a month
    ≈ 1,000 tokens in, 400 out each
    —

Cost calculator →

Frequently asked questions

What is the context window of Jev Router?
Jev Router can read up to 1,000,000 tokens in one request, about 1,875 pages of text.
Is Jev Router open source?
No. Jev Router is a closed model: its weights are not published, so you use it through Typesafe’s own apps and API, or through cloud providers.
Who makes Jev Router?
Jev Router is made by Typesafe. It became available through the API on September 25, 2026.
Can Jev Router read images?
Yes. Besides text, it accepts audio, files such as PDFs, images and video as input.