← All models
TypeSafe: Jev Router
typesafe/jev-routertextVisionFilesVideoAudio
Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on [Jev](https://openrouter.ai/~typesafe/jev-latest), TypeSafe's first System One model, and adapts as your conversation evolves. One endpoint gives you the whole model ecosystem, leveraging the ecosystem's token and spend share.
Context
1M
Released
Sep 25, 2026
Parameters
messagesrequiredmax_tokensoptional · alias max_completion_tokensstreamtrue · falsestream_options{"include_usage": true}pluginsjev-router · models / allowed_models / excluded_models / cost_tierreasoning_efforthint: the router may override · low · medium · highimage_urlimage (data: URL)filePDF · DOCX · TXT · CSV · XLSX · PPTX (data: URL)Top models used by the router
Where the router sends requests (share of tokens, live statistics)
- 1.
DeepSeek V4.1 Flash33.4B · 27.6% - 2.GPT-6.1 Sol20.0B · 16.5%
- 3.
GLM 5.39.7B · 8% - 4.GPT-6 Luna9.4B · 7.8%
- 5.GLM 5.3 Flash8.6B · 7.1%
- 6.Others39.9B · 33%
How to use via API
from openai import OpenAI
client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")
resp = client.chat.completions.create(
model="typesafe/jev-router",
messages=[{"role": "user", "content": "Привет"}],
max_tokens=1024,
stream=False,
)
print(resp.choices[0].message.content)
# Стриминг: stream=True — ответ приходит чанками
for chunk in client.chat.completions.create(
model="typesafe/jev-router",
messages=[{"role": "user", "content": "Привет"}],
stream=True,
):
print(chunk.choices[0].delta.content or "", end="", flush=True)
# свой пул моделей роутера: Jev выбирает только из них
pooled = client.chat.completions.create(
model="typesafe/jev-router",
messages=[{"role": "user", "content": "Привет"}],
extra_body={"plugins": [{"id": "jev-router",
"models": ["anthropic/*", "openai/gpt-6*"]}]},
)
# reasoning_effort — ПОДСКАЗКА: роутер выбирает уровень сам и может переопределить
hinted = client.chat.completions.create(
model="typesafe/jev-router",
messages=[{"role": "user", "content": "Привет"}],
reasoning_effort="high",
)
# с файлом (PDF · DOCX · TXT · CSV · XLSX · PPTX)
doc = client.chat.completions.create(
model="typesafe/jev-router",
messages=[{"role": "user", "content": [
{"type": "text", "text": "Кратко перескажи документ"},
{"type": "file", "file": {
"filename": "doc.pdf",
"file_data": "data:application/pdf;base64,JVBERi0...",
}},
]}],
)
