Search results for 168
168 community
One keyword maps to one global community path.
People
Not Found
Tweets including 168
Jev is quickly beocming the primary choice for classification requests on OpenRouter.
It took 27% of weekly request volume in this category, nearly 2x the share of DeepSeek V4 Flash which previously held the top spot
Show more
RT @koblovinamerica: we took jev and build a model router! hope you enjoy.
Jev Router keeps a model that works for the rest of the session.
It can raise or lower effort without switching models. It switches only when the expected gain is larger than the cost, including the cached chat it would lose.
Show more
Jev reads the conversation text only to pick the model and effort.
It runs under zero data retention (ZDR) terms, so nothing is stored or trained on. Attachments are never sent to Jev, and requests with "zdr: true" work with Jev Router.
Show more
Jev Router runs on Jev, TypeSafe's first Decision / System One model.
Before each turn, Jev reads your prompt and scores it on difficulty and precision. Also checks whether a bigger model or more effort would help, whether a cheaper model is enough, and whether the task changed.
Show more
Most routers pick a model based on each message. Each switch loses the cached chat, so you pay full price for the new model to reread the whole conversation.
Most routers also route on the task type, not the difficulty. Easy and hard coding tasks get the same model.
Show more
On five agent benchmarks, Jev Router had a faster median time to first token than every other router we tested.
3/ Under the hood, Kev is a LoRA adapter and pointer head on Qwen3.5-4B-Base. The weights are on Hugging Face at
Thank you @SiliconFlowAI for hosting
Great insights from @jpatel41 in the @ft on how we're redefining security in the AI era. Proud to see our team leading the way!
