# TypeSafe has updated Jev - now the model can recognize images

> Full text available in Russian

**Published:** October 17, 2026
**Author:** GPT Time | Нейросети | ИИ
**Source:** Telegram — GPT Time | Нейросети | ИИ
**Language:** ru-RU
**HTML:** https://aiqazaqstan.com/en/articles/typesafe-obnovila-jev-teper-model-umeet-raspoznavat-izobrazheniya

⚙️ TypeSafe has updated Jev - now the model can recognize images. In version Jev 1.14, they added work with screenshots and pictures, and the context was increased fourfold - up to 262 thousand tokens. Jev differs from regular LLMs in that it does not write long answers, but returns...

> From the original source: **Telegram — GPT Time | Нейросети | ИИ**
> [Read full article at Telegram — GPT Time | Нейросети | ИИ](https://t.me/gpt_time24/4186)

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*