Jina AI launches jina-ocr-v1, a 570M-active-param visual document parser
JinaAI_ · x · 2026-09-18
Jina AI announced jina-ocr-v1, a new visual document parser with 3.4B total parameters and only 570M active parameters, with built-in speculative decoding. Throw PDFs, scans, tables, charts, or invoices at it and get clean markdown back.
It's available on Hugging Face today and via Jina Reader's x-respond-with parameter, targeting document understanding and RAG data-cleaning workflows.
Related event: Tencent WeVisDoc and Jina AI's jina-ocr-v1 Launch on the Same Day(6 posts)→
More from Models
- Community asks Moonshot when Kimi K3.1 model weights will drop — bgmshana · 2026-11-04
- Meta's Muse Spark Open license counts distilled models as derivatives — aidenclarke_12 · 2026-11-04
- Tencent Hy4 trails GPT-6.1 on hard tests as Kimi K3.1 Pro beats it on two benchmarks — heyshrutimishra · 2026-11-04
- Tencent's Hy4 agent self-trained a smaller model that beat Tencent's own baseline — heyshrutimishra · 2026-11-04
- Hy4 tops open models in finance eval at 3.04, hallucination rate cut to 5.45% — heyshrutimishra · 2026-11-04
- Tencent Hunyuan teases upcoming LMArena debut — TencentHunyuan · 2026-11-04