Model · multimodal model
jina-ocr-v1
jina-ocr-v1 is a multimodal model from Jina AI, first covered on 18 September 2026. It is available as open weights you can download and run (licence: CC BY-NC 4.0). Its context window is 32,768 tokens.
Last updated
At a glance
- Made by
- Jina AI
- Type
- Multimodal model
- Availability
- Open weights
- Licence
- CC BY-NC 4.0
- Context window
- 32,768 tokens
- First seen
- 18 September 2026
- Official page
- api.jina.ai/v1/chat/completions ↗
Taken from the coverage, not from our own testing; "not stated" means none of the reports we read gave it. All tracked models →
1 story about jina-ocr-v1
-
Jina AI releases jina-ocr-v1 3.4B MoE document parser for low‑budget GPUs
Jina AI, part of Elastic, announced the open‑weight release of jina-ocr-v1, a visual document parser that converts PDFs, scans, tables, charts or invoices into clean Markdown in a single pass. The model contains 3.4 B…
1 sourceMarkTechPost
