jina-ocr-v1 · Jina AI
jina-ocr-v1 is Jina AI's latest page-to-Markdown document parsing model, with 570 million active parameters. Its architecture inherits the DeepEncoder from DeepSeek-OCR; jina-ocr-v1 retains that encoder and decoder, and thus supports document parsing for approximately 100 languages.(This model is free for a limited time.)
jina-ocr-v1 is Jina AI's latest page-to-Markdown document parsing model, with 570 million active parameters. Its architecture inherits the DeepEncoder from DeepSeek-OCR; jina-ocr-v1 retains that encoder and decoder, and thus supports document parsing for approximately 100 languages.(This model is free for a limited time.)
Jina Ocr V1 has a 32,000 token context window.
Jina Ocr V1 accepts image input.
Jina Ocr V1 is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to jina-ocr-v1 — no other code changes needed.
Jina Ocr V1 is developed by Jina AI. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
Jina Ocr V1 was released on September 14, 2026 by Jina AI.
jina-reranker-v3.5 is a 0.6B-parameter multilingual listwise document reranker and a…
A 3.8-billion-parameter general vector model (embedding model) for state-of-the-art…
A 3.8-billion-parameter general vector (embedding) model providing state-of-the-art…
DeepSearch combines search, reading, and reasoning capabilities to pursue the best…
A general-purpose vector model with 3.8 billion parameters, used for multimodal and…
Multimodal multilingual document reranker, 131K context, 0.6B parameters, for visual…
Use Jina Ocr V1 via the AIHubMix unified API — one interface for every major LLM.