jina-embeddings-v4 · Jina AI
A general-purpose vector model with 3.8 billion parameters, used for multimodal and multilingual retrieval, supporting both unidirectional and multi-vector embedding outputs.
A general-purpose vector model with 3.8 billion parameters, used for multimodal and multilingual retrieval, supporting both unidirectional and multi-vector embedding outputs.
On AIHubMix, Jina Embeddings V4 costs $0.05 per million input tokens and $0.05 per million output tokens.
Jina Embeddings V4 accepts text and image input.
Jina Embeddings V4 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-embeddings-v4 — no other code changes needed.
Jina Embeddings V4 is developed by Jina AI. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
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…
Multimodal multilingual document reranker, 131K context, 0.6B parameters, for visual…
Multi-modal Embeddings Model, multilingual, 1024-dimensional, 865M parameters.
Use Jina Embeddings V4 via the AIHubMix unified API — one interface for every major LLM.