Jina Embeddings v4
Paid production API
Type / status: embedding / documented_api
Use cases: RAG, Semantic search, Multimodal retrieval
Embedding dimensions (not output tokens): 2048
Supported languages: multilingual
Deployment options: api, huggingface, airgapped
Documented datacenters: US
Model release date: 2025-06-24
API endpoint: https://api.jina.ai/v1/embeddings
Open-weights license (hosted API terms are separate): Qwen Research License
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official model ID: jina-ai/jina-embeddings-v4
Input / output: text, image, pdf → embedding
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
- Input: USD 0.05 / 1,000,000 tokens
Jina Embeddings V4 is a 3.8 billion parameter multimodal embedding model that provides unified text and image representation capabilities. Built on the Qwen2.5-VL-3B-Instruct backbone, the model features an architecture that supports both single-vector and multi-vector embeddings in the late interaction style, addressing limitations found in traditional CLIP-style dual-encoder models. The model incorporates three specialized task-specific LoRA adapters (60M parameters each) that optimize performance across different retrieval scenarios including asymmetric query-document retrieval, semantic text similarity, and code search without modifying the frozen backbone weights. The model demonstrates strong performance in processing visually rich content such as tables, charts, diagrams, screenshots, and mixed-media formats through a unified processing pathway that reduces the modality gap present in conventional architectures. Supporting multilingual capabilities, the model can handle input texts up to 32,768 tokens with images resized to 20 megapixels, making it suitable for various document retrieval and cross-modal search applications across different languages and domains. Endpoint and model identifier are declared in the current OpenAPI schema; authenticated inference was not executed. Endpoint support is documented; authenticated inference was not tested. Embedding dimensions are vector size, not generated tokens.
Documented API context: 32,768 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00