Models/Jina AI/Jina Embeddings v4

Jina Embeddings v4

Jina AI 📐 Embedding

Jina AI's latest multimodal embedding model, embeds text and images into a shared vector space with 32K context. State-of-the-art retrieval quality.

Specifications

ModalitiesInput: text, image  ·  Output: embedding
Context window32K tokens
Speed●●●●○ Fast
FeaturesTools: No Streaming: No

Pricing

$0.0875 / 1M input tokens

Platform credit pricing — live rates on the Models page.

Use Jina Embeddings v4 on Zubnet →

More from Jina AI

J
Jina Embeddings v3
Jina AI's 570M parameter multilingual text embedding model, MTEB benchmark champion, 8K context, 89 languages.
📐 Embedding
J
Jina CLIP v2
Jina AI's CLIP model, cross-modal text-image embeddings supporting 89 languages with Matryoshka representations. 865M params.
📐 Embedding
J
Jina ColBERT v2
Jina AI's ColBERT late-interaction model, multi-vector embeddings for fine-grained retrieval, 89 languages, user-controlled embedding sizes.
📐 Embedding
J
Jina Code Embeddings 1.5B
Jina AI's code-specialized embedding model, 1.5B parameters optimized for code search and retrieval. 32K context.
📐 Embedding