← Embeddings
Jina AI
jina-embeddings-v4
Open-weight multimodal embeddings. Sample entry.
Capabilities, explained
What this API can do, and what each capability means for your project.
Dimensions
2,048
Vector length. Larger can be more accurate but costs more to store and search.
Max input
32K tokens
Longest text that can be embedded in one call.
Multilingual
Yes
Works well across many languages, including cross-language search.
Image + text
Yes
Can embed images and text into the same space (search images with words).
Open weights
Yes
The model weights are downloadable, so you can self-host it or switch hosting providers without changing models.
Price history
Only one price recorded so far. The chart appears once the price changes.