Models/Jina AI/Jina VLM

Jina VLM

Jina AI 🧠 Language Model

Jina AI's 2.4B vision-language model — state-of-the-art multilingual visual QA among 2B-scale VLMs. Processes images up to 4K resolution across 29 languages.

Specifications

Context Window32,768 tokens
Speed●●●●● Fast
ModalitiesInput: text, image  ·  Output: text
FeaturesVision: Yes Tools: No Streaming: Yes

Pricing

Included with plan

Use Jina VLM on Zubnet →

More from Jina AI

R
ReaderLM v2
Jina AI's HTML-to-clean-text model — converts messy web pages to clean markdown or structured data. 512K context for processing entire web pages.
🧠 Language Model
J
Jina Embeddings v4
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.
📐 Embedding
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