Embed v4.0
Our state-of-the-art embedding model designed for precise retrieval across noisy, multilingual, and multimodal data. Multimodal (text, images, PDFs). Multilingual across 100+ languages.
Input
Output
Context
8K
Max Output
128K
Parameters
—
Technical Specifications
Model TypeEmbedding
Context Window8K
Max Output Tokens128K
Parameters—
Training Cutoff—
Licenseproprietary
Capabilities
Input Modalities
text
Output Modalities
embedding
Features
embeddings
Resources & Links
proprietary — Proprietary - API access only
Related Tools
Data sourced from official provider APIs and documentation
Last updated: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.