jina-clip-v1
Shares a vector space between English text and images for multimodal retrieval baselines.
Compare models 0 / 3
Select two or three models to compare their published specifications.
- Released
- 2024-06-05
- Parameters
- 223M
- Context length
- 8K tokens
- Output dimensions
- 768
- Inputs
- image · text
- Languages
- en
- Outputs
- vector
- Availability
- api · huggingface · aws · azure · airgapped
Choose a representation
The catalog lists 768 output dimensions. Supported dimensions and input types depend on the model; check the request schema before switching a production index.
Model weights and hosted API access
The license shown above applies to the published model assets. Calling a hosted API and downloading weights for commercial self-hosting are separate arrangements.
The catalog marks these model assets as Apache-2.0. Check the official repository for the license, notices, and any third-party dependencies before redistribution.
Read the official licenseExplore newer models
Catalog checked on September 7, 2026. This is an independently prepared Chatsax guide to Jina models.