Jina AI: Jina Clip v2

Jina CLIP v2 revolutionizes multimodal AI by bridging the gap between visual and textual understanding across 89 languages. This model solves critical challenges in global e-commerce, content managem…

jina/jina-clip-v2

Jina CLIP v2 revolutionizes multimodal AI by bridging the gap between visual and textual understanding across 89 languages. This model solves critical challenges in global e-commerce, content management, and cross-cultural communication by enabling accurate image-text matching regardless of language barriers. For businesses expanding internationally or managing multilingual content, it eliminates the need for separate models per language or complex translation pipelines. The model particularly shines in scenarios requiring precise visual search across language boundaries, such as global marketplace product discovery or multilingual digital asset management.

Specifications & capabilities

Input
text, image
Output
embeddings
Context window · tokens
8192
Embedding dimensions
1024
Published model ID
jina-clip-v2
Capabilities
embeddings, multimodal, visionInput

Evaluations

1–2 / 2

MTEB

26.94%

source id
mteb
leaderboard name
MTEB Retrieval
dimension
embedding
metric
Average task score
rank
756
sample size
13
aggregation scope
splits
  • test
subsets
  • default
  • english
  • french
  • german
  • spanish
task_count
4
task_names
  • Vidore2BioMedicalLecturesRetrieval
  • Vidore2ESGReportsHLRetrieval
  • Vidore2ESGReportsRetrieval
  • Vidore2EconomicsReportsRetrieval
sample_size
13
subset_count
5
subset_sample
  • default
  • english
  • french
  • german
  • spanish
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 344d954da76eb8ad47a7aaff42d012e30c15b8fe
source model id
jinaai/jina-clip-v2
Original result ↗

MTEB

26.94%

source id
mteb
leaderboard name
MTEB Overall
dimension
embedding
metric
Average task score
rank
912
sample size
13
aggregation scope
splits
  • test
subsets
  • default
  • english
  • french
  • german
  • spanish
task_count
4
task_names
  • Vidore2BioMedicalLecturesRetrieval
  • Vidore2ESGReportsHLRetrieval
  • Vidore2ESGReportsRetrieval
  • Vidore2EconomicsReportsRetrieval
sample_size
13
subset_count
5
subset_sample
  • default
  • english
  • french
  • german
  • spanish
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 344d954da76eb8ad47a7aaff42d012e30c15b8fe
source model id
jinaai/jina-clip-v2
Original result ↗

Published prices

1–1 / 1

jina-ai/jina-clip-v2 ↗

$0.05

Inference provider
jina
Platform
Jina AI
Unit
input_tokens_per_million
Currency
USD
Billing conditions

Provider specifications & access

1–1 / 1

jina ↗

source model id
jina-ai/jina-clip-v2
hosting
jina-hosted
platforms
  • Jina AI
context length
8192
architecture
input_modalities
  • text
  • image
output_modalities
  • embeddings
capabilities
  • embeddings

Source specification observations

1–2 / 2

jina ↗

field
context_length
value
8192
normalized value
8192
scope
source-model
source id
jina
confidence
1

jina ↗

field
embedding_dimensions
value
1024
normalized value
1024
scope
source-model
source id
jina
confidence
1

Original sources

1–7 / 7

Jina AI · Model page ↗

Hugging Face · jinaai/jina-clip-v2 ↗

arXiv · Paper · 2405.20204 ↗

arXiv · Paper · 2412.08802 ↗

Jina AI · Source snapshot ↗

Hugging Face · Catalog ↗

Jina AI · Catalog ↗

Source links

1–3 / 3

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace