Cohere embed-v4
Cohere
Capabilities
Strengths
- Multilingual leader — strong cross-language retrieval
- Very long 128k context
- Matryoshka — 256/512/1024/1536 dim options
- Enterprise privacy options (BYOK, deployment in customer cloud)
Weaknesses
- Closed weights
- Slightly behind Voyage on English MTEB
Pricing
Input / 1M tokens
$0.12
Output
—
Hosting
Hosted only
Embedding specs
Output dimension
1536
Max input
128,000 tokens
Matryoshka
Supported
Matryoshka representation learning: dimension can be truncated to a smaller size at index time without retraining, trading retrieval quality for index size and speed.
Transparency
Open weights
0.0 / 10
Open training data
1.0 / 10
Open methodology
2.0 / 10
Licence openness
1.0 / 10
Provider disclosure
4.0 / 10
FMTI company score
N/A
Closed weights; some methodology disclosed.
Sustainability
Inference energy
N/A
Training footprint
N/A
Provider infrastructure
3.0 / 10
No published sustainability data.
MTEB quality
Grounded in the MTEB (Massive Text Embedding Benchmark) Overall average published by the model authors. Bearing collapses MTEB's retrieval, STS, classification, and clustering categories into a single quality signal because they correlate strongly for embedding models. Methodology.