← All models

Cohere embed-v4

Cohere

flagship

Capabilities

Long ContextMultilingual

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

Composite:1.5 / 10

Closed weights; some methodology disclosed.

Sustainability

Inference energy

N/A

Training footprint

N/A

Provider infrastructure

3.0 / 10

Composite:3.0 / 10

No published sustainability data.

MTEB quality

Embedding
83%

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.