← All models

Mistral mistral-embed-2

Mistral

balanced

Capabilities

Long ContextMultilingual

Strengths

  • EU-hosted option (Paris) for GDPR-sensitive workloads
  • Multilingual support
  • 32k input window

Weaknesses

  • No Matryoshka
  • Mid-pack MTEB scores vs flagships

Pricing

Input / 1M tokens

$0.10

Output

—

Hosting

Hosted only

Embedding specs

Output dimension

1024

Max input

32,000 tokens

Matryoshka

No

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
70%

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.