OpenAI text-embedding-3-small
OpenAI
Capabilities
Strengths
- Very cheap default — 6.5× cheaper than 3-large
- Matryoshka — 512/1024/1536 dim options
- Same mature OpenAI tooling
Weaknesses
- Lower MTEB than flagships
- Closed weights
Pricing
Input / 1M tokens
$0.02
Output
—
Hosting
Hosted only
Embedding specs
Output dimension
1536
Max input
8,192 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.