Google logo

BERT 2 EN Uncased L-2 H-768 A-12

Pricing & Specs API
Free REST API for prices, specs and benchmarks
BERT 2 EN Uncased L-2 H-768 A-12 is Google's embedding model. A shallow uncased English BERT variant with 2 layers and 768 hidden units, offering a balance of speed and embedding quality.
Specifications
Canonical IDgoogle-bert-2-en-uncased-l-2-h-768-a-12
TypeEmbedding
StatusActive
CreatorGoogleGoogle
Input ModalitiesText
Output ModalitiesEmbedding

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text·
Image·
Audio·
Video·
Embedding✓
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
BERT Base Uncased————Available
BERT 2 EN Uncased L-2 H-768 A-12————Current
BERT 2 EN Uncased L-10 H-256 A-4————Available
BERT 2 EN Uncased L-10 H-512 A-8————Available
BERT 2 EN Uncased L-10 H-768 A-12————Available
BERT 2 EN Uncased L-12 H-128 A-2————Available
BERT 2 EN Uncased L-12 H-512 A-8————Available
BERT 2 EN Uncased L-2 H-128 A-2————Available
BERT 2 EN Uncased L-2 H-512 A-8————Available
BERT Base Cased————Available
BERT Base Talking heads Gated Gelu————Available

Model IDs

google-bert-2-en-uncased-l-2-h-768-a-12
tensorflow-tcembedding-bert-en-uncased-L-2-H-768-A-12-2