Canine C
Google's Canine C is an open-source embedding model that operates at a character level, directly processing input text as Unicode code points without requiring an explicit tokenizer. It is genuinely best at learning inner representations of multiple languages through self-supervised pretraining on a large corpus of multilingual data.
Input
Output
Context
2K
Max Output
0K
Parameters
132.1M
Technical Specifications
Model TypeEmbedding
Context Window2,048 tokens
Max Output Tokens320 tokens
Parameters132.1M
Release DateMar 2, 2022
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
Text
Output Modalities
Embedding
Capabilities
Estimated GPU Requirements for Canine C
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.