Command A Vision
Cohere's Command A Vision is a 112 billion parameter vision model optimized for enterprise image understanding tasks, with capabilities including function calling, image understanding, and text generation. It is genuinely best at vision-language understanding tasks, leveraging a multimodal adapter to combine a language model with a vision encoder.
Input
Output
Context
128K
Max Output
8K
Parameters
111.9B
Technical Specifications
Model TypeChat
Context Window128,000 tokens
Max Output Tokens8,000 tokens
Parameters111.9B
Release DateJul 28, 2025
Training CutoffJun 1, 2024
Licensecc-by-nc-4.0
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Command A Vision
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 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.