Command A Vision (07-2025)

ProprietaryMultimodal

About

Cohere's first multimodal model capable of processing both text and images. Command A Vision excels in enterprise use cases such as analyzing charts, graphs, diagrams, table understanding, OCR, document Q&A, and object detection. Supports English, Portuguese, Italian, French, German, and Spanish.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution

Rankings

Best Multimodal / Vision LLMs Best LLMs for Function Calling & Tool Use Cheapest LLM APIs

Specifications

FamilyCommand

Released2025-07-01

Context128k

Architecturetransformer

Specializationvisionchatagentsdocument-understanding

LicenseProprietary