Plain-English Summary
A Cohere model for understanding business documents, images, and mixed visual-text content.
Command A Vision
A Cohere model for understanding business documents, images, and mixed visual-text content.
Command
Multimodal LLM
GA
Open weights: No
API: Yes
Technical Notes
Text-and-image model with 128K context, 8K output, enterprise document understanding, and tool support.
Best For
Document processing, charts, scans, enterprise visual RAG
Watch Out For
Focused on understanding rather than image generation.
Model Specs
- Maker
- Cohere
- Country
- Canada
- Family
- Command
- Type
- Multimodal LLM
- Release date
- 2025-07-01
- Date confidence
- Month / model ID
- Status
- GA
- Context window
- 131,072 tokens
- Max output
- 8,192
- Parameters
- Not disclosed
- Active parameters
- Not disclosed
- Architecture
- Proprietary vision-language transformer
- Reasoning
- General reasoning
- Tool calling
- Yes
- Structured output
- Yes
- API available
- Yes
- Open weights
- No
- Self-hostable
- Private deployment options
- License
- Proprietary
- Inputs
- Text, image
- Outputs
- Text
- Approx. price
- See provider pricing
- How to access
- Provider website or API
- Model / API ID
- command-a-vision-07-2025
- Knowledge cutoff
- Not publicly disclosed
- Fine-tuning
- RAG, tools, private deployment
- Completeness
- 90 %
- Verified
- Jul 18, 2026
- Snapshot date
- Jul 18, 2026
- Source
- Official source