Back to models
Command A Vision (072025)
Flagship modelNew
Cohere multimodal model with vision capabilities
| Context window | 128,000 tokens |
| Max output tokens | 8,192 tokens |
Pricing
| Type | Input | Output |
|---|---|---|
| Standard | $2.50 / 1M tokens | $10.00 / 1M tokens |
Parameters
| Parameter | Default | Range |
|---|---|---|
| Temperature | 1 | 0 to 2 |
| Top P | 1 | 0 to 1 |
| Frequency penalty | 0 | -2 to 2 |
| Presence penalty | 0 | -2 to 2 |
| Max stop sequences | 4 | — |
Supported features
Capabilities
- Streaming
- Function Calling
- Structured Output
- Json Mode
- System Prompt
Endpoints
- Chat Completions
- Vision
Use cases
- text-chat
- vision
- function-calling
Model specifications
| Model ID | command-a-vision-07-2025 |
| Family | command-a |
| Access type | Closed |
| Input modalities | text, image |
| Output modalities | text |