ModelInfo
English
All models

Command A Vision

Image-processing model for charts, tables, diagrams, OCR, document Q&A, and object detection.

Coherecommand-a-vision-07-20252025-07-31Report incorrect data

Specs

Context
128K
Max output
8K
Input price
—
Output price
—
Released
2025-07-31

Context

Context window
128K
Max input
—
Max output
8K

Pricing

Not published

Modalities

Input
TextImage
Output
Text

API

API types
chat

Reasoning

Not published

Info

Status
Active
Released
2025-07-31
Knowledge cutoff
2024-06

Features

Not published
Source · official docsVerified 2026-10-11

How to call

1 provider

coheremodel = command-a-vision-07-2025

chat
POSThttps://api.cohere.com/v2/chat

JSON

Standard format
command-a-vision-07-2025.json
{
  "id": "command-a-vision-07-2025",
  "object": "model",
  "created": 1753920000,
  "owned_by": "cohere",
  "name": "Command A Vision",
  "api": {
    "types": [
      "chat"
    ]
  },
  "limits": {
    "context": 128000,
    "input": null,
    "output": 8000
  },
  "modalities": {
    "input": [
      "text",
      "image"
    ],
    "output": [
      "text"
    ]
  },
  "reasoning": {
    "supported": null,
    "efforts": []
  },
  "pricing": null,
  "features": [],
  "info": {
    "status": "active",
    "release_date": "2025-07-31",
    "knowledge_cutoff": "2024-06",
    "description": "Image-processing model for charts, tables, diagrams, OCR, document Q&A, and object detection.",
    "docs": "https://docs.cohere.com/docs/command-a-vision",
    "verified_at": "2026-10-11"
  }
}

Official sources

4