Command A Vision

Cohere

cohere/command-a-vision-07-2025Open Weights

Cohere vision model for multilingual document analysis, OCR, and image understanding

Benchmark Pricing$2.50 / 1M in$10.00 / 1M out

Context: 128,000 tokens•Max Output: 8,000 tokens•Knowledge: 2024-06-01•Released: 2025-07-31

TECHNICAL SPECIFICATIONS

Context Window128,000128K tokens

Max Output8,0008K tokens

LicenseOpen SourceSelf-hostable

Input Modalities

TextVision

Function / Tool CallingNot Supported

Structured OutputsPrompt Based

MODEL CONTEXT PROTOCOL (MCP) READINESS

⚠ Command A Vision does not natively advertise tool-calling capabilities. When connecting to MCP servers, function calling must be handled via structured prompt injection.

MCP Context Window Recommendations

With a context capacity of 128,000 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling Command A Vision via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.COHERE_API_KEY,
});

const response = await client.chat.completions.create({
  model: "cohere/command-a-vision-07-2025",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);