Command A+
Command A+ is an enterprise-focused AI model developed by Cohere designed for agentic workflows. It supports both text and image inputs and features native tool calling capabilities with structured output. The model offers a 192,000 token context window to handle complex multi-step tasks.
Command A+ specs and pricing
- Provider: Cohere
- Released: September 22, 2026
- Context window: 192K tokens
- Max output: 64K tokens
- Input: text, images
- Output: text
- Price: $0.30 input / $1.50 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Command A+ is good at
- Automating complex enterprise agentic workflows
- Analyzing documents and images for structured data extraction
- Executing multi-step tasks using integrated tool calling
To-dos to try with Command A+
- Analyze a set of project images and text reports to generate a structured status summary.
- Use tool calling to query an internal database and compile a report based on the results.
- Process a long document to extract specific data points into a predefined JSON schema.
FAQ
- What is Command A+ designed to do? It is Cohere's flagship model built specifically for enterprise agentic workflows and complex task automation.
- Can this model process visual information? Yes, Command A+ accepts both text and image inputs.
- How much does Command A+ cost? Command A+ costs $0.30 per million input tokens and $1.50 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1.05 credits ($1 = 100 credits).
- What is the context window of Command A+? Command A+ can read up to 192K tokens at once and write up to 64K tokens in one reply.
- Can I use Command A+ without coding? Yes. In todo.is you pick Command A+ as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.