Context Window
CohereCommandbalancedVisionTool use

Command A+

Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...

192K context·~144K words·64K max output
View context detailsCompare with Jp Anthropic Claude Sonnet 4 6
Context window192Ktokens
Max output64Ktokens

Context window

This model accepts 192K tokens in one request (~144K words of text).

Context window size192K tokens
4K32K128K1M10M

What fits in one request

  • Short document
    About 1,500 words of text
    Fits
  • Long document
    About 37K words of text
    Fits
  • Small codebase
    About 150K words of text
    Won't fit
  • Full novel
    About 375K words of text
    Won't fit

Specifications

Context size, pricing, and release info in one place.

Context window
192,000 tokens (192K)
Max output tokens
64,000 tokens (64K)
Speed tier
balanced
Provider
Cohere
Model family
Command
Release date
Sep 2026
Input cost
$0.300/M / 1M tokens
Output cost
$1.50/M / 1M tokens
Cached input
$0.150/M / 1M tokens

Capabilities

See which features this model supports, such as vision, tools, and streaming.

Supported (6)
Vision
Supported
Tool use
Supported
Function calling
Supported
Extended thinking
Supported
Streaming
Supported
Prompt caching
Supported
Not supported (2)
Web search
Not supported
Batch API
Not supported

Best for

Jump to a guide or ranking that matches each workload.

ReasoningAI agentsMultimodalLong documentsRAG

Compare Command A+

Open a side-by-side comparison with one click.

Frequently asked questions

Short answers about context size and how this model behaves.

Command A+ has a context window of 192K tokens (192,000 tokens). This covers most professional use cases including large code files, lengthy reports, and long conversation histories.

More from Cohere

Other models by Cohere in our catalog.

Command A
Command
256Kbalanced
Command A 03 2025
Command
256Kbalanced
North Mini Code (free)
256Kfast
Cohere Command A
Command
131Kbalanced
Cohere Command R
Command R
128Kbalanced
Cohere Command R Plus
Command R
128Kbalanced

Powered by Mem0

Use a smaller model.
Get better results.

Mem0 gives your AI long-term memory so you stop re-sending context on every call. That means you can use a smaller, faster, cheaper model — and still get better answers.

Calculate your savingsLearn about Mem0

Example: a multi-turn chat session

Without Mem0~128K tokens sent
Full history
Repeated info
Old context
With Mem0~20K tokens sent
Key memories
Current turn

80% less to send — works with any model