cohere

Cohere: Command A

The Cohere Command A is a language model designed for processing text input. It can handle context lengths of up to 256,000 tokens and supports text modality as an input format. This model may be suitable for users who require high-context applications and are willing to pay $2.5 per million input tokens and $10.0 per million output tokens. Its blended benchmark score is 8.4 across two independent benchmarks, but its performance in specific areas like reasoning or tool support remains unproven due to a lack of supporting data.

Quality Score
78/100
price + capability + benchmarks
Input Price
$2.50
per 1M tokens · checked 2026-09-08
Output Price
$10.00
per 1M tokens · checked 2026-09-08
Context Window
256,000
tokens

Benchmark results

Independent, published benchmarks. Blended score 8.4 across 2 benchmarks, last refreshed 2026-09-08. How scoring works →

BenchmarkMeasuresScore
Aider Polyglot code editing across languages 12.0
AI Index broad capability composite 11.5
Model ID
cohere/command-a
Vendor
cohere
Released
March 2025
Tokenizer
Other
Input Modalities
text
Output Modalities
text
Max Output
8,192 tokens
Tool Calling
not supported
Structured Output
✓ supported
Reasoning Mode
not supported
Vision
text only
Audio
no
Moderated
yes

What it costs in practice

Computed from the current $2.50/M input and $10.00/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.09
Classify 1,000 customer emails 500k in / 50k out $1.75
A month of a busy support chatbot 5M in / 2M out $32.50

Similar models

Quick answers

How much does Cohere: Command A cost?
$2.50 per million input tokens and $10.00 per million output tokens.
What is Cohere: Command A's context window?
256,000 tokens, roughly 384 pages of text in a single request.
Does Cohere: Command A support tool calling?
It supports structured output.
Can Cohere: Command A process images?
No, it is text-only on the input side.