Home/Models/Command A
Cohere logo

Command A

by Cohere · Released Mar 2025

Open Source
Compare
Context
256K tokens (~128 books)
Input $/1M
$2.50
Output $/1M
$10.00
Type
text
License
Open Source
Benchmarks
3 tested
Data updated today
About

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...

Tested on 3 benchmarks with 0.0% average. Top scores: Artificial Analysis — Quality Index (13.5%), Artificial Analysis — Coding Index (9.9%), Artificial Analysis — Agentic Index (5.1%).

Capabilities
speed
15.8
#59 globally
Benchmark Scores
Compare All
Tested on 3 benchmarks · Ranked across 1 categories
Score Distribution (all 233 models)
0255075100
Artificial Analysis — Quality Index

Artificial Analysis Quality Index. Composite quality score combining multiple benchmark results into a single metric.

13.5
Artificial Analysis — Coding Index

Artificial Analysis Coding Index. Composite coding quality score from multiple code benchmarks.

9.9
Artificial Analysis — Agentic Index

Artificial Analysis Agentic Index. Composite score measuring agent capability across tool use and planning tasks.

5.1
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
command-a
Specifications
  • Typetext
  • Context256K tokens (~128 books)
  • ReleasedMar 2025
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.015
Available On
Cohere logoCohere$2.50
Categories
Share & Export
Tweet
Command A is an open-source text AI model by Cohere, released in March 2025. Context window: 256K tokens.