Cohere: Command A
cohere/command-a
117th smartest of 182JSON
Intelligence
22.5
117th of 182
Design Elo
—
Speed
—
tokens/sec
Latency
—
first token
Input price
$2.50
288th cheapest
Context
256K
8K max out
How it compares
Smarter than36%
of all ranked models
Cheaper than13%
of all ranked models
Overview
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...
Benchmarks
independent · Artificial Analysis & Design ArenaArtificial Analysis65th percentile
Intelligence Index
22.5
Coding Index
27.8
GPQA Diamond
76%
Humanity's Last Exam
11%
SciCode
38%
Tau²-Bench (agentic)
81%
Providers & pricing (1)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Cohere | $2.50 | $10.00 | 256K | — |
Specifications
Context window256K
Max output8K
Knowledge cutoffAug 2024
Input modalitiestext
Output modalitiestext
Prompt caching—
Cache read price—
ModeratedYes
Open weightsCohereForAI/c4ai-command-a-03-2025 ↗
Command A FAQ
How much does Command A cost?
Command A costs $2.50 per million input tokens and $10.00 per million output tokens via OpenRouter, making it 288th cheapest of 332 paid models.
How smart is Command A?
Command A scores 22.5 on the Artificial Analysis Intelligence Index, ranking 117th of 182 benchmarked models, with a GPQA Diamond score of 76%.
What is Command A's context window?
Command A supports a 256K-token context window and can output up to 8K tokens. It accepts text input.