Cohere
Command A
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.
At a glance
- Input / 1M
- $2.50
- Output / 1M
- $10
- Context
- 256K
- Max output
- 8K
- Intelligence
- 13.1
- Released
- Mar 2025
Pricing
Command A API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $2.50 |
|---|---|
| Output tokensPer 1M tokens | $10 |
| Cached input (read)Per 1M tokens | Not available |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$10
per 1,000 requests
Coding task
30K in, 4K out
$115
per 1,000 requests
Long document summary
150K in, 2K out
$395
per 1,000 requests
Benchmarks
Command A benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
13.1
Coding index
27.8
Agentic index
1
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 256K tokens
- Max output
- 8K tokens
- Input types
- Text
- Output types
- Text
- Reasoning effort
- Not available
- Release date
- March 13, 2025
- Knowledge cutoff
- August 31, 2024
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
Command A vs other models
See how Command A stacks up head to head on price, benchmarks, and features.
VS
Command A vs Claude Haiku 4.5
Cohere vs Anthropic
See comparisonVS
Command A vs Gemini 2.5 Pro
Cohere vs Google
See comparisonVSCommand A vs Gemini 2.5 Flash
Cohere vs Google
See comparisonVS
Command A vs Mistral Medium 3.5
Cohere vs Mistral
See comparisonVS
Command A vs R1 0528
Cohere vs DeepSeek
See comparisonVS
Command A vs GPT-4.1
Cohere vs OpenAI
See comparisonAlternatives
Command A alternatives
Similar models worth considering, and where each one has the edge.
Anthropic
Claude Haiku 4.5
Gemini 2.5 Pro
Gemini 2.5 Flash
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does Command A cost?
Command A costs $2.50 per 1M input tokens and $10 per 1M output tokens through the API. A typical chat message costs about $10 per 1,000 messages.
What is the context window of Command A?
Command A accepts up to 256K tokens of input and can write up to 8K tokens in a single response.
What is the best alternative to Command A?
Claude Haiku 4.5 from Anthropic is a strong alternative. It offers: 2x cheaper output, higher intelligence score, accepts image and file.
Can I use Command A alongside other models?
Yes. Shortcut Chat sends one prompt to Command A and any other models you pick at the same time, so you can compare answers side by side.
Try Command A next to every other model.
Use Command A alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.