Command A — Cohere | Modeldex

Command A

Active

Cohere's most capable model with 256K context, optimized for enterprise agentic tasks.

Updated 4 days agoStructured data from Modeldex catalog

AgenticLong context

Knowledge cutoff

Aug 31, 2024(1.6 years ago)

API release

Mar 13, 2025(1.1 years ago)

Not enough benchmark coverage yet for an Intelligence Index — needs at least 3 results across 2 categories.

Overview

Command A is Cohere's 111B dense model designed to run efficiently on just two A100/H100 GPUs. It features a 256K context window, strong RAG performance, and both reasoning and vision variants. Released March 2025.

History

Command A became available via the Cohere API on 2025-03-13.

Training & availability

Training data has a knowledge cutoff of 2024-08-31 — information about events after that date is unlikely to appear in the model's responses. Cohere has not released the underlying model weights — access is via their hosted API only.

Capabilities

Context window: 256K tokens.
Max output: 8K tokens.
Input modalities: text.

Recommended for: agentic, long-context.

Limitations

The knowledge cutoff is 19 months old — this model will not know about recent events, releases, or API changes.
Text-only — cannot process images, audio, or video inputs.

Pricing

Input: $2.5000 per 1M tokens
Output: $10.0000 per 1M tokens

Use the cost calculator above to estimate monthly spend for your workload.

Quick start

Minimal example using the OpenRouter API. Copy, paste, replace the key.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="sk-or-...",
)
resp = client.chat.completions.create(
    model="cohere/command-a",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)

Cost calculator

Estimate your monthly bill. Presets are typical workload sizes.

Input tokens / month5.0M

@ $2.5/1M

Output tokens / month2.0M

@ $10/1M

Input cost

$12.5

5.0M × $2.5/1M

Output cost

$20

2.0M × $10/1M

Total / month

$32.5

$390 / year

Popularity

Signals from open-source communities — not a quality measure, but useful for gauging adoption among developers.

🤗

HuggingFace downloads

4.3K/ month

HuggingFace likes

384

Integrations & tooling support

Tool calling: Supported
Structured outputs: Supported

Price vs quality

Premium pricing

Priced like a frontier model. Quality tier pending more benchmark coverage.

Quality percentile: —
Effective price: $8.13/1M
Pricing breakdown: $2.5/1M in
$10/1M out

Community ratings

No ratings yet. Be the first to rate Command A.