Cohere: Command A

Cohere command model for multilingual enterprise agents, tools, and chat

Model lab: Cohere
Model family: command-a

Modalitiestext → text

Context window256,000

Maximum output8,192

InputUSD 2 / 1M tokens

OutputUSD 8 / 1M tokens

Try now View docs

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to moduck/cohere/command-a.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "moduck/cohere/command-a"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Command A API Pricing

Type	Price information
Input	USD 2 / 1M tokens
Output	USD 8 / 1M tokens

Benchmarks

Intelligence Index · v4.37

Coding Index—

Agentic Index—

Performance

Output speed63.72 tokens/s

Time to first token1.7 s

Time to first answer token—

End-to-end response time—

Performance trends

Throughput63.72 tok/sCurrent

Time to first token1.7 sCurrent

End-to-end latency8.0 sCurrent

Throughput

Current63.72 tok/s

Window average61.6 tok/s

Time to first token

Current1.7 s

Window average1.8 s

End-to-end latency

Current8.0 s

Window average7.5 s

Tail latency (P99)

Current29.8 s

Window average17.6 s

Prompt cache hit rate

Current31.2%

Window average22.5%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Command A Compare models

Model	Input price	Output price	Context window	Capabilities
Command AThis page	USD 2 / 1M tokens	USD 8 / 1M tokens	256,000	Text output
Command A Translate	USD 2 / 1M tokens	USD 8 / 1M tokens	8,000	Text output · Tool calling
Command A Reasoning	USD 0.504 / 1M tokens	USD 4.04 / 1M tokens	256,000	Text output · Reasoning · Tool calling
Command A	USD 2 / 1M tokens	USD 8 / 1M tokens	256,000	Text output · Tool calling
Command A Plus	USD 2 / 1M tokens	USD 8 / 1M tokens	128,000	Text output · Reasoning · Tool calling

Model specifications

Input: text
Output: text
Context window: 256,000
Maximum output: 8,192
Release date: 2025-03-13
Attachments: No
Reasoning: No
Tool calling: No
Structured output: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Command A for?

Cohere command model for multilingual enterprise agents, tools, and chat

What inputs and outputs does Command A support?

Recorded inputs: text; outputs: text.

How is Command A priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 2 / 1M tokens; Output USD 8 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Command A?

Current model records list Context window 256,000 tokens; Maximum output 8,192 tokens.

What model parameter does the Quickstart use?

The example uses moduck/cohere/command-a. This is a cataloged Moduck public or reserved ID; check your account’s available models before calling it.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.