MODELS / COHERE

Command A

Command A is Cohere's most performant model to date, excelling at tool use, agents, retrieval augmented generation (RAG), and multilingual use cases. Command A has a context length of 256K, only requires two GPUs to run, and has 150% higher throughput compared to Command R+…

START BUILDING COMPARE

TEXTTOOL-USE

256K

CONTEXT WINDOW

MAX OUTPUT TOKENS

$2.50

INPUT PRICE / 1M TOKENS

$10

OUTPUT PRICE / 1M TOKENS

QUICKSTART

Call it in one request.

OpenAI-compatible: change the base URL, and the setup is complete.

curl https://enterprise.blackbox.ai/v1/chat/completions \
  -H "Authorization: Bearer $BLACKBOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "blackboxai/cohere/command-a",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("BLACKBOX_API_KEY"),
    base_url="https://enterprise.blackbox.ai/v1",
)

stream = client.chat.completions.create(
    model="blackboxai/cohere/command-a",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True,
)

for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.BLACKBOX_API_KEY,
  baseURL: 'https://enterprise.blackbox.ai/v1',
});

const stream = await client.chat.completions.create({
  model: 'blackboxai/cohere/command-a',
  messages: [{ role: 'user', content: 'Hello!' }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

SPECIFICATIONS

The full spec sheet.

Context, pricing, modalities, routing, and deployment: everything Command A supports, in one table.

MODEL ID: blackboxai/cohere/command-a
DEVELOPED BY: Cohere
MODEL TYPE: Text
RELEASED: Mar 13, 2025
CONTEXT WINDOW: 256K
MAX OUTPUT TOKENS: 8K
INPUT MODALITIES: text
OUTPUT MODALITIES: text
INPUT PRICE: $2.50 / 1M tokens
OUTPUT PRICE: $10 / 1M tokens
REASONING: Not supported
DATA RETENTION: Standard retention
DEDICATED DEPLOYMENT: Not available (closed-weight model)
SUPPORTED PARAMETERS: max_tokenstemperaturestoptoolstool_choice