Synapse Garden
cohere · Single modalityReleased 2025-03-13

command-a

cohere/command-a id

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+ 08-2024.

Tool use
Type
Use command-a
# Drop-in OpenAI-compatible client
$ import { generateText } from 'ai'
$ 
$ const { text } = await generateText({
$   model: 'cohere/command-a',
$   baseURL: 'https://synapse.garden/api/v1',
$   apiKey: process.env.MG_KEY,
$   prompt: 'Why is the sky blue?',
$ })
256K
CONTEXT WINDOW
8K
MAX OUTPUT
$2.75/M
INPUT · PER M
$11.00/M
OUTPUT · PER M
PRICING

List prices, every modality.

RatePer million tokens · USD
Input$2.75/M
Output$11.00/M
Honest list pricesHow we calculate prices
MORE FROM COHERE

Other cohere models

See all 5
Model
Input
Output
Context
Type
FAQ · COMMAND-A

Frequently asked

01 / 04

How do I call command-a from my code?

Use the OpenAI or Anthropic SDK and point baseURL at https://synapse.garden/api/v1. Set model: ‘cohere/command-a’ and supply your Synapse Garden API key. No code changes beyond the base URL.

02 / 04

How much does command-a cost?

Input: $2.75/M per million tokens. Output: $11.00/M per million tokens. The free tier includes a million tokens every month at no cost.

03 / 04

What's the context window for command-a?

command-a supports a context window of 256K tokens, with a maximum output of 8K tokens.

04 / 04

Do I need a separate Anthropic or OpenAI account?

No. Synapse Garden is the single API surface — one key gives you OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, xAI, Cohere, and more. Billing, rate limits, and audit logs are unified.

READY

Try command-a in three minutes.

Sign up, create a key, drop our base URL into your existing client. The free tier includes a million tokens every month — no credit card.

Start freeQuickstart