How much does Command A cost?

Billing is usage-based: $2.5 per million input tokens and $10 per million output tokens. There is no monthly minimum. You pay only for the tokens you actually use.

How do I access Command A from inside Iran?

Create a Hormouz account, generate an API key and point your client at Hormouz. Access to Command A is served from inside Iran, so you do not need a foreign credit card, a VPN or any sanction-circumvention tooling.

Is Command A compatible with the OpenAI SDK?

Yes. Hormouz exposes an OpenAI-compatible chat-completions API. Change the base URL to Hormouz and drop in your Hormouz key, and existing OpenAI SDK code runs unchanged.

What context window does Command A support?

Command A supports a context window of up to 256K tokens, which is enough for long documents and extended conversations in a single request.

What makes Command A a good fit for enterprise use?

It targets agentic, multilingual and coding tasks with a large 256K context window while keeping hardware costs low. That combination suits business-critical assistants and multilingual retrieval workflows.

Is Command A multilingual?

Yes. Command A is designed to perform well across many languages, which makes it a good choice for multilingual assistants and cross-language retrieval-augmented generation.

Cohere: Command A: AI model

Command A is Cohere's 111B open-weights flagship for agentic, multilingual and coding tasks, with a 256K context window. Reachable from inside Iran through Hormouz.

Context window:: 256,000 tokens
Input:: $2.5/1M tokens
Output:: $10/1M tokens
Type:: text

Streaming
Long context

Command A is Cohere's open-weights flagship, a 111B-parameter model with a 256K-token context window focused on agentic, multilingual and coding use cases. It is designed to deliver strong performance while keeping hardware costs low, which makes it attractive for business-critical workloads.

The model is text-in, text-out and supports structured output, so it fits enterprise assistants, multilingual RAG and coding tasks. Its large context window lets it work over long documents and extended conversations in a single request.

Through Hormouz, Command A is served behind an OpenAI-compatible API and reachable from inside Iran without a foreign credit card. Billing is usage-based at $2.50 per million input tokens and $10.00 per million output tokens.

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. Compared to other leading proprietary...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "cohere/command-a",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

Vendor	Cohere
Type	Text
Context window	256,000 tokens
Pricing	$2.50/M in · $10.00/M out
API	Chat Completions
Capabilities	Streaming

Benchmarks

13.1

Intelligence Index

Better than 22% of models we compared

27.8

Coding Index

Better than 30% of models we compared

Agentic Index

Better than 12% of models we compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

76.1%

HLE

Humanity's Last Exam

12%

IFBench

Instruction-following

73.9%

AA-LCR

Long-context reasoning

52.7%

CritPt

Research-level physics reasoning

0.3%

AA Omniscience

Broad factual knowledge accuracy

8.9%

Non-Hallucination

Rate of avoiding fabricated answers

85.8%

Coding

SciCode

Python for scientific computing

38.5%

Terminal-Bench Hard

Agentic coding & terminal use

25%

Agentic

τ²-Bench

Tool-use agents in dual-control scenarios

80.7%

GDPval

Economically valuable tasks

0.9%

Source: Artificial Analysis

Code example

cURL

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "cohere/command-a",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python

from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="cohere/command-a",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

JavaScript

import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "cohere/command-a",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Cohere: Command A API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches Cohere: Command A and 600+ other models, and you pay only for what you use.
No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.

Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Command A cost?: Billing is usage-based: $2.5 per million input tokens and $10 per million output tokens. There is no monthly minimum. You pay only for the tokens you actually use.
How do I access Command A from inside Iran?: Create a Hormouz account, generate an API key and point your client at Hormouz. Access to Command A is served from inside Iran, so you do not need a foreign credit card, a VPN or any sanction-circumvention tooling.
Is Command A compatible with the OpenAI SDK?: Yes. Hormouz exposes an OpenAI-compatible chat-completions API. Change the base URL to Hormouz and drop in your Hormouz key, and existing OpenAI SDK code runs unchanged.
What context window does Command A support?: Command A supports a context window of up to 256K tokens, which is enough for long documents and extended conversations in a single request.
What makes Command A a good fit for enterprise use?: It targets agentic, multilingual and coding tasks with a large 256K context window while keeping hardware costs low. That combination suits business-critical assistants and multilingual retrieval workflows.
Is Command A multilingual?: Yes. Command A is designed to perform well across many languages, which makes it a good choice for multilingual assistants and cross-language retrieval-augmented generation.

Updated 2026-10-13