Cohere

Cohere Command A

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...

Context window
256Ktokens
Max output
8Ktokens
Input
$2.50/ 1M
Output
$10.00/ 1M

Quick start

from openai import OpenAI

client = OpenAI(
    base_url="https://neurongate.net/v1",
    api_key="sk-ng-your-api-key",
)

completion = client.chat.completions.create(
    model="cohere/command-a",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(completion.choices[0].message.content)

Cost

Example requestTokensCost
Short prompt1K in$0.0025
Typical chat turn1K in · 500 out$0.0075
Document analysis10K in · 2K out$0.045
Long context100K in · 10K out$0.35
Estimated cost per request$0.0075

Prices in USD. Billed per token actually used, from a balance prepaid in USDT, USDC, ETH or BTC.

Frequently asked questions

What is Cohere Command A?

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...

How much does Cohere Command A cost?

Cohere Command A is priced at $2.5 per 1 million input tokens and $10 per 1 million output tokens when accessed via NeuronGate. You pay per token — no subscriptions required. Top up with crypto (USDT, USDC, ETH, BTC).

Does Cohere Command A support streaming?

Yes, Cohere Command A supports streaming responses via NeuronGate's API. Use the standard "stream": true parameter in your request.

What is the context window of Cohere Command A?

Cohere Command A has a context window of 256K tokens (~192K words). Maximum output is 8K tokens.

Does Cohere Command A support function calling (tools)?

Yes, Cohere Command A supports function calling / tool use via NeuronGate's standard API.

How do I use Cohere Command A with NeuronGate?

Create a NeuronGate account, top up your balance with crypto, generate an API key, and use the model id cohere/command-a in your requests. NeuronGate uses the OpenAI-compatible API format — set your base URL to https://neurongate.net/v1.