amicsdocs
Get started

Quickstart

Get your API key and make your first inference, model deployment, and compute calls.

1. Get your API key

Sign up from the dashboard and create an API key. It looks like amics_sk_... and is shown once.

export AMICS_API_KEY=amics_sk_...

2. Run Hosted Inference

Use the SDK:

from amics import Client

amics = Client()

response = amics.inference.chat(
    "deepseek-v4-pro",
    messages=[{"role": "user", "content": "Summarise this email: ..."}],
)

print(response["choices"][0]["message"]["content"])

Or use any OpenAI-compatible client:

from openai import OpenAI

client = OpenAI(
    api_key="amics_sk_...",
    base_url="https://ingest.amics.ai/v1",
)

response = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[{"role": "user", "content": "Implement Hello World in Python"}],
)

3. Deploy Your Own Model

model = amics.models.deploy("ticket-classifier", template="llama")

deployment = amics.models.create_deployment(
    model["id"],
    "production",
    accelerator="H100",
    production=True,
)

4. Launch Compute

session = amics.compute.launch(
    project_id="fine-tune",
    name="notebook",
    hardware="H100",
    ttl_minutes=120,
)

On this page