Quickstart

Get up and running with Solon in under a minute.

Install

curl -fsSL https://getsolon.dev | sh

Start the server

On first run, Solon automatically creates an admin API key and displays it. Save this key — it won't be shown again.

solon serve

Pull a model

solon models pull llama3.2:3b

Make your first request

curl http://localhost:8420/v1/chat/completions \
  -H "Authorization: Bearer sol_sk_live_xxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama3.2:3b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Open the dashboard

Visit http://localhost:8420 in your browser to access the built-in dashboard for managing models, API keys, and monitoring requests.

Use with any OpenAI SDK

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8420/v1",
    api_key="sol_sk_live_xxxx",
)

response = client.chat.completions.create(
    model="llama3.2:3b",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)