GET STARTED

Your first Yugos request

A familiar API, with automatic model routing.

1. Create an API key

Sign in to the console, select a project, and create a key. Save the key on your server; it is shown once. Never put it in frontend code or source control.

Start with yugos/free without adding credit. The free beta includes 10 requests per day per workspace, subject to shared capacity. For automatic routing with yugo or paid models, add credit in Billing. Top-ups start at $10.

2. Set your connection

The API base URL is https://api.yugos.ai/v1.

export YUGO_API_KEY="<your project key>"
export YUGO_BASE_URL="https://api.yugos.ai/v1"

3. Make a Chat Completions call

import os
from openai import OpenAI

client = OpenAI(
    base_url=os.environ["YUGO_BASE_URL"],
    api_key=os.environ["YUGO_API_KEY"],
    max_retries=0,
)

response = client.chat.completions.create(
    model="yugos/free",
    messages=[{"role": "user", "content": "Hello, Yugos."}],
    max_tokens=1024,
)
print(response.choices[0].message.content)

Use an output-limit parameter supported by the chosen models. max_tokens and max_completion_tokens retain their native semantics. Find supported capabilities with GET /v1/catalog.

Yugos Free supports text Chat Completions, including streaming, tools, and structured output when free capacity supports your request. It allows one request at a time per workspace and up to 1,024 output tokens. The daily allowance resets at 00:00 UTC. See the free model guide for limits.

4. Inspect the receipt

Responses include a request ID and receipt location. View execution and billing status in Requests, then inspect actual model costs in Usage & spend. Pending costs remain pending until authoritative usage is available.

See routing controls before integrating a client.