Get started / Quickstart

# Quickstart

One API key, one call, and a response that tells you which endpoint served it and what it cost.

## Install

```
pip install openai  # or: npm install openai — any OpenAI SDK works
```

## Authenticate

Keys are scoped to a project and environment and are sent as `Authorization: Bearer`. Read `YELNO_API_KEY` from the environment — never hard-code it, and never put it in a URL.

```
export YELNO_API_KEY="yk_live_…"
```

## Make your first call

```
import os
from openai import OpenAI

client = OpenAI(base_url="https://yelno.ai/v1", api_key=os.environ["YELNO_API_KEY"])
res = client.chat.completions.create(
    model="mistral/mistral-large-2",
    messages=[{"role": "user", "content": "ping"}],
)
print(res.choices[0].message.content)
meta = res.model_extra["yelno"]   # additive object; existing clients ignore it
# cost is integer nanos: 46000 = $0.000046
print(meta["provider"], meta["attempts"][0]["region"], meta["cost"]["customer_nanos"], meta["cost"]["state"])
```

```
pong
mistral eu-west 46000 final
```

## What's next

- [Routing policies](https://yelno.ai/docs/routing): Require ZDR, pin regions, and allow or block providers and models — per organization.

- [Streaming](https://yelno.ai/docs/streaming): SSE chunks plus a terminal frame carrying usage and the cost state.

- [Migration](https://yelno.ai/docs/sdks): Point any OpenAI SDK at our base URL and keep your code.

Source: https://yelno.ai/docs