Quickstart

Stav is an OpenAI- and Anthropic-compatible inference gateway. You keep the SDK you already use and change two things: the base URL and the key.

1. Get access

Sign up at stav.ai/signup. Access is granted from the waitlist; once your account is enabled you land in Your workspace.

Inference is paid from your workspace's prepaid credit wallet. Top up under Billing in the account menu (your avatar) before sending traffic. See Credits and billing.

2. Create an API key

Open Your workspace → Connect → API keys and create a key. It is shown once — copy it then.

export STAV_API_KEY="sk_stav_live_..."

Check it works. This call costs nothing:

curl https://api.stav.ai/v1/auth/validate \
  -H "Authorization: Bearer $STAV_API_KEY"

Key types, scopes and rotation: Authentication & API keys.

3. Send a request

Base URL: https://api.stav.ai/v1

curl

curl https://api.stav.ai/v1/chat/completions \
  -H "Authorization: Bearer $STAV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [{"role": "user", "content": "Say hello in Norwegian."}]
  }'

Python (OpenAI SDK)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["STAV_API_KEY"],
    base_url="https://api.stav.ai/v1",
)

resp = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Say hello in Norwegian."}],
)
print(resp.choices[0].message.content)
print("served by:", resp

TypeScript (OpenAI SDK)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.STAV_API_KEY,
  baseURL: "https://api.stav.ai/v1",
});

const resp = await client.chat.completions.create({
  model: "auto",
  messages: [{ role: "user", content: "Say hello in Norwegian." }],
});

Anthropic SDK

POST /v1/messages speaks the Anthropic wire format. The SDK sends x-api-key, which Stav accepts.

import os
from anthropic import Anthropic

client = Anthropic(
    api_key=os.environ["STAV_API_KEY"],
    base_url="https://api.stav.ai",  # no /v1 — the SDK adds it
)

msg = client.messages.create(
    model="anthropic/claude-sonnet-4-5",
    max_tokens=512,
    messages=[{"role": "user", "content": "Say hello in Norwegian."}],
)
print(msg.content[0].text)

4. Choose a model

The model field takes:

Details in Models.

5. Stream

stream = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Write a haiku about fjords."}],
    stream=True,
    stream_options={"include_usage": True},
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].

6. See what happened

Every response carries X-Stav-* headers: the model and Inference Provider that served it, the sovereignty level and the routing reason. See Response headers. Each request also appears in Your workspace → Monitor → Request log.

Surfaces

Unknown or unsupported request parameters are refused with a 400 that names them, not silently left out. See Request parameters.

Next

• Try it in the Playground first, then copy the request as code
• Smart Router
• Sovereignty
• Errors