Quickstart

Swap your existing OpenAI-compatible provider for Corti Models in two changes.

Already using the OpenAI SDK, Azure OpenAI, or any OpenAI-compatible provider? Switching to Corti Models means changing two lines — no new SDK, no rewrite, no migration.

Corti Models is available only for Corti projects hosted in the EU region (https://ai.eu.corti.app). Credentials from a US-hosted project can’t access Corti Models. See Environments & Tenants.

Get your API key

Grab your API key from the Corti Console’s Developer Quickstart — a one-click Copy all as .env variables action copies everything you need.

Open the Developer Quickstart in the Corti Console

Sign in, then under Default client → Copy all as .env variables.

Swap your provider

If your code looks like this today:

Python

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["OPENAI_API_KEY"],
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}],
)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
});

const response = await client.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: "Hello!" }],
});

Change the base URL and API key, and you’re running on Corti:

Python

from openai import OpenAI

# corti-s1 | corti-s1-instant | corti-s1-mini | corti-s1-mini-instant
MODEL = "corti-s1"

client = OpenAI(
    base_url="https://ai.eu.corti.app/v1",
    api_key="<your-api-key>",
)

response = client.chat.completions.create(
    model=MODEL,
    messages=[{"role": "user", "content": "Hello!"}],
)

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

import OpenAI from "openai";

// corti-s1 | corti-s1-instant | corti-s1-mini | corti-s1-mini-instant
const MODEL = "corti-s1";

const client = new OpenAI({
  baseURL: "https://ai.eu.corti.app/v1",
  apiKey: "<your-api-key>",
});

const response = await client.chat.completions.create({
  model: MODEL,
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(response.choices[0].message.content);

API_KEY="<your-api-key>"
# corti-s1 | corti-s1-instant | corti-s1-mini | corti-s1-mini-instant
MODEL="corti-s1"

curl https://ai.eu.corti.app/v1/chat/completions \
  -H "Authorization: Bearer ${API_KEY}" \
  -H "Content-Type: application/json" \
  -d "{
    \"model\": \"${MODEL}\",
    \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}]
  }"

Everything else in your code — streaming, tool calling, JSON mode, multi-turn conversations, the Responses API — works unchanged. Corti Models is a drop-in replacement.

OAuth 2.0 access tokens will be supported soon. For now, use your Corti API key as the apiKey / Bearer credential.

See which models are available

List the models your credentials can access to confirm the model IDs you can pass:

cURL

API_KEY="<your-api-key>"

curl https://ai.eu.corti.app/v1/models \
  -H "Authorization: Bearer ${API_KEY}"

See the Models page for the full lineup and pricing.

Next steps

Models

Compare the four model variants by capability, reasoning, speed, and price.

Code with Corti

Connect OpenCode, ForgeCode, Crush, or Pi to Corti Models with the Corti CLI.

API Reference

Browse the full Corti Models API with interactive examples.

Authentication

How authentication works at Corti.