Connect Your App to AI Gateway

AUTH_TOKEN=$(curl -s --request POST \
    --url 'https://auth.prd.cloud.redpanda.com/oauth/token' \
    --header 'content-type: application/x-www-form-urlencoded' \
    --data grant_type=client_credentials \
    --data client_id=<client-id> \
    --data client_secret=<client-secret> \
    --data audience=cloudv2-production.redpanda.cloud | jq -r .access_token)

from authlib.integrations.requests_client import OAuth2Session
import requests

# Discover token endpoint from OIDC metadata
metadata = requests.get(
    "https://auth.prd.cloud.redpanda.com/.well-known/openid-configuration"
).json()
token_endpoint = metadata["token_endpoint"]

client = OAuth2Session(
    client_id="<client-id>",
    client_secret="<client-secret>",
    token_endpoint=token_endpoint,
)

token = client.fetch_token(
    grant_type="client_credentials",
    audience="cloudv2-production.redpanda.cloud",
)

access_token = token["access_token"]

import { Issuer } from 'openid-client';

const issuer = await Issuer.discover(
  'https://auth.prd.cloud.redpanda.com'
);

const client = new issuer.Client({
  client_id: '<client-id>',
  client_secret: '<client-secret>',
});

const tokenSet = await client.grant({
  grant_type: 'client_credentials',
  audience: 'cloudv2-production.redpanda.cloud',
});

const accessToken = tokenSet.access_token;

import os
from openai import OpenAI

client = OpenAI(
    base_url=os.environ["PROXY_URL"],       # .../llm/v1/providers/my-openai
    api_key=os.environ["AUTH_TOKEN"],        # OIDC access token
)

response = client.chat.completions.create(
    model="gpt-4o",                          # native OpenAI model ID
    messages=[{"role": "user", "content": "Hello from AI Gateway"}],
)
print(response.choices[0].message.content)

import os
from anthropic import Anthropic

client = Anthropic(
    base_url=os.environ["PROXY_URL"],       # .../llm/v1/providers/my-anthropic
    auth_token=os.environ["AUTH_TOKEN"],     # OIDC access token
)

message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello from AI Gateway"}],
)
print(message.content[0].text)

import os
from google import genai

client = genai.Client(
    api_key=os.environ["AUTH_TOKEN"],        # forwarded as x-goog-api-key
    http_options={"base_url": os.environ["PROXY_URL"]},  # .../llm/v1/providers/my-google
)

response = client.models.generate_content(
    model="gemini-2.0-flash",
    contents="Hello from AI Gateway",
)
print(response.text)

import os, httpx

# Bedrock 4.6+ Anthropic models require an inference profile (us./eu./apac./global.).
# Replace with the inference profile your provider exposes.
response = httpx.post(
    f"{os.environ['PROXY_URL']}/model/us.anthropic.claude-sonnet-4-6/invoke",
    headers={"Authorization": f"Bearer {os.environ['AUTH_TOKEN']}"},
    json={
        "anthropic_version": "bedrock-2023-05-31",
        "messages": [{"role": "user", "content": "Hello"}],
        "max_tokens": 1024,
    },
)
print(response.json())

import os
from openai import OpenAI

client = OpenAI(
    base_url=os.environ["PROXY_URL"],       # .../llm/v1/providers/my-vllm
    api_key=os.environ["AUTH_TOKEN"],
)

response = client.chat.completions.create(
    model="meta-llama/Llama-3.3-70B-Instruct",  # as exposed by your upstream
    messages=[{"role": "user", "content": "Hello"}],
)