Call your model

curl -X POST https://model-YOUR_MODEL_ID.api.baseten.co/environments/production/predict \
  -H "Authorization: Bearer $BASETEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "Hello, world!"}'

import requests
import os

api_key = os.environ["BASETEN_API_KEY"]
model_id = "YOUR_MODEL_ID"

response = requests.post(
    f"https://model-{model_id}.api.baseten.co/environments/production/predict",
    headers={"Authorization": f"Bearer {api_key}"},
    json={"prompt": "Hello, world!"},
)

print(response.json())

https://model-{model-id}.api.baseten.co/environments/{production}/sync/{route}

import os
from openai import OpenAI

model_id = "abcdef" # TODO: replace with your model id
api_key = os.environ.get("BASETEN_API_KEY")
model_url = f"https://model-{model_id}.api.baseten.co/environments/production/sync/v1"

client = OpenAI(
    base_url=model_url,
    api_key=api_key,
)

stream = client.chat.completions.create(
    model="Qwen/Qwen2.5-3B-Instruct",  # must match --served-model-name in the deployment
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of France?"}
    ],
    stream=True,
)

for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="")