Streaming

# Self-deployed Truss model: stream from the model's predict endpoint
import os
import requests

model_id = "YOUR_MODEL_ID"

with requests.post(
    f"https://model-{model_id}.api.baseten.co/production/predict",
    headers={"Authorization": f"Bearer {os.environ['BASETEN_API_KEY']}"},
    json={"prompt": "Write a haiku about the ocean.", "stream": True},
    stream=True,
) as resp:
    for chunk in resp.iter_content():
        print(chunk.decode("utf-8"), end="", flush=True)

# Model APIs: OpenAI-compatible endpoint at inference.baseten.co
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://inference.baseten.co/v1",
    api_key=os.environ["BASETEN_API_KEY"],
)

stream = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Pro",
    messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

# Model APIs: Anthropic-compatible endpoint (beta) at inference.baseten.co
import os
import anthropic

api_key = os.environ["BASETEN_API_KEY"]

client = anthropic.Anthropic(
    base_url="https://inference.baseten.co",
    api_key=api_key,
    default_headers={"Authorization": f"Bearer {api_key}"},
)

with client.messages.stream(
    model="deepseek-ai/DeepSeek-V4-Pro",
    max_tokens=4096,
    messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

# Model APIs: add "stream": true and keep the connection open with --no-buffer
curl https://inference.baseten.co/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $BASETEN_API_KEY" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V4-Pro",
    "messages": [{"role": "user", "content": "Write a haiku about the ocean."}],
    "stream": true
  }' \
  --no-buffer