Chat & Text

Streaming Responses

Set "stream": true to receive tokens incrementally via Server-Sent Events (SSE). This keeps UIs responsive while long outputs are being generated.

Streaming is available on all chat completion endpoints. The response uses thetext/event-stream content type.

Python (SSE)

python

import requests, json

BASE_URL = "https://api.oneinfer.ai"

token = requests.post(
    f"{BASE_URL}/v1/ula/oauth-authentication?api_key=YOUR_API_KEY"
).json()["access_token"]

with requests.post(
    f"{BASE_URL}/v1/ula/chat/completions",
    headers={
        "Authorization": f"Bearer {token}",
        "Content-Type": "application/json",
    },
    json={
        "provider": "anthropic",
        "model": "claude-sonnet-4-6",
        "messages": [{"role": "user", "content": "Explain transformer architecture."}],
        "max_tokens": 512,
        "stream": True,
    },
    stream=True,
) as r:
    for line in r.iter_lines():
        if line and line.startswith(b"data:"):
            payload = json.loads(line[5:])
            print(payload.get("delta", ""), end="", flush=True)