Skip to main content

Custom SLAs

Terminal is adding request-level SLA controls so you can define latency and cost preferences without changing endpoints. These headers are not live yet.
from openai import OpenAI

client = OpenAI(
    base_url="https://api.terminal.fyi/v1",
    api_key="TERMINAL_API_KEY",
)

response = client.chat.completions.create(
    model="gemma-4-31b",
    messages=[
        {
            "role": "user",
            "content": "Extract launch-review action items and group them by owner.",
        }
    ],
    max_tokens=8000,
    extra_headers={
        "X-Terminal-SLA-Deadline": "10m",
        "X-Terminal-SLA-Priority": "cost",
    },
    timeout=1800.0,
)

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