K
KairosRoute
Docs/SDKs

SDKs

For chat completions, use any OpenAI-compatible SDK. For workflows, tasks, and receipts, use the branded kairosroute SDK.

Chat completions

Drop any OpenAI SDK onto our base URL. We speak the OpenAI API shape — streaming, tool use, JSON mode, vision, logprobs, all passthrough.

pip install openai
from openai import OpenAI

client = OpenAI(
    api_key="kr-your-key",
    base_url="https://api.kairosroute.com/v1",
)

resp = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

Using LangChain, CrewAI, AutoGen, or the Vercel AI SDK? See framework integrations.

Workflows & tasks

The branded SDK wraps the agent runtime: typed DAGs, budgets, streaming step events, task snapshots, and receipt retrieval. Python and TypeScript today, Go on the way.

pip install kairosroute
from kairosroute import KairosRoute

kr = KairosRoute(api_key="kr-your-key")

result = kr.workflows.execute(
    workflow="research",
    input={"goal": "Summarize Q1 2026 GPU launches"},
    budget={"max_cost_usd": 0.25, "on_exceed": "downgrade"},
)
print(result["outputs"]["summary"])

Full DAG semantics, strategies, and capability hints in the agents guide.

Links