TokenLab

Frameworks & Platforms

Guardrails

Validate TokenLab model outputs with Guardrails

Overview

Configure the OpenAI SDK with the TokenLab Base URL, request JSON, then validate the returned text with Guard.parse.

Installation

pip install guardrails-ai openai

Environment

export TOKENLAB_API_KEY="sk-your-tokenlab-key"

Example

import os

from guardrails import Guard
from openai import OpenAI
from pydantic import BaseModel, Field


class Pet(BaseModel):
    pet_type: str = Field(description="Species of pet")
    name: str = Field(description="A unique pet name")


guard = Guard.for_pydantic(output_class=Pet)

client = OpenAI(
    api_key=os.environ["TOKENLAB_API_KEY"],
    base_url="https://api.tokenlab.sh/v1",
)

response = client.chat.completions.create(
    model="claude-sonnet-5",
    response_format={"type": "json_object"},
    messages=[{
        "role": "user",
        "content": "Suggest a pet. Return only JSON with string fields pet_type and name.",
    }],
)

outcome = guard.parse(response.choices[0].message.content)
print(outcome.validated_output)

Endpoint Notes

Guardrails focuses on validation around the LLM call. Use the OpenAI-compatible path for chat-completions flows, or pass a custom callable if your application needs a native TokenLab endpoint.

On this page