Use Wren R1 as the model under test in your evaluation framework

If your evaluation framework already accepts a custom OpenAI-compatible provider, you can point it at Wren R1 and run the same suite you run today. You set two values and keep your existing evaluation code.

Set the base URL to https://webwright.ai/v1 and the model to wren-r1.

from openai import OpenAI

client = OpenAI(
    base_url="https://webwright.ai/v1",
    api_key="YOUR_WEBWRIGHT_KEY",
)

response = client.chat.completions.create(
    model="wren-r1",
    messages=[{"role": "user", "content": "Reply with the single word: ready"}],
)

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

Most evaluation frameworks read the provider from the same OpenAI-compatible client or from a base URL and model pair in their config. Some evaluation frameworks, including Ragas, DeepEval, Braintrust and Arize Phoenix, let you set the provider this way, so the change is configuration, not a new integration.

If you run evaluations and want a second model under test or judge, tell us what you are evaluating. We will help you point your framework at Wren R1.

The WebWright Team