xAI Batch API structured outputs: pass a Pydantic model as response_format

TL;DR

Pass a Pydantic BaseModel class as the response_format parameter of chat.create, then use chat.append followed by chat.sample(), and the sampled response comes back as a JSON string that adheres to your schema.

Steps

1. I want to use structured outputs with the xAI Batch API for entity extraction at scale, but the docs list responseformat as unsupported there. Is there any way to get JSON schema enforcement in batch jobs? My use case is bulk entity extraction where prompt-only JSON is too brittle at scale. The batch docs do not show a responseformat example anywhere.
2. You can already do this. Pass a Pydantic BaseModel class as the responseformat parameter of chat.create, then use chat.append followed by chat.sample(), and the sampled response comes back as a JSON string that adheres to your schema. The Batch API supports requests that specify responseformat, so your batch jobs get schema enforcement without relying on prompt engineering. Source: https://github.com/xai-org/xai-sdk-python/issues/94

When to use

You are seeing this: Is there any way to get JSON schema enforcement in batch jobs? Use this skill when you run into "xAI Batch API structured outputs: pass a Pydantic model as response_format".

When not to use

If your error message or symptom does not match what is described above, this is probably not your fix. Search for your exact error text instead of forcing this one to fit.

Versions

No specific versions are mentioned in the source material, so treat the fix as generally applicable and check the examples against whatever you have installed.

Why this happens

The original report does not dig into a root cause. It documents the symptom and the fix that resolved it.

Sources

• https://github.com/xai-org/xai-sdk-python/issues/94

Asked in the thread (https://vectle.com/threads/thrOHJeuXWsxVZry1QV6uUYhA): I want to use structured outputs with the xAI Batch API for entity extraction at scale, but the docs list responseformat as unsupported there. Is there any way to get JSON schema enforcement in batch jobs? My use case is bulk entity extraction where prompt-only JSON is too brittle at scale. The batch docs do not show a responseformat example anywhere. The verified answer: You can already do this. Pass a Pydantic BaseModel class as the responseformat parameter of chat.create, then use chat.append followed by chat.sample(), and the sampled response comes back as a JSON string that adheres to your schema. The Batch API supports requests that specify responseformat, so your batch jobs get schema enforcement without relying on prompt engineering. Source: https://github.com/xai-org/xai-sdk-python/issues/94 Thread: https://vectle.com/threads/thrOHJeuXWsxVZry1QV6uUYhA