Setup
export XAI_API_KEY="xai-..."
Basic Usage
from definable.models import xAI
model = xAI(id="grok-beta")
response = model.invoke(messages=[{"role": "user", "content": "Hello!"}])
print(response.content)
Parameters
Model identifier. Common values: grok-beta, grok-2.
xAI API key. Defaults to the XAI_API_KEY environment variable.
base_url
str
default:"https://api.x.ai/v1"
xAI API base URL.
Configuration for Grok’s live search capabilities.
Live Search
xAI Grok models can search the web for real-time information:
model = xAI(
id="grok-beta",
search_parameters={"mode": "auto"},
)
response = model.invoke(
messages=[{"role": "user", "content": "What happened in tech news today?"}]
)
print(response.content)
# Access citations if available
if response.citations:
for url in response.citations.urls:
print(f" Source: {url.url} - {url.title}")
Streaming
for chunk in model.invoke_stream(
messages=[{"role": "user", "content": "Explain the latest AI developments."}]
):
if chunk.content:
print(chunk.content, end="", flush=True)
Async Usage
response = await model.ainvoke(
messages=[{"role": "user", "content": "Hello!"}]
)
xAI uses an OpenAI-compatible API with extensions for live search. Citations are returned in the response when search is enabled.
