xAI Grok

OverviewCopy Anchor Link

xAI's Grok models.

• GrokLLMService: an OpenAILLMService subclass with xAI Grok's base URL and default model.

InstallationCopy Anchor Link

bun add @pipedog/xai

It depends on @pipedog/openai, which is installed with it.

import { GrokLLMService } from "@pipedog/xai/llm";

PrerequisitesCopy Anchor Link

• An xAI account and an API key from the xAI console.
• Pass the key as apiKey. It is required, and the service never falls back to OPENAI_API_KEY. The examples read it from XAI_API_KEY.

GrokLLMServiceCopy Anchor Link

ConfigurationCopy Anchor Link

The other options (organization, project, defaultHeaders, serviceTier, retryOnTimeout, retryTimeoutSecs, function calling) are OpenAILLMService's. See OpenAI.

SettingsCopy Anchor Link

Runtime-updatable settings, passed as settings: new GrokLLMService.Settings({...}) (GrokLLMSettings). They are OpenAI's settings, with these defaults:

Every other setting keeps OpenAI's default. Unset sampling settings are left out of the request, so the provider's own defaults apply. extra carries provider-specific request fields.

UsageCopy Anchor Link

import { LLMUpdateSettingsFrame } from "@pipedog/core/frames/frames";
import { GrokLLMService } from "@pipedog/xai/llm";

const llm = new GrokLLMService({
  apiKey: process.env.XAI_API_KEY ?? "",
  settings: new GrokLLMService.Settings({
    model: "grok-4.20-non-reasoning",
    systemInstruction: "You are a helpful assistant in a voice conversation.",
    temperature: 0.7,
  }),
});

A reasoning model, with its reasoning effort:

const reasoning = new GrokLLMService({
  apiKey: process.env.XAI_API_KEY ?? "",
  settings: new GrokLLMService.Settings({ model: "grok-4.6", reasoningEffort: "low" }),
});

Change settings mid-call with an LLMUpdateSettingsFrame. The next completion uses them:

// Queue it on the worker, or push it from a processor upstream of the service.
const update = new LLMUpdateSettingsFrame({
  delta: new GrokLLMService.Settings({ temperature: 0.2, maxTokens: 300 }),
});

NotesCopy Anchor Link

• Runs a completion for each LLMContextFrame, between an LLMFullResponseStartFrame and an LLMFullResponseEndFrame, and streams the reply as LLMTextFrames, as OpenAILLMService does. Function calls, token usage metrics and runInference work the same way.
• "developer" messages are sent as is: the API supports that role.
• xAI reports reasoning tokens apart from completion_tokens, so they are added to the completion count in token usage metrics when the total says so.
• @pipedog/grok re-exports GrokLLMService from @pipedog/xai/llm, as upstream's deprecated pipecat.services.grok.llm does. Import from @pipedog/xai/llm.
• The same package has xAI's speech-to-text and text-to-speech services, and Grok Voice Agent, the realtime (speech-to-speech) service.

Runtime notesCopy Anchor Link

Generated from pipecat.runtimes and pipecat.compat in packages/xai/package.json: ✅ means the compat smoke test passes on that runtime.

• The client is the official openai JS SDK (through @pipedog/openai), which talks through fetch. It works on Bun, Node, Deno and Cloudflare Workers.
• The deprecated model constructor option is not ported. Use settings.
• Tested against a local OpenAI-compatible mock server, not against xAI Grok itself.