xAI

Access 13 xAI models through Mastra's model router. Authentication is handled automatically using the XAI_API_KEY environment variable.

Learn more in the xAI documentation.

.env

XAI_API_KEY=your-api-key

src/mastra/agents/my-agent.ts

import { Agent } from "@mastra/core/agent";

const agent = new Agent({
  id: "my-agent",
  name: "My Agent",
  instructions: "You are a helpful assistant",
  model: "xai/grok-4.20-0309-non-reasoning"
});

// Generate a response
const response = await agent.generate("Hello!");

// Stream a response
const stream = await agent.stream("Tell me a story");
for await (const chunk of stream) {
  console.log(chunk);
}

Models

12 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
xai/grok-4.20-0309-non-reasoning	1.0M						$1	$3
xai/grok-4.20-0309-reasoning	1.0M						$1	$3
xai/grok-4.20-multi-agent-0309	1.0M						$1	$3
xai/grok-4.3	1.0M						$1	$3
xai/grok-4.5	500K						$2	$6
xai/grok-4.6	500K						$2	$6
xai/grok-4.7	500K						$2	$6
xai/grok-build-0.1	256K						$1	$2
xai/grok-imagine-image	16K						—	—
xai/grok-imagine-video	1K						—	—
xai/grok-imagine-video-1.5	1K						—	—
xai/grok-imagine-video-1.5-lite	1K						—	—

Model availability, capabilities, context windows, and pricing are sourced from models.dev and may change.

Advanced configuration

Custom headers

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    id: "xai/grok-4.20-0309-non-reasoning",
    apiKey: process.env.XAI_API_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});

Dynamic model selection

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "dynamic-agent",
  name: "Dynamic Agent",
  model: ({ requestContext }) => {
    const useAdvanced = requestContext.task === "complex";
    return useAdvanced
      ? "xai/grok-imagine-video-1.5-lite"
      : "xai/grok-4.20-0309-non-reasoning";
  }
});

Provider Options

xAI supports the following provider-specific options via the providerOptions parameter:

const response = await agent.generate("Hello!", {
  providerOptions: {
    xai: {
      // See available options in the table below
    }
  }
});

Available Options

reasoningEffort?:

"none" | "low" | "medium" | "high" | undefined

logprobs?:

boolean | undefined

topLogprobs?:

number | undefined

parallel_function_calling?:

boolean | undefined

searchParameters?:

{ mode: "off" | "auto" | "on"; returnCitations?: boolean | undefined; fromDate?: string | undefined; toDate?: string | undefined; maxSearchResults?: number | undefined; sources?: ({ ...; } | ... 2 more ... | { ...; })[] | undefined; } | undefined