xAI

xai

Aliases: grok

YAML config

providers:
  - id: xai:grok-2
    config:
      apiKey: ${XAI_API_KEY}

TypeScript usage

import { createProvider } from "@evalguard/core";

const provider = createProvider("xai", process.env.XAI_API_KEY);
const response = await provider.complete({
  model: "grok-2",
  messages: [{ role: "user", content: "Hello" }],
});

Authentication

Set XAI_API_KEY in your environment. EvalGuard validates the key on first call and surfaces typed errors for 401 / 403 / rate-limit responses (with Retry-After parsing).

Setup walkthrough

  1. 1. Sign up for an account on the xAI platform.
  2. 2. Obtain your API key from the dashboard after logging in.
  3. 3. Review the API documentation to understand the endpoints and usage.
  4. 4. Set up your development environment with the necessary libraries for API calls.
  5. 5. Make a test API call to ensure your setup is working correctly.

Gotchas

  • Rate limits are strict; exceeding them may result in temporary access restrictions.
  • Some features may not be available in certain regions due to compliance issues.
  • The API may return different results based on the model version used, so ensure consistency in your calls.

Cost note

Pricing is $0.01 per 1,000 tokens for the cheapest model and $0.06 per 1,000 tokens for the flagship model.

Recommended models

Eval / judge
xai-gpt-3.5-turbo
Agent / tool-use
xai-grok-2.0
Code
xai-codex-1.0
Vision
xai-vision-1.0

LLM-generated (llm-gpt-4o) · 2026-05-23