xAI (Grok)

The xAI plugin provides AI text generation and vision analysis using xAI’s Grok models.

Features

Feature	Provider	Description
Text Generation	Grok	Generate text with structured JSON output support
Vision Analysis	Grok Vision	Analyze images and extract information

Installation

pnpm add @teamflojo/floimg-xai

API Key

Get your API key from xAI Console.

export XAI_API_KEY=your-api-key

All providers support per-request API keys via the apiKey parameter, allowing users to provide their own keys.

---

Grok Text

Generate text using Grok with optional structured JSON output.

Registration

import createClient from '@teamflojo/floimg';
import { grokText } from '@teamflojo/floimg-xai';

const floimg = createClient();
floimg.registerTextProvider(grokText());

Usage

// Simple text generation
const result = await floimg.generateText({
  provider: 'grok-text',
  params: {
    prompt: 'Write 3 creative image prompts for a cyberpunk cityscape',
  }
});

console.log(result.content);

Structured JSON Output

// Generate structured JSON
const result = await floimg.generateText({
  provider: 'grok-text',
  params: {
    prompt: 'Generate image prompts for a tech product launch',
    outputFormat: 'json',
    jsonSchema: {
      type: 'object',
      properties: {
        prompts: {
          type: 'array',
          items: { type: 'string' }
        },
        style: { type: 'string' },
        mood: { type: 'string' }
      }
    }
  }
});

console.log(result.parsed); // Typed JSON object

Parameters

Parameter	Type	Required	Description
prompt	string	Yes	Text prompt for generation
systemPrompt	string	No	System prompt to guide behavior
context	string	No	Additional context
outputFormat	'text' | 'json'	No	Output format (default: 'text')
jsonSchema	object	No	JSON schema for structured output
temperature	number	No	Creativity (0-2, default: 0.7)
maxTokens	number	No	Max response tokens (default: 1000)
model	string	No	Model name (default: grok-2)
apiKey	string	No	Per-request API key override

Models

Model	Description
grok-2	Latest Grok 2 model (default)
grok-3-beta	Grok 3 beta

---

Grok Vision

Analyze images using Grok’s vision capabilities.

Registration

import createClient from '@teamflojo/floimg';
import { grokVision } from '@teamflojo/floimg-xai';

const floimg = createClient();
floimg.registerVisionProvider(grokVision());

Usage

// Analyze an image
const result = await floimg.analyzeImage({
  provider: 'grok-vision',
  blob: imageBlob,
  params: {
    prompt: 'What objects are in this image? Describe the scene.',
  }
});

console.log(result.content);

Structured Output

// Get structured analysis
const result = await floimg.analyzeImage({
  provider: 'grok-vision',
  blob: imageBlob,
  params: {
    prompt: 'Analyze this image for content moderation',
    outputFormat: 'json',
    jsonSchema: {
      type: 'object',
      properties: {
        objects: { type: 'array', items: { type: 'string' } },
        people: { type: 'number' },
        setting: { type: 'string' },
        mood: { type: 'string' },
        safeForWork: { type: 'boolean' }
      }
    }
  }
});

console.log(result.parsed.safeForWork);

Parameters

Parameter	Type	Required	Description
prompt	string	No	What to analyze (default: “Describe this image”)
outputFormat	'text' | 'json'	No	Output format (default: 'text')
jsonSchema	object	No	JSON schema for structured output
maxTokens	number	No	Max response tokens (default: 1000)
model	string	No	Model name (default: grok-2-vision)
apiKey	string	No	Per-request API key override

Models

Model	Description
grok-2-vision	Grok 2 with vision (default)

---

Complete Pipeline Example

Combine Grok text and vision in a workflow:

import createClient from '@teamflojo/floimg';
import { grokText, grokVision } from '@teamflojo/floimg-xai';

const floimg = createClient();
floimg.registerTextProvider(grokText());
floimg.registerVisionProvider(grokVision());

// 1. Analyze the input image
const analysis = await floimg.analyzeImage({
  provider: 'grok-vision',
  blob: inputImage,
  params: {
    prompt: 'Describe this image in detail, including mood and style',
  }
});

// 2. Generate enhancement suggestions based on analysis
const suggestions = await floimg.generateText({
  provider: 'grok-text',
  params: {
    prompt: 'Based on this image description, suggest 3 creative variations',
    context: analysis.content,
    outputFormat: 'json',
    jsonSchema: {
      type: 'object',
      properties: {
        variations: {
          type: 'array',
          items: {
            type: 'object',
            properties: {
              name: { type: 'string' },
              prompt: { type: 'string' },
              style: { type: 'string' }
            }
          }
        }
      }
    }
  }
});

console.log(suggestions.parsed.variations);

API Compatibility

The xAI API is OpenAI-compatible. Under the hood, the plugin uses the OpenAI SDK with xAI’s base URL (https://api.x.ai/v1).

See Also

• Google AI (Gemini) - Gemini text, vision, and image editing
• OpenAI - GPT and DALL-E
• CLI AI Commands - Command-line AI tools
• Studio AI Nodes - Visual workflow AI nodes