xAI (Grok)

Overview

xAI is an AI company founded by Elon Musk, offering the Grok model family with real-time knowledge access and strong reasoning capabilities.

Official Website: https://x.ai API Documentation: https://docs.x.ai

Key features

Chat — Text generation with function calling and streaming
Reasoning — Extended thinking for complex problems
Vision — Image analysis and understanding
Web search — Access to current information
Structured output — JSON and schema-constrained responses
Image generation — Text-to-image
Embeddings & batch — Text embeddings and asynchronous batch processing

Address Grok models using the provider/model convention by prefixing with xai/ (for example, xai/grok-beta). Requests use the same Yunxin base URL (https://api.yuhuanstudio.com/v1) and your Yunxin sk- API key.

Usage example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["YUNXIN_API_KEY"],
    base_url="https://api.yuhuanstudio.com/v1"
)

response = client.chat.completions.create(
    model="xai/grok-beta",
    messages=[{"role": "user", "content": "What's the latest news?"}]
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.YUNXIN_API_KEY,
  baseURL: "https://api.yuhuanstudio.com/v1",
});

const response = await client.chat.completions.create({
  model: "xai/grok-beta",
  messages: [{ role: "user", content: "What's the latest news?" }],
});

console.log(response.choices[0].message.content);

curl https://api.yuhuanstudio.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YUNXIN_API_KEY" \
  -d '{
    "model": "xai/grok-beta",
    "messages": [{"role": "user", "content": "What'"'"'s the latest news?"}]
  }'

Available models

Query the live catalog with the Models API:

curl "https://api.yuhuanstudio.com/v1/models?provider=xai" \
  -H "Authorization: Bearer $YUNXIN_API_KEY"

Capabilities and pricing are tracked per model. Use GET /v1/models?provider=xai and each model's capabilities array as the authoritative source rather than relying on a hardcoded list.

Chat — Text generation with function calling and streaming
Reasoning — Extended thinking for complex problems
Vision — Image analysis and understanding
Web search — Access to current information
Structured output — JSON and schema-constrained responses
Image generation — Text-to-image
Embeddings & batch — Text embeddings and asynchronous batch processing

Using xAI with Yunxin

Usage example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["YUNXIN_API_KEY"],
    base_url="https://api.yuhuanstudio.com/v1"
)

response = client.chat.completions.create(
    model="xai/grok-beta",
    messages=[{"role": "user", "content": "What's the latest news?"}]
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.YUNXIN_API_KEY,
  baseURL: "https://api.yuhuanstudio.com/v1",
});

const response = await client.chat.completions.create({
  model: "xai/grok-beta",
  messages: [{ role: "user", content: "What's the latest news?" }],
});

console.log(response.choices[0].message.content);

curl https://api.yuhuanstudio.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YUNXIN_API_KEY" \
  -d '{
    "model": "xai/grok-beta",
    "messages": [{"role": "user", "content": "What'"'"'s the latest news?"}]
  }'

Available models

Query the live catalog with the Models API:

curl "https://api.yuhuanstudio.com/v1/models?provider=xai" \
  -H "Authorization: Bearer $YUNXIN_API_KEY"

Capabilities and pricing are tracked per model. Use GET /v1/models?provider=xai and each model's capabilities array as the authoritative source rather than relying on a hardcoded list.

Overview

Key features

Using xAI with Yunxin

Usage example

Available models

Official resources

On this page

xAI (Grok)

Overview

Key features

Using xAI with Yunxin

Usage example

Available models

Official resources

On this page