Xai Models

What's your primary need?
│
├─► Tool calling / Agent workflows
│   └─► grok-4-1-fast ($0.20/$0.50)
│
├─► Complex reasoning / Analysis
│   └─► grok-4 ($3.00/$15.00)
│
├─► General chat / Simple tasks
│   └─► grok-3-fast ($0.20/$0.50)
│
├─► High volume / Cost sensitive
│   └─► grok-3-mini ($0.30/$0.50)
│
└─► Image/Vision tasks
    └─► grok-2-vision ($2.00/$10.00)

# Best choice for X search and sentiment analysis
response = client.chat.completions.create(
    model="grok-4-1-fast",
    messages=[{"role": "user", "content": "Search X for AAPL sentiment"}]
)

# Use for complex multi-step analysis
response = client.chat.completions.create(
    model="grok-4",
    messages=[{"role": "user", "content": "Analyze market trends..."}]
)

# Good default choice for most tasks
response = client.chat.completions.create(
    model="grok-3-fast",
    messages=[{"role": "user", "content": "Summarize this..."}]
)

# Use for bulk processing
response = client.chat.completions.create(
    model="grok-3-mini",
    messages=[{"role": "user", "content": "Classify: ..."}]
)

import base64

# Encode image
with open("chart.png", "rb") as f:
    image_data = base64.b64encode(f.read()).decode()

response = client.chat.completions.create(
    model="grok-2-vision",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Analyze this chart"},
            {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{image_data}"}}
        ]
    }]
)

# For filtering/classification - use mini
filter_response = client.chat.completions.create(
    model="grok-3-mini",
    messages=[{"role": "user", "content": f"Is this relevant? {text}"}]
)

# For analysis - use fast
if is_relevant:
    analysis = client.chat.completions.create(
        model="grok-4-1-fast",
        messages=[{"role": "user", "content": f"Analyze: {text}"}]
    )

# Instead of 10 separate calls, batch them
texts = ["text1", "text2", "text3"]
batch_prompt = "Analyze these texts:\n" + "\n".join(texts)

response = client.chat.completions.create(
    model="grok-3-fast",
    messages=[{"role": "user", "content": batch_prompt}]
)

MODELS = {
    "filter": "grok-3-mini",      # Fast filtering
    "analyze": "grok-4-1-fast",   # Tool calling + analysis
    "deep": "grok-4"              # Complex reasoning (rare)
}

MODELS = {
    "bulk": "grok-3-mini",
    "quality_check": "grok-3-fast"
}

MODELS = {
    "search": "grok-4-1-fast",
    "analyze": "grok-4",
    "summarize": "grok-3-fast"
}

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("XAI_API_KEY"),
    base_url="https://api.x.ai/v1"
)

# List available models
models = client.models.list()
for model in models.data:
    print(f"{model.id}")

# Use specific model
response = client.chat.completions.create(
    model="grok-4-1-fast",
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=100
)