xAI | liteLLM (original) (raw)

https://docs.x.ai/docs

tip

We support ALL xAI models, just set model=xai/<any-model-on-xai> as a prefix when sending litellm requests

Supported Models​

Latest Release - Grok 4.1 Fast: Optimized for high-performance agentic tool calling with 2M context and prompt caching.

When to use:

• ✅ Reasoning model: Complex analysis, planning, multi-step reasoning problems
• ✅ Non-reasoning model: Simple queries, faster responses, lower token usage

Example:

from litellm import completion

# With reasoning
response = completion(
    model="xai/grok-4-1-fast-reasoning",
    messages=[{"role": "user", "content": "Analyze this problem step by step..."}]
)

# Without reasoning
response = completion(
    model="xai/grok-4-1-fast-non-reasoning",
    messages=[{"role": "user", "content": "What's 2+2?"}]
)

All Available Models​

Features:

• Reasoning = Chain-of-thought reasoning with reasoning tokens
• Tools = Function calling / Tool use
• Web search = Live internet search
• Vision = Image understanding
• Audio = Audio input support
• Caching = Prompt caching for cost savings
• Code generation = Optimized for code tasks

Pricing: See xAI's pricing page for current rates.

API Key​

# env variable
os.environ['XAI_API_KEY']

Sample Usage​

LiteLLM python sdk usage - Non-streaming

from litellm import completion
import os

os.environ['XAI_API_KEY'] = ""
response = completion(
    model="xai/grok-3-mini-beta",
    messages=[
        {
            "role": "user",
            "content": "What's the weather like in Boston today in Fahrenheit?",
        }
    ],
    max_tokens=10,
    response_format={ "type": "json_object" },
    seed=123,
    stop=["\n\n"],
    temperature=0.2,
    top_p=0.9,
    tool_choice="auto",
    tools=[],
    user="user",
)
print(response)

Sample Usage - Streaming​

LiteLLM python sdk usage - Streaming

from litellm import completion
import os

os.environ['XAI_API_KEY'] = ""
response = completion(
    model="xai/grok-3-mini-beta",
    messages=[
        {
            "role": "user",
            "content": "What's the weather like in Boston today in Fahrenheit?",
        }
    ],
    stream=True,
    max_tokens=10,
    response_format={ "type": "json_object" },
    seed=123,
    stop=["\n\n"],
    temperature=0.2,
    top_p=0.9,
    tool_choice="auto",
    tools=[],
    user="user",
)

for chunk in response:
    print(chunk)

Sample Usage - Vision​

LiteLLM python sdk usage - Vision

import os 
from litellm import completion

os.environ["XAI_API_KEY"] = "your-api-key"

response = completion(
    model="xai/grok-2-vision-latest",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://science.nasa.gov/wp-content/uploads/2023/09/web-first-images-release.png",
                        "detail": "high",
                    },
                },
                {
                    "type": "text",
                    "text": "What's in this image?",
                },
            ],
        },
    ],
)

Usage with LiteLLM Proxy Server​

Here's how to call a XAI model with the LiteLLM Proxy Server

1. Modify the config.yaml

model_list:
  - model_name: my-model
    litellm_params:
      model: xai/<your-model-name>  # add xai/ prefix to route as XAI provider
      api_key: api-key                 # api key to send your model

1. Start the proxy

$ litellm --config /path/to/config.yaml

1. Send Request to LiteLLM Proxy Server

• OpenAI Python v1.0.0+
• curl

import openai
client = openai.OpenAI(
    api_key="sk-1234",             # pass litellm proxy key, if you're using virtual keys
    base_url="http://0.0.0.0:4000" # litellm-proxy-base url
)

response = client.chat.completions.create(
    model="my-model",
    messages = [
        {
            "role": "user",
            "content": "what llm are you"
        }
    ],
)

print(response)

Reasoning Usage​

LiteLLM supports reasoning usage for xAI models.

• LiteLLM Python SDK
• LiteLLM Proxy - OpenAI SDK Usage

reasoning with xai/grok-3-mini-beta

import litellm
response = litellm.completion(
    model="xai/grok-3-mini-beta",
    messages=[{"role": "user", "content": "What is 101*3?"}],
    reasoning_effort="low",
)

print("Reasoning Content:")
print(response.choices[0].message.reasoning_content)

print("\nFinal Response:")
print(completion.choices[0].message.content)

print("\nNumber of completion tokens (input):")
print(completion.usage.completion_tokens)

print("\nNumber of reasoning tokens (input):")
print(completion.usage.completion_tokens_details.reasoning_tokens)

Example Response:

Reasoning Content:
Let me calculate 101 multiplied by 3:
101 * 3 = 303.
I can double-check that: 100 * 3 is 300, and 1 * 3 is 3, so 300 + 3 = 303. Yes, that's correct.

Final Response:
The result of 101 multiplied by 3 is 303.

Number of completion tokens (input):
14

Number of reasoning tokens (input):
310