Grok Community XDK
A community-maintained SDK (Standard Developer Kit) for XAI Grok models supporting usage with the Python Programming Language. This library provides convenient access to the xAI REST API from Python 3.11+ applications, with type definitions for all request parameters and response fields.
Installation
pip install xai-grok
Requirements
- Python 3.11 or higher
- pydantic
- requests
Usage
from xai_grok import Grok
client = Grok(
api_key="your-api-key-here"
)
# Example: Create a chat completion
response = client.chat_completions(
ChatRequest(
messages=[
{"role": "user", "content": "Tell me about AI"}
],
model="model-name-here"
)
)
print(response.choices[0].message.content)
Available Endpoints
API Key Operations
api_key()- Retrieve information about the current API key
Chat and Completion Operations
-
chat_completions(request: ChatRequest)- Create chat completions- Input: ChatRequest object containing messages and model settings
- Throws: InvalidRequestError, IncompleteRequestError
-
complete(request: CompleteRequest)- Generate completions- Input: CompleteRequest object with prompt and settings
- Throws: InvalidRequestError, IncompleteRequestError
-
completions(request: SampleRequest)- Alternative completion endpoint- Input: SampleRequest object
- Throws: InvalidRequestError, IncompleteRequestError
Embedding Operations
-
embedding_model(model_id: str)- Get details of a specific embedding model- Input: Model ID string
- Throws: ModelNotFoundError
-
embedding_models()- List all available embedding models -
embeddings(request: EmbeddingRequest)- Generate embeddings- Input: EmbeddingRequest object
- Throws: InvalidRequestError, IncompleteRequestError
Language Model Operations
-
language_model(model_id: str)- Get details of a specific language model- Input: Model ID string
- Throws: ModelNotFoundError
-
language_models()- List all available language models
Message Operations
messages(request: MessageRequest)- Send messages- Input: MessageRequest object
- Throws: InvalidRequestError, IncompleteRequestError
Model Management
-
models()- List all available models -
model(model_id: str)- Get details of a specific model- Input: Model ID string
- Throws: ModelNotFoundError
Text Operations
tokenize_text(request: TokenizeTextRequest)- Tokenize input text- Input: TokenizeTextRequest object
- Throws: InvalidRequestError
Request and Response Types
All request and response types are Pydantic models, providing type safety and validation. Refer to the schemas module for detailed type definitions.
Base URL
The API uses https://api.x.ai as the base URL for all endpoints.
Authentication
The API requires an authorized API key. Authentication-related errors are handled by specific error types:
NoAPIKeyProvidedError: Raised when no API key is provided in the Authorization headerInvalidAPIKeyProvidedError: Raised when an incorrect API key is provided
To avoid these errors:
- Obtain a valid API key from console.x.ai
- Include it in the client initialization:
client = Grok(api_key="your-api-key-here")
Note on Responses
All responses are parsed into their corresponding Pydantic models, providing
type-safe access to response data. If the API response cannot be parsed into
the expected type, a FailedToParseResponseError will be raised.
Metadata
Release files for xai-grok 0.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| xai_grok-0.0.1.tar.gz | 18.1 kB | Without provenance | Details for xai_grok-0.0.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| xai_grok-0.0.1-py3-none-any.whl | Python 3 | none | any | Details for xai_grok-0.0.1-py3-none-any.whl |
Total release size: 47.6 kB
Release files / xai_grok-0.0.1.tar.gz
| Download URL | xai_grok-0.0.1.tar.gz |
|---|---|
| Size | 18.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
81cf1753abff558b5fbe2e57dcfe66d00479c68ae958bb3a66d1fcaefa8f9794
|
|
BLAKE2b-256 checksum How to use checksums |
63f97298acdc2fd3bcc93338b52f256ac56c7b34d3447fe9fe31e071a62850c5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.6
|
Release files / xai_grok-0.0.1-py3-none-any.whl
| Download URL | xai_grok-0.0.1-py3-none-any.whl |
|---|---|
| Size | 29.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
78eaacdc959bd6b9bb6403f90d70654c97f0f78b7f5fbb2d44c176f415aedfb8
|
|
BLAKE2b-256 checksum How to use checksums |
b5ca24af581d53a1764d5a06e6db1e85f7533f0dee65490913f052000fd29a2f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.6
|
Security for xai-grok 0.0.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.