Skip to main content

LLMGateway Python SDK

LLMGateway Logo

A Python SDK for interacting with the LLMGateway API.


Project Status
CI  CI  Pre-commit  Codecov
Meta  Package version  Pydantic Version 2  Ruff

Installation

# using pip
pip install llmgateway-sdk

# using uv
uv pip install llmgateway-sdk

# using poetry
poetry add llmgateway-sdk

Usage

Basic Usage

from llmgateway import LLMGatewayClient, ChatCompletionRequest, Message

# Initialize the client
client = LLMGatewayClient(api_key="your-api-key")

# Create a chat completion request
request = ChatCompletionRequest(
    model="gpt-4",
    messages=[
        Message(role="user", content="Hello!")
    ]
)

# Get a completion
response = client.chat_completions(request)
print(response.message)

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

Async Usage

import asyncio
from llmgateway import LLMGatewayClient, ChatCompletionRequest, Message

async def main():
    client = LLMGatewayClient(api_key="your-api-key")

    request = ChatCompletionRequest(
        model="gpt-4",
        messages=[
            Message(role="user", content="Hello!")
        ]
    )

    # Get a completion asynchronously
    response = await client.achat_completions(request)
    print(response.message)

    # List models asynchronously
    models = await client.alist_models()
    for model in models.data:
        print(f"Model: {model.name} (ID: {model.id})")

    # Don't forget to close the client
    await client.aclose()

asyncio.run(main())

Streaming Responses

from llmgateway import LLMGatewayClient, ChatCompletionRequest, Message

client = LLMGatewayClient(api_key="your-api-key")

request = ChatCompletionRequest(
    model="gpt-4",
    messages=[
        Message(role="user", content="Tell me a story")
    ],
    stream=True
)

# Get streaming responses
for response in client.chat_completions(request):
    print(response.message, end="", flush=True)

Features

  • Synchronous and asynchronous API support
  • Streaming responses
  • Type hints and validation using Pydantic
  • Comprehensive test coverage
  • Modern Python packaging with pyproject.toml

License

MIT License

Metadata

Release files for llmgateway-sdk 0.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for llmgateway-sdk 0.1.1
File Size Uploaded
llmgateway_sdk-0.1.1.tar.gz 8.7 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for llmgateway-sdk 0.1.1
File Interpreter ABI Platform
llmgateway_sdk-0.1.1-py3-none-any.whl Python 3 none any Details

Total release size: 14.6 kB

Release files / llmgateway_sdk-0.1.1.tar.gz

Download URL llmgateway_sdk-0.1.1.tar.gz
Size 8.7 kB
Tags Source
SHA-256 checksum
How to use checksums
180786ac838be563a1d3607033fee98592c2d96f2aa3d37508ef65c7efa644cd
BLAKE2b-256 checksum
How to use checksums
8719c37730132a69deae2eaba95aea29efe1c0c54e2e63728d22e0b3b6a276cc
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jun 10, 2025.

Transparency log

Release files / llmgateway_sdk-0.1.1-py3-none-any.whl

Download URL llmgateway_sdk-0.1.1-py3-none-any.whl
Size 5.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
19308b96110e65ee946e70ecb984f39c031dc5a8f841aad1c921633f0e8aa369
BLAKE2b-256 checksum
How to use checksums
7215b47ad7827a1ccb32167215ecce78cae5ee78a9fe4af0f4e385ad8e116759
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jun 10, 2025.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.1 This release

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page