lmux-azure-foundry

Azure AI Foundry provider for lmux. Uses the openai SDK's AzureOpenAI client.

Supports chat completions, streaming, embeddings, and the Responses API.

Part of the lmux ecosystem: standardized interface, cost tracking on every response, and registry-based routing across providers.

Optional Extras

  • lmux-azure-foundry[identity]: Azure AD token authentication via azure-identity

Auth

Three authentication methods:

API Key (default)

Set AZURE_FOUNDRY_API_KEY in your environment:

from lmux_azure_foundry import AzureFoundryProvider

provider = AzureFoundryProvider(endpoint="https://your-resource.openai.azure.com")

Azure AD Token

from lmux_azure_foundry import AzureFoundryProvider, AzureAdToken

provider = AzureFoundryProvider(
    endpoint="https://your-resource.openai.azure.com",
    auth=my_auth_returning_azure_ad_token,
)

Token Provider

from lmux_azure_foundry import AzureFoundryTokenAuthProvider

provider = AzureFoundryProvider(
    endpoint="https://your-resource.openai.azure.com",
    auth=AzureFoundryTokenAuthProvider(),  # uses azure-identity DefaultAzureCredential
)

Usage

Chat

from lmux import UserMessage

response = provider.chat("gpt-4o", [UserMessage(content="Hello")])
print(response.content)
print(response.cost)

Streaming

for chunk in provider.chat_stream("gpt-4o", [UserMessage(content="Hello")]):
    if chunk.delta:
        print(chunk.delta, end="")

Embeddings

response = provider.embed("text-embedding-3-small", "Hello")
print(response.embeddings)

Responses API

Required for models that are only served through the Responses API:

response = provider.create_response("gpt-5-pro", "Hello")
print(response.output_text)

Async

All methods have async variants: achat, achat_stream, aembed, acreate_response.

Registry

Use with the lmux registry to route across multiple providers:

from lmux import Registry

registry = Registry()
registry.register("azure", provider)
response = registry.chat("azure/gpt-4o", messages)

Provider Params

from lmux_azure_foundry import AzureFoundryParams

response = provider.chat(
    "gpt-4o",
    messages,
    provider_params=AzureFoundryParams(deployment_type="data_zone"),
)
Parameter Type Description
reasoning_effort "low" | "medium" | "high" Reasoning effort for o-series models
seed int Deterministic sampling seed
user str End-user identifier
deployment_type "global" | "data_zone" | "regional" Affects cost calculation only, not sent to API

Constructor Options

AzureFoundryProvider(
    endpoint=...,      # required, Azure resource endpoint
    auth=...,          # AuthProvider, default: AzureFoundryKeyAuthProvider()
    api_version=...,   # API version (default: "2025-04-01-preview")
    timeout=...,       # Request timeout in seconds
    max_retries=...,   # Max retry attempts
)

Project links

Data verified by PyPI on Jun 30, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.10.0)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for cluebbehusen from gravatar.com cluebbehusen

Credits

PyPI data
Data sourced directly from PyPI's database.

Author: Connor Luebbehusen

GitHub Statistics

Data verified by PyPI on Jun 30, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License expression

MIT
View SPDX License List

Requires

Python >=3.13

Provides Extra

identity

Tags

llm ai azure openai language-model

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

lmux_azure_foundry-0.6.1.tar.gz (12.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

lmux_azure_foundry-0.6.1-py3-none-any.whl (15.9 kB view details)

Uploaded Python 3

File details

Details for the file lmux_azure_foundry-0.6.1.tar.gz.

File metadata

  • Download URL: lmux_azure_foundry-0.6.1.tar.gz
  • Upload date:
  • Size: 12.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for lmux_azure_foundry-0.6.1.tar.gz
Algorithm Hash digest
SHA256 f21f51f3ee02f2ccd0fcfde0e848522ded4f4c05d9322c378e35164109b0792e
MD5 ac6cbc738bf4b79a8f4904cf5dc01f79
BLAKE2b-256 fb4713823f71623ef846751f8439c4d0a7a07b25a926fafa205a59b35d0dbe11

See more details on using hashes here.

Provenance

The following attestation bundles were made for lmux_azure_foundry-0.6.1.tar.gz:

Publisher: publish.yml on cluebbehusen/lmux

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file lmux_azure_foundry-0.6.1-py3-none-any.whl.

File metadata

File hashes

Hashes for lmux_azure_foundry-0.6.1-py3-none-any.whl
Algorithm Hash digest
SHA256 0481525dbb2d9ea0b78d0b052867e6f9319bf65fef38ba8298d5960c0572b502
MD5 79f50a0ee216041639749bb4f7f72cb3
BLAKE2b-256 cc122182181aac34f19b515bf4fe118325c930bf4e45c903491f21de061a2e8f

See more details on using hashes here.

Provenance

The following attestation bundles were made for lmux_azure_foundry-0.6.1-py3-none-any.whl:

Publisher: publish.yml on cluebbehusen/lmux

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page