azureml-inference-server-http
Azure Machine Learning inferencing server.
Decision gist · record as of 2026-08-14
Yes, if you are deploying models through Azure ML and need a standardized, Microsoft-supported HTTP server for inference. The package is actively maintained with recent dependency upgrades (Pydantic 2.12 in version 1.5.1) and has no known security vulnerabilities. The aging maintenance status reflects a stable, mature codebase rather than abandonment. However, review the unclear proprietary license terms before use, and ensure your scoring scripts are compatible with Flask 2.x and Pydantic 2.0+.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.9 or later; Python 3.8 support was dropped in version 1.4.0.
- Pydantic 2.0+ is required as of version 1.1.0, which is a breaking change from Pydantic 1.x.
- Low install friction with a pure-Python wheel.
License · maintenance · safety
(unclear) — License treatment is unclear; the raw license URL points to a Microsoft proprietary license at https://aka.ms/azureml-sdk-license with no SPDX identifier. Review Microsoft's terms before use in proprietary or open-source contexts.
last release 2025-12-18 (239 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 181,485 downloads/mo, #10,126 on PyPI
Alternatives
Verify before relying
pip install azureml-inference-server-http
from azureml_inference_server_http.server import Server
from inference_schema.schema_decorators import input_schema, output_schema
# Define your score function with decorators
@input_schema('data', ...)
@output_schema(...)
def score(data):
return prediction
# Server loads and runs the scoring script- Whether the package works with custom Flask 2.x request handling beyond the documented compatibility layer removal
- Performance characteristics and throughput limits under production load
- Whether OpenTelemetry integration requires additional Azure Monitor configuration beyond the exporter dependency
What it is and what it does
Azure Machine Learning Inference HTTP Server is a Flask-based HTTP server designed to host and serve machine learning models deployed through Azure ML. It wraps user-defined scoring scripts (Python functions decorated with input/output schemas) and exposes them as HTTP endpoints, handling request routing, response formatting, and error management. The server includes built-in observability through OpenTelemetry and Azure Monitor integration, allowing operators to collect metrics, traces, and logs for production monitoring.
The package abstracts away much of the HTTP server boilerplate, letting data scientists focus on the scoring logic while the server handles Flask configuration, CORS, health checks, and request/response validation. It supports both gunicorn (Linux/macOS) and waitress (Windows) as WSGI servers and includes features like configurable health check ports and JSON-based server configuration through environment variables.
Use it for
- Deploy a trained scikit-learn or TensorFlow model as a production HTTP endpoint in Azure ML with automatic request validation and response formatting.
- Monitor inference latency and error rates in production by leveraging built-in OpenTelemetry metrics and Azure Monitor export.
- Host a batch of related scoring functions (e.g., preprocessing, model inference, postprocessing) as separate endpoints on a single server instance.
- Migrate existing Flask-based scoring scripts to Azure ML without rewriting the core logic, using the server's Flask compatibility layer.
- Configure separate health check and inference ports to isolate monitoring traffic from production scoring requests.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are deploying models through Azure ML and need a standardized, Microsoft-supported HTTP server for inference.
The package is actively maintained with recent dependency upgrades (Pydantic 2.12 in version 1.5.1) and has no known security vulnerabilities. The aging maintenance status reflects a stable, mature codebase rather than abandonment. However, review the unclear proprietary license terms before use, and ensure your scoring scripts are compatible with Flask 2.x and Pydantic 2.0+.
Install
azureml-inference-server-http on PyPI
Before you install
Low install friction with a pure-Python wheel. Maintenance status is aging (239 days since last release), though the package receives periodic updates for dependency upgrades and security patches.
Requires Python 3.9 or later; Python 3.8 support was dropped in version 1.4.0. Pydantic 2.0+ is required as of version 1.1.0, which is a breaking change from Pydantic 1.x.
License in practice
License treatment is unclear; the raw license URL points to a Microsoft proprietary license at https://aka.ms/azureml-sdk-license with no SPDX identifier. Review Microsoft's terms before use in proprietary or open-source contexts.
Quickstart
pip install azureml-inference-server-http
from azureml_inference_server_http.server import Server
from inference_schema.schema_decorators import input_schema, output_schema
# Define your score function with decorators
@input_schema('data', ...)
@output_schema(...)
def score(data):
return prediction
# Server loads and runs the scoring scriptVerify before relying
- Whether the package works with custom Flask 2.x request handling beyond the documented compatibility layer removal
- Performance characteristics and throughput limits under production load
- Whether OpenTelemetry integration requires additional Azure Monitor configuration beyond the exporter dependency
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release >=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 14 packagesflaskflask-corsgunicorninference-schemaopentelemetry-sdkopentelemetry-apiopentelemetry-semantic-conventionsazure-monitor-opentelemetry-exporterpsutilpydanticpydantic-settingswaitresswerkzeugcertifi |
| Maintenance | Aging 239 days since the last release |
| First released | |
| Downloads | 181,485 / month, #10,126 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Intended Audience :: DevelopersIntended Audience :: Science/ResearchLicense :: Other/Proprietary LicenseOperating System :: MacOSOperating System :: Microsoft :: WindowsOperating System :: POSIX :: LinuxProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.9 |
Evidence: azureml_inference_server_http-1.5.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “azure ml model serving”
- azureml-inference-server-httpProvides an HTTP server for serving Azure Machine Learning models…
- kserveKServe Python SDK provides server and client libraries for deploying…
- bentomlBentoML is a Python framework for building and deploying REST APIs…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also azureml-contrib-services · azureml-mlflow · azureml-train-restclients-hyperdrive · azureml-ai-monitoring · azureml-defaults · azureml-train · azureml · azure-ml-component · azureml-fsspec · kserve