[FR] Add OpenAI-compatible `GET /v1/models` for MLflow Gateway endpoints

[!WARNING] Before submitting a PR, please make sure that:

• A maintainer has triaged this issue and applied the ready label
• This issue has no assignee
• No duplicate PR exists

PRs not meeting these requirements may be automatically closed.

Willingness to contribute

Yes. I can contribute this feature independently.

Proposal Summary

MLflow Gateway already exposes OpenAI-compatible inference routes such as POST /v1/chat/completions, but it does not expose the corresponding OpenAI-style model discovery endpoint, GET /v1/models.

This creates a compatibility gap for OpenAI-compatible clients and tools that expect both inference APIs and a model-listing API.

Motivation

In some OpenAI-compatible integrations, support for chat or responses APIs alone is not sufficient. Some clients, SDK wrappers, agent frameworks, gateways, and developer tools also call GET /v1/models to discover available models, validate configuration, or populate model selectors.

Today, an MLflow Gateway endpoint can be invoked via the OpenAI-compatible API, but clients that also require /v1/models may fail to initialize or require MLflow-specific workarounds.

Details

Add an OpenAI-compatible GET /v1/models endpoint for MLflow Gateway so that newly created endpoints can be discovered in a standard way, not only invoked.

This would make MLflow Gateway more interoperable with the broader OpenAI-compatible ecosystem.

If this is a feature the maintainers would be open to supporting, I’d be happy to contribute a PR.

What machine learning domain(s) is this feature request about?

• domain/genai: LLMs, Agents, and other GenAI-related use cases
• domain/classical-ml: Traditional machine learning, such as linear regression.
• domain/deep-learning: Deep learning and neural networks.
• domain/platform: MLflow platform foundation, not specific to a particular machine learning domain.

What area(s) of MLflow is this feature request about?

• area/tracking: Tracking Service, tracking client APIs, autologging
• area/model-registry: Model Registry service, APIs, and the fluent client calls for Model Registry
• area/scoring: MLflow model serving, deployment tools, Spark UDFs
• area/evaluation: MLflow model evaluation features, evaluation metrics, and evaluation workflows
• area/prompt: MLflow prompt engineering features, prompt templates, and prompt management
• area/tracing: MLflow Tracing features, tracing APIs, and LLM tracing functionality
• area/gateway: MLflow AI Gateway client APIs, server, and third-party integrations
• area/projects: MLproject format, project running backends
• area/uiux: Front-end, user experience, plotting
• area/docs: MLflow documentation pages