Scope adding openai compatible providers via json

[ishaan-jaff]

Title

Scope: Simplify OpenAI-Compatible Provider Onboarding via JSON Configuration

Relevant issues

N/A

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement - see details
• I have added a screenshot of my new test passing locally
• My PR passes all unit tests on make test-unit
• My PR's scope is as isolated as possible, it only solves 1 specific problem

Type

🆕 New Feature

Changes

This PR introduces a comprehensive scoping document (SCOPE_OPENAI_COMPATIBLE_JSON_CONFIG.md) outlining a plan to simplify the addition of OpenAI-compatible providers.

Why:
The current process for integrating new OpenAI-compatible providers is complex, requiring modifications across 9+ Python files and significant boilerplate code. This creates a high barrier to entry for contributors and increases maintenance overhead.

What:
The proposed solution enables configuring simple OpenAI-compatible providers via a single JSON file (litellm/openai_compatible_providers.json). The document details the JSON schema, a phased implementation plan (including a dynamic config loader and class generator), and a migration strategy for existing providers.

Benefits:

• For Contributors: Reduces the number of files to edit from 9+ to 1, eliminates the need for Python code for simple providers, and drastically cuts down the time required for onboarding.
• For Maintainers: Simplifies PR reviews, ensures consistent provider patterns, and reduces the overall maintenance burden.
• For the Community: Fosters faster integration of new providers and encourages more contributions.

---

Slack Thread

 

[cursor]

Cursor Agent can help with this pull request. Just @cursor in comments and I'll start working on changes in this branch.
_{Learn more about Cursor Agents}

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Preview	Comments	Updated (UTC)
litellm	Ready	Preview	Comment	Dec 4, 2025 2:21am

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[krrishdholakia]

why do this? @ishaan-jaff - shouldn't it just send what's in supported?