Add support for Nscale (EU-Sovereign) Provider

[tomukmatthews]

Adds support for Nscale (EU Sovereign) Provider.

NScale docs

NScale is a European-domiciled full-stack AI cloud platform that allows you to scale your workloads securely, sustainably and cost-effectively - without sacrificing control. It provides production-grade reliability for serverless deployments of LLMs with full data sovereignty and compliance baked in.

Key Features

• EU Sovereign: Full data sovereignty and compliance with European regulations
• Ultra-Low Cost (starting at $0.01 / M tokens): Extremely competitive pricing for both text and image generation models
• Production Grade: Reliable serverless deployments with full isolation
• No Setup Required: Instant access to compute without infrastructure management
• Full Control: Your data remains private and isolated

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
📖 Documentation
✅ Test

Changes

• Adds support for Nscale (text and image generation) via openai compliant API
• Adds documentation for the new provider
• Adds unit tests
• Small improvement to move a test asset from a module to a pytest fixture in a root conftest.py (doing this resolved a issues with running the actual unit tests).

[vercel]

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

Name	Status	Preview	Comments	Updated (UTC)
litellm	🛑 Canceled (Inspect)			May 8, 2025 3:44pm

[CLAassistant]

All committers have signed the CLA.

[tomukmatthews]

Tagging @ishaan-jaff and @krrishdholakia for review please!

[ishaan-jaff]

reviewed

[ishaan-jaff]

request to not make any changes around large text etc

[tomukmatthews]

Waiting to update these until i hear back from the team on the latest openai params supported

[ishaan-jaff]

LGTM