Skip to content

Conversation

@massaindustries
Copy link

Add Regolo.ai provider and models

This PR adds Regolo.ai as a new provider to models.dev, including provider metadata, logo, and the full set of currently available models.

Regolo.ai is a European AI inference platform focused on privacy-first, low-latency, and OpenAI-compatible APIs, designed for production use in regulated and enterprise environments.
All inference is hosted in EU datacenters, with no training on customer data and full data isolation by design.

Provider details

  • Name: Regolo.ai
  • API compatibility: OpenAI-compatible (/v1/chat/completions, embeddings, vision, speech, etc.)
  • Target users: developers, enterprises, public sector, research
  • Hosting: EU-only infrastructure
  • Data policy: no data retention for training, no cross-tenant leakage

Official links:

What’s included in this PR

  • provider.toml for regolo

  • logo.svg (monochrome, currentColor, SVG)

  • Model definitions (.toml) for:

    • Large language models (general, coding, multilingual)
    • Vision-language models

Each model TOML specifies:

  • context length , output limits, prices
  • supported capabilities (text, vision, etc.)

Notes

  • The provider is intentionally implemented as OpenAI-compatible to ensure seamless adoption across the AI SDK ecosystem (including OpenCode).
  • No custom authentication or nonstandard headers are required.
  • Capabilities declared in the model files reflect actual API behavior.

If additional metadata or validation changes are required, I’m happy to iterate quickly.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant