Feature Request: Add v1beta compatibility for Gemini API

[h2cone]

First, thank you to the Plano maintainers and contributors for building and open-sourcing this project. The existing unified endpoint and routing design is already very useful in practice.

Summary

According to Gemini API version docs, the API has both v1 (stable) and v1beta (early features), and Gemini SDKs default to v1beta unless api_version is explicitly changed.

To improve drop-in compatibility, Plano should perhaps support these Gemini v1beta routes:

• POST /v1beta/models/{model}:generateContent
• POST /v1beta/models/{model}:streamGenerateContent

These requests should be translated into Plano’s existing routing/provider pipeline so existing Gemini clients can use Plano with little to no request-format changes.

Current behavior

A request like:

POST /v1beta/models/gemini-2.5-flash:generateContent

returns 404 Not Found from Plano 0.4.9, even when Gemini model providers are configured.

Expected behavior

When a Gemini provider is configured, Plano should accept the above v1beta endpoints and return normal Gemini-compatible responses.

Why prioritize v1beta

1. SDK alignment: Gemini SDKs default to v1beta, so this is the most common client path.
2. Lower migration cost: Existing Gemini apps can switch to Plano without endpoint rewrites.
3. Additive compatibility: This complements Plano’s unified endpoints rather than replacing them.

[adilhafeez]

Thanks for the feature request! This is a non-trivial change — the native Gemini API uses a completely different request/response format from OpenAI, so supporting it requires bidirectional translation across multiple layers of the stack (similar in scope to how we added Anthropic Messages API support).

Gemini already works through Plano today via the OpenAI-compatible endpoint. Plano automatically routes /v1/chat/completions to Gemini's /v1beta/openai/chat/completions when a Gemini provider is configured.

Any OpenAI-compatible client can use Gemini models through Plano without issues.

We'll keep native Gemini SDK support on our radar for a future release.