Cannot add Gemini models as remote provider.

[jarodise]

Checks

• I have searched existing issues and discussions
• I can reproduce this with the latest main or release

Describe the bug

tried multiple times to add Google's Gemini models as remote provider, didn't work.

Steps to reproduce

No response

Osaurus version / commit

No response

macOS version

No response

Apple Silicon chip

No response

Xcode version

No response

Logs

Screenshots

No response

[tpae]

hey @jarodise , we're currently supporting OpenAI API format. Are you requesting gemini API format or gemini proxy?

[unstatusthequo]

Love the application, @tpae. Would love to see support for Athropic and Gemini APIs directly. in the meantime, @jarodise this may help:

Run a local OpenAI-compatible proxy in front of Anthropic, then point Osaurus "Custom" provider to that proxy

Use LiteLLM Proxy locally. LiteLLM is specifically designed to call providers (including Anthropic) and expose OpenAI-compatible endpoints. Then Osaurus can connect to your local proxy using its "Custom" provider, because that proxy is OpenAI-compatible.

• Set your Anthropic key in env, run LiteLLM proxy (see LiteLLM docs; it supports Anthropic and OpenAI-compatible endpoints).

• In Osaurus Management window (Cmd+Shift+M) -> Providers -> Add Provider -> Custom

  • Use:

  • Base URL: http://127.0.0.1:4000/v1

  • API Key: anything (or your LiteLLM proxy key if you set one)

  • Model name in Osaurus: whatever model mapping you expose via LiteLLM