Add Cheaper Inference as a built-in AI provider #11070

Description

I want to use Cheaper Inference as a built-in AI provider in marimo.
Cheaper Inference is an OpenAI-compatible LLM gateway.
One API key gives access to models from several labs.

The change follows the OpenRouter and OpenCode Go pattern:

• [ai.cheaperinference] config with api_key and base_url.
• Default base URL https://api.cheaperinference.com/v1/.
• Env fallback CHEAPER_INFERENCE_API_KEY.
• Model prefix cheaperinference/, for example cheaperinference/gpt-5.4-mini.
• A settings panel entry, an icon, docs, and tests.

Requests go through the marimo server, like other OpenAI-compatible providers.

Are you willing to submit a PR? (You must receive approval from the team before submitting a PR.)

• Yes

Alternatives

Users can add it under custom_providers with the base URL and key.

Additional context

Docs: https://cheaperinference.com/docs
Models: https://cheaperinference.com/markets