Add "By provider" section to LLM Gateway overview

[devin-ai-integration]

Add "By provider" section to LLM Gateway overview

Summary

Adds a new "By provider" subsection to the Available models section on the LLM Gateway overview page, placed below the existing "By quality" and "By latency" tables. Models are grouped into three provider-specific tables (Anthropic Claude, OpenAI GPT, Google Gemini), each sorted from newest to oldest model. The Provider column is omitted from these tables since the provider is already indicated by the section heading.

All 21 models appear across the three provider tables, with LMArena Score and Latency values matching the existing cross-provider tables.

Review & Testing Checklist for Human

• Verify "newest to oldest" ordering is correct. Claude and Gemini models have clear version numbers, but the ordering of OpenAI GPT-5 variants (nano vs mini) and open-weight models (oss-120b vs oss-20b) is ambiguous — confirm the intended order.
• Check rendered output via the Fern preview deployment to confirm all three provider tables render cleanly and the page reads well with three table sections stacked together.

Notes

• Requested by @dan-ince-aai
• Link to Devin Session

[devin-ai-integration]

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

• Address comments on this PR. Add '(aside)' to your comment to have me ignore it.
• Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

• Disable automatic comment and CI monitoring

[github-actions]

🌿 Preview your docs: https://assemblyai-preview-c9cd4c03-4cd9-43df-bf08-36cef99c83e8.docs.buildwithfern.com/docs