docs: update hugging face inference

[burtenshaw]

Description

This PR updated the model provider section for the latest offering from Hugging Face. This includes:

• removing deprecated inference api
• adding inference providers section and config with links to get token
• adding inference endpoints section with link to create endpoint.
• I've also moved the Hugging Face page in the menu. Hope that's ok.

AI Code Review

• Team members only: AI review runs automatically when PR is opened or marked ready for review
• Team members can also trigger a review by commenting @continue-review

Checklist

• I've read the contributing guide
• The relevant docs, if any, have been updated or created
• [n/a] The relevant tests, if any, have been updated or created

Screen recording or screenshot

[ When applicable, please include a short screen recording or screenshot - this makes it much easier for us as contributors to review and understand your changes. See this PR as a good example. ]

Tests

[ What tests were added or updated to ensure the changes work as expected? ]

---

Summary by cubic

Updated Hugging Face model provider docs to use Inference Providers and Inference Endpoints, replacing the deprecated Inference API. Also moved the Hugging Face page to the top-level menu.

• New Features

  • Added a new top-level Hugging Face docs page with config examples for Inference Providers and Inference Endpoints.
  • Linked to token settings, provider prioritization, and endpoint creation.
  • Included JSON examples (still marked deprecated).

• Migration

  • Removed the old huggingfaceinferenceapi.mdx page; switch configs to provider: huggingface-inference-providers or huggingface-inference-endpoints.
  • Use apiBase https://router.huggingface.co/v1 for Providers, and your dedicated endpoint URL for Endpoints.

^{Written for commit 0d645fc. Summary will update automatically on new commits.}

[continue]

Keep this PR in a mergeable state →

Learn more

---

All Green is an AI agent that automatically:

✅ Addresses code review comments

✅ Fixes failing CI checks

✅ Resolves merge conflicts

[github-actions]

All contributors have signed the CLA ✍️ ✅
_{Posted by the CLA Assistant Lite bot.}

[continue]

This PR contains only documentation changes (moving and updating Hugging Face inference docs). No additional test coverage is needed as there are no code modifications to test.

[continue]

Documentation Updates

I've added a commit with the following fixes:

Critical Fixes

• Corrected provider names: Changed from huggingface-inference-providers and huggingface-inference-endpoints to huggingface-inference-api (the only provider name that actually exists in the codebase)
  • The code in core/llm/llms/HuggingFaceInferenceAPI.ts only defines huggingface-inference-api
  • The code automatically detects OpenAI-compatible endpoints (like the router) and handles them appropriately

Minor Fixes

• Fixed typo: "run your open models dedicated hardware" → "run your open models on dedicated hardware"
• Updated Inference Endpoints link from user-specific URL to generic endpoint: https://ui.endpoints.huggingface.co
• Fixed punctuation in intro sentence (period → colon)

All changes maintain the same level of detail and scope as the original documentation.

[cubic-dev-ai]

1 issue found across 3 files

Prompt for AI agents (all 1 issues)

Check if these issues are valid — if so, understand the root cause of each and fix them.


<file name="docs/customize/model-providers/top-level/huggingfaceinference.mdx">

<violation number="1" location="docs/customize/model-providers/top-level/huggingfaceinference.mdx:34">
The JSON config example still references the deprecated `huggingface-inference-api` provider even though this page is meant to describe Hugging Face Inference Providers, so JSON users would be guided to an invalid backend.</violation>
</file>

---

Since this is your first cubic review, here's how it works:

• cubic automatically reviews your code and comments on bugs and improvements
• Teach cubic by replying to its comments. cubic learns from your replies and gets better over time
• Ask questions if you need clarification on any suggestion

_{Reply to cubic to teach it or ask questions. Re-run a review with @cubic-dev-ai review this PR}

[RomneyDa]

@burtenshaw appreciate the contribution! I think will likely want to keep HuggingFace in More for now just based on usage, but not sure, @TyDunn thoughts?

EDIT, talked with @ty, we're good with the move, but I think some copy on the customize/model-providers/overview page will need to be updated with the section move

[TyDunn]

Thanks for the contribution, @burtenshaw! We will need you to follow these instructions to sign our CLA in order to merge: #8910 (comment)

[burtenshaw]

I have read the CLA Document and I hereby sign the CLA

[burtenshaw]

recheck

[RomneyDa]

Thanks for the updates!

[sestinj]

🎉 This PR is included in version 1.7.0 🎉

The release is available on:

• npm package (@latest dist-tag)
• GitHub release

Your semantic-release bot 📦🚀