Add Claude Code integration guide for Inference Providers#2387
Merged
Conversation
- Add dedicated integration page (claude-code.md) documenting: - hf-claude extension (recommended) for interactive model/provider selection - Manual environment variable configuration - Billing to an organization - Add Claude Code to the integrations overview table and Developer Tools category - Add Claude Code to the sidebar navigation (_toctree.yml) Co-authored-by: Lucain <Wauplin@users.noreply.github.com>
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
- Feature Gemma 4 instead of DeepSeek R1 in intro - Link to huggingface.co/inference/models instead of models search page - Use MiniMaxAI/MiniMax-M2.7:fireworks-ai as provider suffix example - Expand TIP to show different models per slot (GLM 5.1 for Opus, gemma-4-31B-it:together for Sonnet, gpt-oss-120b:cerebras for Haiku) - Remove Billing to an Organization section Co-authored-by: Lucain <Wauplin@users.noreply.github.com>
Co-authored-by: Lucain <Wauplin@users.noreply.github.com>
Wauplin
commented
Apr 15, 2026
davanstrien
reviewed
Apr 15, 2026
davanstrien
approved these changes
Apr 15, 2026
Member
davanstrien
left a comment
davanstrien
left a comment
There was a problem hiding this comment.
very nice! Will give this a try myself!
Co-authored-by: Daniel van Strien <davanstrien@users.noreply.github.com>
pcuenca
approved these changes
Apr 15, 2026
| You can also append a `:cheapest` or `:fastest` suffix to prefer cheaper or faster providers (e.g. `MiniMaxAI/MiniMax-M2.7:cheapest`). | ||
|
|
||
| > [!TIP] | ||
| > The `ANTHROPIC_DEFAULT_*_MODEL` variables map to Claude Code's internal model slots (Opus, Sonnet, Haiku), from the most powerful to the quickest. You can assign different models to each slot to balance capability and speed e.g. `zai-org/GLM-5.1` for Opus, `google/gemma-4-31B-it:together` for Sonnet, and `openai/gpt-oss-120b:cerebras` for Haiku. `CLAUDE_CODE_SUBAGENT_MODEL` controls which model is used for sub-agents. |
Member
There was a problem hiding this comment.
Is this available through the extension picker or just by setting the envvars? (just curious)
Contributor
Author
There was a problem hiding this comment.
This is only when setting env vars manually (could be added to hf-claude I suppose cc @hanouticelina - low prio though)
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR adds a new integration guide documenting how to use Claude Code with Hugging Face Inference Providers.
Changes
New file:
docs/inference-providers/integrations/claude-code.mdA dedicated integration page covering two setup methods:
hf-claudeextension (recommended) — an extension for thehfCLI (hanouticelina/hf-claude) that provides an interactive model and provider picker, then launches Claude Code with the correct environment variables.ANTHROPIC_BASE_URL,ANTHROPIC_AUTH_TOKEN,ANTHROPIC_API_KEY, andANTHROPIC_DEFAULT_*_MODELto route Claude Code throughrouter.huggingface.co.Also covers prerequisites, billing to an organization, and links to resources.
Updated:
docs/inference-providers/integrations/index.mdUpdated:
docs/inference-providers/_toctree.ymlSlack Thread