Hugging Face provider models not showing in VS Code model select with huggingface-inference-providers configuration

[AlexisPelcik]

Before submitting your bug report

• I've tried using the "Ask AI" feature on the Continue docs site to see if the docs have an answer
• I'm not able to find a related conversation on GitHub discussions that reports the same bug
• I'm not able to find an open issue that reports the same bug
• I've seen the troubleshooting guide on the Continue Docs

Relevant environment info

- OS: Linux
- Continue version: v1.3.30
- IDE version: VSCode 1.109.0
- Model: Qwen/Qwen3-Coder-Next:novita
- config:
  
name: Local Config
version: 1.0.0

schema: v1
models:
  - name: huggingfacembe
    provider: huggingface-inference-providers
    model: Qwen/Qwen3-VL-Embedding-2B
    apiKey: hf_XXXXXX
    apiBase: https://router.huggingface.co/v1
    roles:
      - embed

  - name: huggingfaceAutocomplete
    provider: huggingface-inference-providers
    model: Qwen/Qwen2.5-Coder-7B:fastest
    apiKey: hf_XXXXXX
    apiBase: https://router.huggingface.co/v1
    roles:
      - autocomplete

  - name: huggingface
    provider: huggingface-inference-providers
    model: Qwen/Qwen3-Coder-Next:cheapest
    apiKey: hf_XXXXXXX
    apiBase: https://router.huggingface.co/v1
    roles:
      - chat
      - edit
      - apply

Description

I’m trying to use Hugging Face models in Continue (VS Code extension) by following the documented configuration format. However, the configured model never shows up in the model picker UI.

If I modify the provider to:

provider: huggingface-inference-api

then it does show up in the picker but using that provider results in 404 errors from Hugging Face.

This makes it impossible to use Hugging Face inference providers the way the docs describe: Continue doesn’t show models for huggingface-inference-providers, but only for huggingface-inference-api, which fails in practice.

To reproduce

Add a Hugging Face inference model definition in config.json or VS Code config, e.g.:

- name: huggingface
  provider: huggingface-inference-providers
  model: Qwen/Qwen3-Coder-Next:cheapest
  apiKey: hf_XXXXX
  apiBase: https://router.huggingface.co/v1
  roles:
    - chat

Log output

[sestinj]

Related issues:

• Unable to connect to hugging face inference providers #5763 - Unable to connect to hugging face inference providers (configuration and connection issues)
• Continue will not allow api base for huggingface api inference providers and garbles the resulting url it tries on #3986 - Continue will not allow api base for huggingface api inference providers and garbles the resulting url
• correct provider field in continue config.json for VScode #5630 - Correct provider field in continue config.json for VSCode (provider not recognized in valid values list)