Hugging Face provider

You can proxy requests to Hugging Face AI models through AI Gateway using the AI Proxy and AI Proxy Advanced plugins. This reference documents all supported AI capabilities, configuration requirements, and provider-specific details needed for proper integration.

AI Gateway automatically routes requests to the appropriate Hugging Face API endpoints. The following table shows the upstream paths used for each capability.

The following tables show the AI capabilities supported by Hugging Face provider when used with the AI Proxy or the AI Proxy Advanced plugin.

Set the plugin’s route_type based on the capability you want to use. See the tables below for supported route types.

Text generation

Support for Hugging Face basic text generation capabilities including chat, completions, and embeddings:

Video

Support for Hugging Face video generation capabilities:

For requests with large payloads (video generation), consider increasing config.max_request_body_size to three times the raw binary size.

The base URL is https://api-inference.huggingface.co, where {route_type_path} is determined by the capability.

AI Gateway uses this URL automatically. You only need to configure a URL if you’re using a self-hosted or Hugging Face-compatible endpoint, in which case set the upstream_url plugin option.

By default, the AI Proxy plugin uses OpenAI-compatible request formats. Set config.llm_format to a native format to use Hugging Face-specific APIs and features.

The following native Hugging Face APIs are supported:

To use Hugging Face with AI Gateway, configure the AI Proxy or AI Proxy Advanced.

Here’s a minimal configuration for chat completions:

_format_version: "3.0"
plugins:
  - name: ai-proxy
    config:
      route_type: llm/v1/chat
      auth:
        header_name: Authorization
        header_value: Bearer ${{ env "DECK_HUGGINGFACE_TOKEN" }}
      model:
        provider: huggingface
        name: Qwen/Qwen3-4B-Instruct-2507

curl -i -X POST http://localhost:8001/plugins/ \
    --header "Accept: application/json" \
    --header "Content-Type: application/json" \
    --data '
    {
      "name": "ai-proxy",
      "config": {
        "route_type": "llm/v1/chat",
        "auth": {
          "header_name": "Authorization",
          "header_value": "Bearer '$HUGGINGFACE_TOKEN'"
        },
        "model": {
          "provider": "huggingface",
          "name": "Qwen/Qwen3-4B-Instruct-2507"
        }
      }
    }
    '

curl -X POST https://{region}.api.konghq.com/v2/control-planes/{controlPlaneId}/core-entities/plugins/ \
    --header "accept: application/json" \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-proxy",
      "config": {
        "route_type": "llm/v1/chat",
        "auth": {
          "header_name": "Authorization",
          "header_value": "Bearer '$HUGGINGFACE_TOKEN'"
        },
        "model": {
          "provider": "huggingface",
          "name": "Qwen/Qwen3-4B-Instruct-2507"
        }
      }
    }
    '

echo "
apiVersion: configuration.konghq.com/v1
kind: KongClusterPlugin
metadata:
  name: ai-proxy
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
  labels:
    global: 'true'
config:
  route_type: llm/v1/chat
  auth:
    header_name: Authorization
    header_value: Bearer $HUGGINGFACE_TOKEN
  model:
    provider: huggingface
    name: Qwen/Qwen3-4B-Instruct-2507
plugin: ai-proxy
" | kubectl apply -f -

resource "konnect_gateway_plugin_ai_proxy" "my_ai_proxy" {
  enabled = true

  config = {
    route_type = "llm/v1/chat"

    auth = {
      header_name = "Authorization"
      header_value = "Bearer var.huggingface_token"
    }

    model = {
      provider = "huggingface"
      name = "Qwen/Qwen3-4B-Instruct-2507"
    }
  }

  control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
}

variable "huggingface_token" {
  type = string
}

For more configuration options and examples, see:

• AI Proxy examples
• AI Proxy Advanced examples

• Set up AI Proxy Advanced with HuggingFace in Kong Gateway View →
• Set up AI Proxy with HuggingFace in Kong Gateway View →
• Route Claude CLI traffic through AI Gateway and HuggingFace View →