OpenAI provider

You can proxy requests to OpenAI 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 OpenAI API endpoints. The following table shows the upstream paths used for each capability.

The following tables show the AI capabilities supported by OpenAI 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 OpenAI basic text generation capabilities including chat, completions, and embeddings:

¹ Use text-embedding-3-small or text-embedding-3-large for dynamic dimensions.

Advanced text generation

Support for OpenAI function calling to allow OpenAI models to use external tools and APIs:

Processing

Support for OpenAI file operations, batch operations, assistants, and response handling:

² Requires header OpenAI-Beta: assistants=v2

Audio

Support for OpenAI text-to-speech, transcription, and translation capabilities:

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

Supported audio formats, voices, and parameters vary by model. Refer to your provider’s documentation for available options.

Image

Support for OpenAI image generation and editing capabilities:

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

Supported image sizes and formats vary by model. Refer to your provider’s documentation for allowed dimensions and requirements.

Video

Support for OpenAI video generation capabilities:

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

Realtime

Support for OpenAI’s bidirectional streaming for realtime applications:

Realtime processing requires the AI Proxy Advanced plugin and uses WebSocket protocol.

To use the realtime route, you must configure the protocols ws and/or wss on both the Service and on the Route where the plugin is associated.

³ For requests to OpenAI realtime API, include include the header OpenAI-Beta: realtime=v1.

The base URL is https://api.openai.com:443/{route_type_path}, 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 OpenAI-compatible endpoint, in which case set the upstream_url plugin option.

To use OpenAI 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_OPENAI_API_KEY" }}
      model:
        provider: openai
        name: gpt-5.1
        options:
          max_tokens: 512
          temperature: 1.0

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 '$OPENAI_API_KEY'"
        },
        "model": {
          "provider": "openai",
          "name": "gpt-5.1",
          "options": {
            "max_tokens": 512,
            "temperature": 1.0
          }
        }
      }
    }
    '

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 $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-proxy",
      "config": {
        "route_type": "llm/v1/chat",
        "auth": {
          "header_name": "Authorization",
          "header_value": "Bearer '$OPENAI_API_KEY'"
        },
        "model": {
          "provider": "openai",
          "name": "gpt-5.1",
          "options": {
            "max_tokens": 512,
            "temperature": 1.0
          }
        }
      }
    }
    '

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 $OPENAI_API_KEY
  model:
    provider: openai
    name: gpt-5.1
    options:
      max_tokens: 512
      temperature: 1.0
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.openai_api_key"
    }

    model = {
      provider = "openai"
      name = "gpt-5.1"

      options = {
        max_tokens = 512
        temperature = 1.0
      }
    }
  }

  control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
}

variable "openai_api_key" {
  type = string
}

For more configuration options and examples, see:

• AI Proxy examples
• AI Proxy Advanced examples

• Control accuracy of LLM models using the AI LLM as judge plugin View →
• Control prompt size with the AI Compressor plugin View →
• Configure dynamic authentication to LLM providers using HashiCorp vault View →
• Filter knowledge base queries with the AI RAG Injector plugin View →
• Get started with AI Gateway View →
• Use AI PII Sanitizer to protect sensitive data in requests View →
• Send asynchronous requests to LLMs View →
• Set up AI Proxy Advanced with OpenAI in Kong Gateway View →
• Set up AI Proxy with OpenAI in Kong Gateway View →
• Validate Gen AI tool calls with Jaeger and OpenTelemetry View →