Proxy Gemini Requests

Google Gemini provides an OpenAI-compatible API that allows you to access Gemini models using the familiar OpenAI API format.

This guide shows how to integrate APISIX with Google Gemini using the ai-proxy plugin. With provider set to gemini, you do not need to set a custom endpoint.

Prerequisite(s)

• Install Docker.
• Install cURL to send requests to the services for validation.
• Follow the Getting Started Tutorial to start a new APISIX instance in Docker or on Kubernetes.

Obtain a Google API Key

Create an account and API key by following the Google AI Studio. Optionally save the key to an environment variable:

export GEMINI_API_KEY=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx  # replace with your API key

Create a Route to Gemini

Create a route with the ai-proxy plugin as such:

Admin API

curl "http://127.0.0.1:9180/apisix/admin/routes" -X PUT -d '{
  "id": "gemini-chat",
  "uri": "/anything",
  "plugins": {
    "ai-proxy": {
      "provider": "gemini",
      "auth": {
        "header": {
          "Authorization": "Bearer '"$GEMINI_API_KEY"'"
        }
      },
      "options": {
        "model": "gemini-2.5-flash"
      }
    }
  }
}'

❶ Set the provider to gemini.

❷ Attach the Google API key using the Authorization header.

❸ Set a model supported by Gemini, for example gemini-2.5-flash.

ADC

adc.yaml

services:
  - name: Gemini Service
    routes:
      - uris:
          - /anything
        name: gemini-chat
        plugins:
          ai-proxy:
            provider: gemini
            auth:
              header:
                Authorization: "Bearer xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
            options:
              model: gemini-2.5-flash

❶ Set the provider to gemini.

❷ Attach the Google API key using the Authorization header.

❸ Set a model supported by Gemini, for example gemini-2.5-flash.

Synchronize the configuration to APISIX:

adc sync -f adc.yaml

Ingress Controller

Create a Kubernetes manifest file to configure a route:

Gateway API

gemini-route.yaml

apiVersion: apisix.apache.org/v1alpha1
kind: PluginConfig
metadata:
  namespace: ingress-apisix
  name: ai-proxy-plugin-config
spec:
  plugins:
    - name: ai-proxy
      config:
        provider: gemini
        auth:
          header:
            Authorization: "Bearer xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
        options:
          model: gemini-2.5-flash
---
apiVersion: gateway.networking.k8s.io/v1
kind: HTTPRoute
metadata:
  namespace: ingress-apisix
  name: gemini-chat
spec:
  parentRefs:
  - name: apisix
  rules:
  - matches:
    - path:
        type: Exact
        value: /anything
    filters:
    - type: ExtensionRef
      extensionRef:
        group: apisix.apache.org
        kind: PluginConfig
        name: ai-proxy-plugin-config

APISIX CRD

gemini-route.yaml

apiVersion: apisix.apache.org/v2
kind: ApisixRoute
metadata:
  namespace: ingress-apisix
  name: gemini-route
spec:
  ingressClassName: apisix
  http:
    - name: gemini-route
      match:
        paths:
          - /anything
      plugins:
      - name: ai-proxy
        enable: true
        config:
          provider: gemini
          auth:
            header:
              Authorization: "Bearer xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
          options:
            model: gemini-2.5-flash

❶ Set the provider to gemini.

❷ Attach the Google API key using the Authorization header.

❸ Set a model supported by Gemini, for example gemini-2.5-flash.

Apply the configuration to your cluster:

kubectl apply -f gemini-route.yaml

Verify

Send a request with the following prompts to the route:

curl "http://127.0.0.1:9080/anything" -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      { "role": "system", "content": "You are a helpful AI assistant" },
      { "role": "user", "content": "What is the capital of France?" }
    ]
  }'

You should receive a response similar to the following:

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "The capital of France is **Paris**.",
        "role": "assistant"
      }
    }
  ],
  "model": "gemini-2.5-flash",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 8,
    "prompt_tokens": 15,
    "total_tokens": 41
  },
  ...
}

Next Steps

You have learned how to integrate APISIX with Google Gemini. See the Google AI for Developers and Models pages for more details.

If you would like to stream responses, enable streaming in your request and use the proxy-buffering plugin to disable NGINX proxy_buffering to avoid server-sent events (SSE) being buffered.