Access Hundreds of LLMs via OpenRouter

OpenRouter provides a unified OpenAI-compatible API that gives access to 200+ models from multiple providers. This guide shows how to route traffic to OpenRouter through API7 Gateway using the ai-proxy plugin.

Prerequisites

• Install Docker.

• Install cURL to send requests to the services for validation.

• Have a running API7 Gateway instance.

• Create a token from the Dashboard and save it to an environment variable:

  export API_KEY=your-dashboard-token   # replace with your Dashboard token

• Replace {gateway_group_id} with your gateway group ID. Use default if you are following the quickstart.

• If you are following the Admin API examples, create or reuse a service in API7 Gateway. If you do not have one yet, follow Create or Reuse a Service, then save its ID to an environment variable:

  export SERVICE_ID=your-service-id         # replace with your service ID

Obtain an OpenRouter API Key

Create an account at openrouter.ai and generate an API key. Save the key to an environment variable:

export OPENROUTER_API_KEY=sk-or-xxxxxxxxxxxxxxxxxxxxxxxx   # replace with your OpenRouter API key

Configure the AI Proxy for OpenRouter

Create a route with the ai-proxy plugin:

Admin API

curl -k "https://localhost:7443/apisix/admin/routes?gateway_group_id={gateway_group_id}" -X PUT \
  -H "X-API-KEY: ${API_KEY}" \
  -d '{
    "id": "openrouter-route",
    "service_id": "'"$SERVICE_ID"'",
    "paths": ["/openrouter"],
    "plugins": {
      "ai-proxy": {
        "provider": "openrouter",
        "auth": {
          "header": {
            "Authorization": "Bearer '"$OPENROUTER_API_KEY"'"
          }
        },
        "options": {
          "model": "anthropic/claude-sonnet-4-20250514"
        }
      }
    }
  }'

❶ Set the provider to openrouter.

❷ Attach the OpenRouter API key in the Authorization header.

❸ Set the model using the provider/model format. Browse available models at openrouter.ai/models.

ADC

adc.yaml

services:
  - name: OpenRouter Service
    routes:
      - uris:
          - /openrouter
        name: openrouter-route
        plugins:
          ai-proxy:
            provider: openrouter
            auth:
              header:
                Authorization: "Bearer ${OPENROUTER_API_KEY}"
            options:
              model: anthropic/claude-sonnet-4-20250514

❶ Set the provider to openrouter.

❷ Attach the OpenRouter API key in the Authorization header.

❸ Set the model using the provider/model format. Browse available models at openrouter.ai/models.

Synchronize the configuration to API7 Gateway:

adc sync -f adc.yaml

Multi-Model Routing via OpenRouter

Use ai-proxy-multi to load-balance across different models available through OpenRouter:

Admin API

curl -k "https://localhost:7443/apisix/admin/routes?gateway_group_id={gateway_group_id}" -X PUT \
  -H "X-API-KEY: ${API_KEY}" \
  -d '{
    "id": "openrouter-multi-route",
    "service_id": "'"$SERVICE_ID"'",
    "paths": ["/openrouter"],
    "plugins": {
      "ai-proxy-multi": {
        "instances": [
          {
            "name": "budget-model",
            "provider": "openrouter",
            "auth": { "header": { "Authorization": "Bearer '"$OPENROUTER_API_KEY"'" } },
            "options": { "model": "google/gemini-2.0-flash" },
            "weight": 8
          },
          {
            "name": "premium-model",
            "provider": "openrouter",
            "auth": { "header": { "Authorization": "Bearer '"$OPENROUTER_API_KEY"'" } },
            "options": { "model": "anthropic/claude-sonnet-4-20250514" },
            "weight": 2
          }
        ]
      }
    }
  }'

❶ Route 80% of traffic to a budget-friendly model.

❷ Route 20% to a premium model for higher-quality responses.

ADC

adc.yaml

services:
  - name: OpenRouter Multi-Model
    routes:
      - uris:
          - /openrouter
        name: openrouter-multi-route
        plugins:
          ai-proxy-multi:
            instances:
              - name: budget-model
                provider: openrouter
                auth:
                  header:
                    Authorization: "Bearer ${OPENROUTER_API_KEY}"
                options:
                  model: google/gemini-2.0-flash
                weight: 8
              - name: premium-model
                provider: openrouter
                auth:
                  header:
                    Authorization: "Bearer ${OPENROUTER_API_KEY}"
                options:
                  model: anthropic/claude-sonnet-4-20250514
                weight: 2

❶ Route 80% of traffic to a budget-friendly model.

❷ Route 20% to a premium model for higher-quality responses.

Synchronize the configuration to API7 Gateway:

adc sync -f adc.yaml

For more routing strategies, see Multi-LLM Routing and Fallback.

Validate the Configuration

Send a chat completion request:

curl "http://127.0.0.1:9080/openrouter" -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      { "role": "user", "content": "What is an API gateway?" }
    ]
  }'

You should receive a response similar to the following:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "anthropic/claude-sonnet-4-20250514",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "An API gateway is a server that acts as a single entry point for a set of microservices or APIs, handling request routing, composition, and protocol translation."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 32,
    "total_tokens": 42
  }
}

To enable streaming responses, set "stream": true in the request body. Use the proxy-buffering plugin to disable NGINX proxy_buffering to avoid server-sent events (SSE) being buffered.

Next Steps

You have learned how to route traffic to OpenRouter through API7 Gateway. See the OpenRouter documentation to learn more about available models and pricing.

• Multi-LLM Routing and Fallback — Combine OpenRouter with direct provider connections for failover.
• Token Rate Limiting — Control spending across models.