Lewati ke konten utama
Halaman ini belum tersedia dalam bahasa Anda, atau terjemahannya sedang menunggu tinjauan teknis. Teks asli dalam bahasa Inggris ditampilkan di bawah. Buka halaman berbahasa Inggris

OpenRouter Integration

OpenRouter uses the OpenAI-compatible API, so you can use wrap_openai() to add automatic policy enforcement. Your dashboard policies control which models and providers agents can access through OpenRouter.

Gateway proxy not available

Control Zero does not have a native OpenRouter gateway path. Since OpenRouter is OpenAI API-compatible, use the OpenAI integration with base_url="https://openrouter.ai/api/v1" and your OpenRouter API key.

Setup​

pip install controlzero openai
from controlzero import Client
from controlzero.integrations.openai import wrap_openai
import openai

cz = Client(api_key="cz_live_your_api_key_here")

# Point OpenAI SDK at OpenRouter and wrap it
client = wrap_openai(
    openai.OpenAI(
        base_url="https://openrouter.ai/api/v1",
        api_key="sk-or-your-openrouter-key",
    ),
    cz,
)

# Use normally. All calls are governed by your dashboard policies
response = client.chat.completions.create(
    model="anthropic/claude-sonnet-4-6",
    messages=[{"role": "user", "content": "Hello"}],
)

Since OpenRouter uses the OpenAI SDK format, wrap_openai() works identically. The model name (including the provider prefix like anthropic/ or openai/) is used as the resource in policy checks.

Example Policy​

Allow specific models through OpenRouter while blocking expensive ones:

{
  "name": "openrouter-model-policy",
  "description": "Control which models can be used via OpenRouter",
  "rules": [
    {
      "effect": "allow",
      "action": "llm:generate",
      "resource": "model/anthropic/claude-sonnet-4-6"
    },
    { "effect": "allow", "action": "llm:generate", "resource": "model/openai/gpt-5.4" },
    {
      "effect": "allow",
      "action": "llm:generate",
      "resource": "model/meta-llama/llama-3-70b-instruct"
    },
    {
      "effect": "deny",
      "action": "llm:generate",
      "resource": "model/anthropic/claude-opus-4-6"
    },
    { "effect": "deny", "action": "llm:generate", "resource": "model/*" }
  ]
}

Runtime behavior:

# ALLOWED: matches rule 1
client.chat.completions.create(model="anthropic/claude-sonnet-4-6", messages=[...])

# BLOCKED: matches rule 4
client.chat.completions.create(model="anthropic/claude-opus-4-6", messages=[...])
# Raises PolicyDeniedError

# BLOCKED: matches catch-all deny (rule 5)
client.chat.completions.create(model="google/gemini-pro", messages=[...])
# Raises PolicyDeniedError

Why Use Control Zero with OpenRouter?​

OpenRouter aggregates many providers, which increases the surface for cost overruns and unauthorized model usage. Control Zero adds governance:

  • Model allowlists: Only approved models can be used, even if OpenRouter supports hundreds more.
  • Cost control: Block expensive models (Opus, GPT-4 Turbo) while allowing cost-effective ones.
  • Per-agent policies: Different agents get different model access through conditions.
  • Audit trail: Every model call is logged with agent, model, and decision.

Node.js​

import { Client } from '@controlzero/sdk';
import OpenAI from 'openai';

const cz = new Client({ policyFile: './controlzero.yaml' });

const client = new OpenAI({
  baseURL: 'https://openrouter.ai/api/v1',
  apiKey: process.env.OPENROUTER_API_KEY,
});

// Manual enforcement for Node.js
function generate(prompt: string, model: string) {
  cz.guard('llm', { method: 'generate', args: { model }, raiseOnDeny: true });

  const response = await client.chat.completions.create({
    model,
    messages: [{ role: 'user', content: prompt }],
  });
  return response.choices[0].message.content;
}

Next Steps​