OpenRouter through the Vigil proxy

One row per call: the model id as OpenRouter returned it, input and output tokens, cache reads and writes where the response reports them, latency, the HTTP status and the provider's error code when it fails, and the agent named in the X-Vigil-Agent header. Likely prompt injections and personal data in prompts are flagged on the Errors page. A cost spike is flagged when a call costs over three times the agent's seven-day median.

Cost is left empty for this provider. OpenRouter prices are an upstream passthrough plus a fee, and the authoritative cost its responses carry is denominated in credits whose USD ratio is unverified. These calls are logged and monitored; their cost column stays empty rather than converting at a rate we cannot confirm.

Every route has the shape https://api.vigil.tools/{user_id}/{provider}/{path}. For OpenRouter the provider segment is openrouter, so the base URL is https://api.vigil.tools/{user_id}/openrouter and a request path such as /v1/chat/completions is forwarded unchanged. The proxy stores the origin only, so the path after the segment is whatever your client already uses, /v1 for most OpenAI-compatible APIs.

Two headers: X-Vigil-Key, your Vigil key from the dashboard, and X-Vigil-Agent, the name the dashboard groups this traffic under. Your OpenRouter key stays where it was, in OPENROUTER_API_KEY.

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPENROUTER_API_KEY,   // unchanged
  baseURL: "https://api.vigil.tools/{user_id}/openrouter/v1",
  defaultHeaders: {
    // MUST be X-Vigil-Key: Authorization already carries your OpenRouter key.
    "X-Vigil-Key": "vk_your_vigil_key",
    "X-Vigil-Agent": "my-agent",
  },
});

const completion = await client.chat.completions.create({
  model: "<your model id>",
  messages: [{ role: "user", content: "Hello!" }],
});

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["OPENROUTER_API_KEY"],  # unchanged
    base_url="https://api.vigil.tools/{user_id}/openrouter/v1",
    default_headers={
        "X-Vigil-Key": "vk_your_vigil_key",
        "X-Vigil-Agent": "my-agent",
    },
)

completion = client.chat.completions.create(
    model="<your model id>",
    messages=[{"role": "user", "content": "Hello!"}],
)

curl https://api.vigil.tools/{user_id}/openrouter/v1/chat/completions \
  -H "content-type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "X-Vigil-Key: vk_your_vigil_key" \
  -H "X-Vigil-Agent: my-agent" \
  -d '{
    "model": "<your model id>",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

Replace {user_id} and vk_your_vigil_key with the values on your Connect page. The snippets above are generated by the same code as that page.

Vigil leaves the body untouched, so cache markers your own client sets are forwarded to whatever OpenRouter routes to. Vigil adds no key of its own.

With optimisation On: the provider caches automatically or not at all; Vigil records cache use and does not change the request. In Shadow, Vigil measures what caching would have saved and changes nothing. Off records the call and nothing more.

Does Vigil see or store my OpenRouter API key?

No, not the key itself. Your OpenRouter key passes through the proxy with the request and is never written to disk. A call record can keep a short one-way digest of the credential, so that one key’s cache is kept apart from another’s; it cannot be turned back into the key. Vigil identifies you by the X-Vigil-Key header and your user id in the URL.

Does routing OpenRouter through Vigil add latency?

Some. The proxy runs on Cloudflare’s edge, so the added hop is short, but reading the request body to place cache markers takes time, and there is a bounded lookup for your account state. The dashboard shows total latency per call. For long calls, stream: Cloudflare’s edge closes non-streaming connections after roughly 125 seconds.

Which OpenRouter models does Vigil price?

None yet. OpenRouter prices are an upstream passthrough plus a fee, and the authoritative cost its responses carry is denominated in credits whose USD ratio is unverified. These calls are logged and monitored; their cost column stays empty rather than converting at a rate we cannot confirm.

• LLM proxy setup — base URLs, headers, modes and errors for every provider
• LLM provider differences — LLM provider differences
• prompt caching providers — Prompt caching providers: inject, steer or observe
• LLM token cost — LLM token cost is a function, not a number
• AI token calculator — price a call from the same rate registry