Cerebras through the Vigil proxy

One row per call: the model id as Cerebras 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. Cerebras publishes no machine-readable rate table, and the figures in circulation are third-party observations rather than published rates. These calls are logged and monitored; their cost column stays empty rather than showing a number nobody published.

Every route has the shape https://api.vigil.tools/{user_id}/{provider}/{path}. For Cerebras the provider segment is cerebras, so the base URL is https://api.vigil.tools/{user_id}/cerebras 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 Cerebras key stays where it was, in CEREBRAS_API_KEY.

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.CEREBRAS_API_KEY,   // unchanged
  baseURL: "https://api.vigil.tools/{user_id}/cerebras/v1",
  defaultHeaders: {
    // MUST be X-Vigil-Key: Authorization already carries your Cerebras 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["CEREBRAS_API_KEY"],  # unchanged
    base_url="https://api.vigil.tools/{user_id}/cerebras/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}/cerebras/v1/chat/completions \
  -H "content-type: application/json" \
  -H "Authorization: Bearer $CEREBRAS_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.

This provider caches automatically, on its own terms. Vigil records what it reports and prices it — there is nothing for Vigil to add to the request.

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 Cerebras API key?

No, not the key itself. Your Cerebras 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 Cerebras 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 Cerebras models does Vigil price?

None yet. Cerebras publishes no machine-readable rate table, and the figures in circulation are third-party observations rather than published rates. These calls are logged and monitored; their cost column stays empty rather than showing a number nobody published.

• 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