Mistral through the Vigil proxy

One row per call: the model id as Mistral 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 computed from the proxy's rate registry, which prices 7 models on this platform today. A model the registry has no row for is logged with its cost left empty, never estimated.

• codestral-25-08inferred
• ministral-3-14b-25-12inferred
• ministral-3-3b-25-12inferred
• ministral-3-8b-25-12inferred
• mistral-large-3-25-12inferred
• mistral-medium-3-5-26-04inferred
• mistral-small-4-0-26-03inferred

Every route has the shape https://api.vigil.tools/{user_id}/{provider}/{path}. For Mistral the provider segment is mistral, so the base URL is https://api.vigil.tools/{user_id}/mistral and a request path such as /v1/chat/completions is forwarded unchanged.

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

import MistralClient from "@mistralai/mistralai";

const client = new MistralClient({
  serverURL: "https://api.vigil.tools/{user_id}/mistral",
});

const response = await client.chat.complete({
  model: "mistral-large-latest",
  messages: [{ role: "user", content: "Hello!" }],
}, {
  // Authorization already carries your Mistral key — Vigil’s goes in its own header.
  fetchOptions: {
    headers: {
      "X-Vigil-Key": "vk_your_vigil_key",
      "X-Vigil-Agent": "my-agent",
    },
  },
});

curl https://api.vigil.tools/{user_id}/mistral/v1/chat/completions \
  -H "content-type: application/json" \
  -H "Authorization: Bearer $MISTRAL_API_KEY" \
  -H "X-Vigil-Key: vk_your_vigil_key" \
  -H "X-Vigil-Agent: my-agent" \
  -d '{
    "model": "mistral-large-latest",
    "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 sets one field on the request — a cache key naming which cache this call belongs to — and Mistral discounts the reused tokens. This is NOT the breakpoint injection used on Anthropic: Vigil does not choose what gets cached here, only which cache it belongs to, so there is no prefix for the Optimise page to tune.

With optimisation On: Vigil sets a prompt_cache_key so repeated prompts can hit the cache. 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 Mistral API key?

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

The registry holds no verified rate for a Mistral model yet, so calls are logged and monitored with the cost left empty rather than guessed.

• 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