Mistral AI

Installation

pip
uv
npm
yarn
pnpm

pip install "pandaprobe[mistral]"

uv add "pandaprobe[mistral]"

npm install pandaprobe @mistralai/mistralai

yarn add pandaprobe @mistralai/mistralai

pnpm add pandaprobe @mistralai/mistralai

Setup

Python
TypeScript

Python

from pandaprobe.wrappers import wrap_mistral
from mistralai.client import Mistral

client = wrap_mistral(Mistral(api_key="..."))

TypeScript

import { Mistral } from "@mistralai/mistralai";
import { wrapMistral } from "pandaprobe/wrappers/mistral";

const client = wrapMistral(new Mistral({ apiKey: process.env.MISTRAL_API_KEY }));

PandaProbe traces both synchronous and asynchronous Python methods, plus the Promise-based TypeScript client.

Chat API

Span name: "mistral-chat", SpanKind: LLM

Python

response = client.chat.complete(
    model="mistral-small-latest",
    messages=[
        {"role": "system", "content": "You are a concise assistant."},
        {"role": "user", "content": "Explain recursion in one sentence."},
    ],
    temperature=0.5,
    max_tokens=200,
)

TypeScript

const response = await client.chat.complete({
  model: "mistral-small-latest",
  messages: [
    { role: "system", content: "You are a concise assistant." },
    { role: "user", content: "Explain recursion in one sentence." },
  ],
  temperature: 0.5,
  maxTokens: 200,
});

What gets traced

Input: messages list, captured directly (Mistral already speaks the universal schema)
Output: assistant message from choices[0].message
Model name (from the response body)
Token usage
Model parameters: temperature, top_p, max_tokens, random_seed, safe_prompt, response_format, tool_choice, presence_penalty, frequency_penalty, n, stop

Streaming

Python

res = client.chat.stream(
    model="mistral-small-latest",
    messages=[{"role": "user", "content": "Hello!"}],
)
with res as event_stream:
    for event in event_stream:
        delta = event.data.choices[0].delta
        if delta.content:
            print(delta.content, end="")

The TypeScript wrapper instruments the JavaScript SDK’s asynchronous chat.stream method:

TypeScript

const stream = await client.chat.stream({
  model: "mistral-small-latest",
  messages: [{ role: "user", content: "Hello!" }],
});
for await (const event of stream) {
  const content = event.data?.choices?.[0]?.delta?.content;
  if (typeof content === "string") process.stdout.write(content);
}

Python’s chat.stream and chat.stream_async, plus TypeScript’s chat.stream, are traced with time-to-first-token and reduced output.

Token usage mapping

Mistral already uses our canonical names, so the mapping is the identity:

Mistral Field	PandaProbe Field
`prompt_tokens`	`prompt_tokens`
`completion_tokens`	`completion_tokens`
`total_tokens`	`total_tokens`

Get Started

Tracing

Installation

Setup

Chat API

Streaming

Token usage mapping

​Installation

​Setup

​Chat API

​Streaming

​Token usage mapping

Installation

Setup

Chat API

Streaming

Token usage mapping