Mistral AI Observability
Overview
Monitor Mistral AI API usage, latency, token consumption, error rates, and costs. Covers instrumented client wrapper, Prometheus metrics, Grafana dashboard panels, alerting rules, and structured logging.
Prerequisites
- Mistral API integration in production
- Prometheus or OpenTelemetry-compatible metrics backend
- Alerting system (Alertmanager, PagerDuty, or similar)
Instructions
Step 1: Instrumented Client Wrapper
import { Mistral } from '@mistralai/mistralai';
const PRICING: Record<string, { input: number; output: number }> = {
'mistral-small-latest': { input: 0.10, output: 0.30 },
'mistral-large-latest': { input: 0.50, output: 1.50 },
'codestral-latest': { input: 0.30, output: 0.90 },
'mistral-embed': { input: 0.10, output: 0 },
};
interface MetricsEvent {
model: string;
endpoint: string;
durationMs: number;
status: 'success' | 'error';
statusCode?: number;
inputTokens?: number;
outputTokens?: number;
costUsd?: number;
}
function emitMetrics(event: MetricsEvent): void {
// Push to your metrics backend (Prometheus, Datadog, etc.)
console.log(JSON.stringify({ type: 'mistral_metric', ...event }));
}
async function instrumentedChat(
client: Mistral,
model: string,
messages: any[],
options?: any,
) {
const start = performance.now();
try {
const response = await client.chat.complete({ model, messages, ...options });
const duration = Math.round(performance.now() - start);
const pricing = PRICING[model] ?? PRICING['mistral-small-latest'];
const pt = response.usage?.promptTokens ?? 0;
const ct = response.usage?.completionTokens ?? 0;
emitMetrics({
model,
endpoint: 'chat.complete',
durationMs: duration,
status: 'success',
inputTokens: pt,
outputTokens: ct,
costUsd: (pt / 1e6) * pricing.input + (ct / 1e6) * pricing.output,
});
return response;
} catch (error: any) {
emitMetrics({
model,
endpoint: 'chat.complete',
durationMs: Math.round(performance.now() - start),
status: 'error',
statusCode: error.status,
});
throw error;
}
}
