Computer Usage Analytics - Perplexity

2026-02-04 · Source: perplexity.ai via Google News · Field: Technology & Digital — Software Development & Engineering, Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Intermediate, quick

Summary

The Perplexity Computer Usage Analytics API provides organizations with detailed, bucketed usage data for their computational resources. Accessible via the https://api.perplexity.ai/v1/analytics/computer/usage endpoint, it requires a specific organization analytics API key, distinct from a regular Sonar API key, generated by an organization administrator. Users can query various datasets, including credit_usage, connectors, artifacts, skills, spaces, workflows, and task_durations, specifying start_time, end_time, and bucket_width (1d or 1h). The API returns chronological usage data, such as a count of 350 for a given period, broken down by_category into "paid" (250) and "promo" (80), with pagination support for larger data sets.

Key takeaway

For MLOps Engineers or platform administrators managing Perplexity resources, integrating with the Computer Usage Analytics API is crucial for cost management and operational visibility. You can programmatically monitor credit_usage and track resource consumption across connectors, skills, and workflows to optimize spending and identify usage patterns. Implement automated alerts based on task_durations or specific dataset usage to proactively manage your organization's computational footprint and ensure efficient resource allocation.

Key insights

Perplexity offers an API for organizations to monitor detailed computer usage analytics across various datasets.

Principles

• Organizational analytics require a dedicated API key.
• Usage data is bucketed by time and category.
• Query windows are limited to 90 days.

Method

Query the analytics/computer/usage endpoint with an organization analytics API key, specifying dataset, start_time, end_time, and bucket_width to retrieve chronological usage data.

In practice

• Track credit_usage for billing reconciliation.
• Monitor connectors and skills adoption.
• Analyze task_durations for performance insights.

Topics

• Perplexity API
• Usage Analytics
• API Key Management
• Resource Monitoring
• Cost Optimization
• Data Bucketing

Best for: CTO, VP of Engineering/Data, Director of AI/ML, Software Engineer, AI Engineer, MLOps Engineer

Related on AIssential

• How to use Perplexity’s new Computer to build a Pricing Intelligence Engine, OKR review system, API cost simulator and more — Perplexity Computer is an AI "digital worker" that orchestrates multi-model workflows for complex tasks.
• 8 Ways I Reduced My AI API Bill by 60 Percent Without Any User Noticing Any Difference — Significant AI API cost reductions are achievable by eliminating non-value-adding expenditures without quality degradation.
• Personal Computer Is Here - Perplexity — Perplexity's Personal Computer orchestrates local and web resources to automate complex workflows on your machine.
• Use Computer on the mobile app - Perplexity — The "Connectors" feature integrates a wide array of third-party services for data access and action within a central "Computer" system.
• Perplexity announces hybrid AI system that decides what runs locally or in the cloud — Perplexity's hybrid AI orchestrator intelligently routes tasks between local and cloud models for optimal privacy and efficiency.
• The Computer Is Personal Again — Agentic computing shifts from direct manipulation to supervised delegation, making trust and orchestration paramount.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by perplexity.ai via Google News.