---
updatedAt: 2026-09-18T18:57:57.000Z
agentTools:
  projectIndex: https://docs.ascerta.com/llms.txt
---

# Requests

# Overview

In Ascerta, a **Request** refers to an API call to a <Glossary>Provider</Glossary>, such as getting a chat completion from Anthropic or generating an image with DALL-E. Requests are the fundamental unit of tracking in the Ascerta system and serve as your <Glossary>statement of record</Glossary> for all GenAI interactions.

## The Core of Ascerta Tracking

Requests form the backbone of Ascerta's tracking and analytics system. Each request represents a discrete API call that Ascerta captures, enriches, and analyzes. When Ascerta instruments a request, it records much more than just cost:

* **Usage metrics**: Tokens, images, or other resource consumption
* **Performance data**: Response times, latency statistics
* **Cost information**: Calculated based on the latest <Glossary>Provider</Glossary> pricing
* **Success/failure status**: Whether the API call completed successfully
* **Semantic information**: Use cases, user IDs, custom properties
* **Limit tracking**: How the request affects your defined budgets and quotas

This comprehensive data collection makes requests the central element in Ascerta's monitoring, analytics, and control capabilities.

## How Ascerta Works with Requests

Your application communicates directly with the GenAI provider, while Ascerta captures metrics asynchronously:

```
Your App → GenAI Provider
       ↓
     Ascerta
```

This approach provides:

* Minimal latency impact
* No direct dependency on Ascerta for request success
* Comprehensive usage tracking
* Support for all Ascerta analytics features