Documentation

Nostimates API

Collect AI answers and search results for your own applications. Submit a prompt and supported targets, follow an asynchronous job, then download the collected data. Access is arranged manually; these docs are open to everyone.

Start the quickstart Request API access

curl --fail-with-body --silent --show-error --max-time 30 \
  -X POST "$NOSTIMATES_BASE_URL/v1/crawl-jobs" \
  -H "Authorization: Bearer $NOSTIMATES_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "prompt": "What are the best CRM tools for a small team?",
  "targets": [
    "google",
    "chatgpt",
    "perplexity"
  ],
  "runCount": 1,
  "options": {
    "country": "US"
  }
}' \
  --output accepted.json

Illustrative request and acceptance. Use the base URL and account token supplied during onboarding.

Getting started

Introduction

Collect AI answers and search results for your own applications.

Quickstart

Submit a job, wait for completion, and download its collected results.

Authentication

Account bearer tokens supplied after manual approval.

Core concepts

Targets and output schemas

Five target IDs and their provider-specific response shapes.

Repeat collection and task counts

Choose runCount and interpret successful runs and failures.

API reference

Crawl jobs

Create a crawl job and retrieve its status and progress.

Results

Download the artifact and interpret partial or all-failed collections.

Webhooks

Verify signed completion metadata, accept duplicate deliveries safely, and retrieve results.

Errors and limits

Validation, account access, conflicting requests, and active jobs.

Operations

Collection reliability

Persisted jobs, bounded retries, partial outcomes, and completion-delivery recovery.

Using data in your application

Build your own analysis and discuss applicable usage terms during onboarding.