Build photo intelligence into your product.

Try It Now

Paste this. Get structured context back.

The sandbox key pt_test_sandbox returns fixture data instantly. Use it to shape integrations before signup; the response is the same fake payload every call.

curl -X POST https://api.phototology.com/v1/analyze \
  -H "Authorization: Bearer pt_test_sandbox" \
  -H "Content-Type: application/json" \
  -d '{"imageUrl":"https://example.com/photo.jpg","preset":"full-analysis"}'

Test keys return fixture data instantly. Sign up for a live key when you are ready to analyze real photos.

Integration Surfaces

Four ways in. Same engine.

npx @phototology/mcp

{
  "mcpServers": {
    "phototology": {
      "command": "npx",
      "args": ["-y", "@phototology/mcp"],
      "env": {
        "PHOTOTOLOGY_API_KEY": "pt_test_sandbox"
      }
    }
  }
}

import { PhototologyClient } from '@phototology/sdk';

const pt = new PhototologyClient({ apiKey: 'pt_test_sandbox' });
const result = await pt.analyze({
  imageUrl: 'https://example.com/photo.jpg',
  modules: ['dating', 'entities'],
});

POST https://api.phototology.com/v1/analyze
Authorization: Bearer pt_test_sandbox
Content-Type: application/json

{
  "imageUrl": "https://example.com/photo.jpg",
  "preset": "full-analysis"
}

GET https://api.phototology.com/v1/docs
GET https://api.phototology.com/v1/openapi.json

Response Shape

Every response. Every surface. Same envelope.

Zod-validated. Deterministic. The shape never changes between lenses, stacks, or SDK versions. (The concept words are lens and stack; on the wire, the API request body uses the field names modules and preset for back-compat with existing SDK callers. Both naming conventions refer to the same units.)

{
  "id": "an_...",
  "object": "analysis",
  "schemaVersion": "2.1.0",
  "outputSchema": "photo",
  "createdAt": "2026-04-29T12:00:00Z",
  "output": { /* flat-keyed fields per requested lenses */ },
  "usage": {
    "inputTokens": 1847,
    "outputTokens": 412,
    "totalTokens": 2259,
    "modulesUsed": ["dating", "entities", "describe"],
    "creditsCharged": 3
  },
  "warnings": [],
  "meta": {
    "processingTimeMs": 2340,
    "provider": "gemini",
    "model": "gemini-3.1-flash-lite",
    "vendor": "google",
    "promptHash": "sha256:...",
    "requestId": "req_abc123",
    "ai_generated": true
  }
}

Error Handling

Built for agents. Every error tells you what to do.

Every error response includes a retryable boolean. Your agent never has to guess.

{
  "error": {
    "code": "RATE_LIMITED",
    "message": "Rate limit exceeded. Retry after 2 seconds.",
    "retryable": true,
    "requestId": "req_abc123"
  }
}

Rate limit: 600 requests per minute on authenticated keys. The public sandbox key (anonymous, no account) is capped at 2 requests per minute and 10 per day per IP. The Retry-After header is included on all 429 responses.