Skip to main content

​
Flash API

Base URL: https://api.timepointai.com All endpoints require X-Service-Key header authentication.

​
Health Check

GET /health
No auth required. Returns service status and provider availability. 
{
  "status": "healthy",
  "version": "2.4.0",
  "database": true,
  "providers": {
    "google": true,
    "openrouter": true
  }
}

​
Render Endpoints

​
POST /api/v1/timepoints/generate/sync

Synchronous render — blocks until the full scene is generated. 
curl -X POST https://api.timepointai.com/api/v1/timepoints/generate/sync \
  -H "Content-Type: application/json" \
  -H "X-Service-Key: YOUR_KEY" \
  -d '{"query": "AlphaGo plays Move 37, Seoul, March 10 2016", "generate_image": true}'
Request Body:
FieldTypeRequiredDescription
querystringYesNatural language description of the moment
generate_imagebooleanNoGenerate photorealistic image (default: false)
Response: Full scene with characters, dialog, atmosphere, relationships, image URL, confidence scores, and source citations. Output is TDF-compatible.

​
POST /api/v1/timepoints/generate/stream

Server-Sent Events (SSE) stream — returns pipeline progress in real-time as each agent completes. 
curl -N -X POST https://api.timepointai.com/api/v1/timepoints/generate/stream \
  -H "Content-Type: application/json" \
  -H "X-Service-Key: YOUR_KEY" \
  -d '{"query": "Moon landing, July 20 1969", "generate_image": true}'
Events are streamed as each agent in the pipeline completes: Judge → Timeline → Grounding → Scene → Characters → Moment → Camera → Dialog → Critique → ImagePrompt → Optimizer → ImageGen

​
Image Generation

Flash uses a 3-tier fallback chain:
  1. Google Imagen (primary)
  2. OpenRouter Flux (fallback)
  3. Pollinations.ai (free fallback)
Image URLs are included in the response when generate_image: true.

​
LLM Providers

ProviderRole
Google GeminiPrimary LLM for all agents
OpenRouterFallback with dynamic model registry