GenzoAI API
One REST API and one key for text, image, video and speech generation across OpenAI, Anthropic, Runway and VoiceNom. Requests are metered against a single credit balance shared with your GenzoAI Studio account.
Base URL — all endpoints are relative to
https://api.genzoai.com/v1. The legacy base
https://genzoai.com/api/v1 resolves to the same routes and remains
supported; new integrations should use api.genzoai.com.
How it works
- Create a GenzoAI account and choose a plan — every plan includes API access.
- Generate an API key from the keys page.
- Send a request naming a
providerandmodel. - A flat credit cost for that modality and provider is deducted up front, and refunded if the call fails.
A first request
curl https://api.genzoai.com/v1/generate/text \ -H "Authorization: Bearer $GENZO_API_KEY" \ -H "Content-Type: application/json" \ -d '{"prompt":"Say hello in five words.","provider":"anthropic"}'
Endpoint map
| Method | Path | Purpose |
|---|---|---|
| POST | /v1/generate/text | Text generation |
| POST | /v1/generate/image | Image generation |
| POST | /v1/generate/video | Video generation (async) |
| POST | /v1/generate/audio | Text to speech |
| GET | /v1/generate/{'{'}uuid{'}'} | Fetch one generation |
| GET | /v1/generate/history | List past generations |
| GET | /v1/providers | Available providers and models |
| GET | /v1/credits/balance | Current credit balance |
| GET | /v1/credits/estimate | Cost estimate before calling |
| GET | /v1/api-keys | Manage keys |
| GET | /health | Service status (no auth) |
Conventions
- All request and response bodies are JSON. Send
Content-Type: application/json. - Every generation returns a
uuid— keep it to fetch results or debug later. - Timestamps are ISO 8601 in UTC.
- Text and image requests complete synchronously. Video and audio are queued — poll
GET /v1/generate/{'{'}uuid{'}'}.
Next
Start with the quickstart, then read authentication for key handling and credits for how billing is calculated.