Skip to main content

Build with PoYo

Welcome to PoYo.ai. 👋 This guide walks you through the essential information you need to start integrating PoYo.ai APIs into your product, including models, pricing, authentication, request flow, limits, and support. We aim to be transparent, practical, and developer-friendly. Please read this carefully before going to production. Access image, video, audio, music, 3D, and chat models through one API key. Start with a model call, then choose REST, CLI, or MCP for your application.

Browse models

Compare model capabilities and test inputs in the Playground.

Get an API key

Create a key and configure usage limits or an IP allowlist.

View pricing

Check current model pricing before submitting paid work.

1. Available Models & Playground

Find the latest supported models on our Model page.
  • We continuously update and onboard new models as soon as they are stable.
  • Each model page links to its Playground, where you can test and experiment directly in our UI before calling the API.
  • The Playground is the best place to understand model behavior, parameters, and output formats.

2. Pricing

The complete and up-to-date pricing list is available on the pricing page.
  • Our prices are typically 30%-50% lower than official APIs.
  • For some models, discounts can reach up to 80%.
  • Pricing may change as upstream providers adjust their costs, so always refer to the pricing page for the latest numbers.

3. Choose how to integrate

4. Creating and Securing Your API Key

Create and manage your API keys on the API key page. Important security notes:
  • Never expose your API key in frontend code (browser, mobile apps, public repositories).
  • Treat your API key as a secret.
To help protect your usage, we provide:
  • Rate limits per key (hourly, daily, and total usage caps)
  • IP whitelist support, allowing only approved server IPs to access the API
These features help prevent accidental overuse and unauthorized requests.

5. Required Request Headers

Every API request must include the correct headers:
If these headers are missing or incorrect, you may receive:
Always double-check your headers when debugging authentication issues.

6. Make your first generation request

Generation is asynchronous. Submit a task, save its task_id, then poll its status or receive a webhook.
A successful submit response means the task was accepted, not that generation has finished.

7. Retrieve the result

Continue while the task is queued or running. When it finishes, download the returned files to storage you control. For production workloads, prefer signed webhooks instead of frequent polling.

8. Logs & Task Details

Inspect all your historical tasks on the task history page. For each task, you can view:
  • Creation time
  • Model used
  • Input parameters
  • Task status
  • Credit consumption
  • Final results or error details
If you ever suspect incorrect credit usage, this page is the source of truth for verification.

9. Data Retention Policy

Please note our retention rules:
  • Generated media files: stored for 3 days, then automatically deleted
  • Log records (text / metadata): stored for 2 months, then automatically deleted
If you need long-term access, make sure to download and store results on your side in time.

10. Asynchronous Task Model

All generation tasks on PoYo.ai are asynchronous. A successful request returns:
  • HTTP 200
  • A task_id
A 200 response only means the task was created, not completed. To get the final result, you must either:
  • Provide a callback (webhook) URL in the request, or
  • Actively poll the “Get Task Status” API using the task_id

11. Rate Limits & Concurrency

By default, we apply the following limits:
  • Up to 20 new generation requests per 10 seconds
  • This typically allows 100+ concurrent running tasks
  • Limits are applied per account
If you exceed the limit:
  • Requests will be rejected with HTTP 429
  • Rejected requests will not enter the queue
For most users, this is more than sufficient. If you consistently hit 429 errors, you may contact support to request a higher limit - approvals are handled cautiously.

12. Before production

  • Keep API keys on your server; never expose them in browser or mobile code.
  • Validate inputs against the selected model’s current schema.
  • Handle 401, 402, 429, and transient server failures explicitly.
  • Treat every submission retry as potentially new paid work; confirm whether the original request created a task before resubmitting.
  • Review task statuses, error responses, and current pricing.
  • Generated media is temporary. Download results promptly and follow the retention policy shown in your account and API documentation.

13. Build with an AI assistant

Connect PoYo MCP when an assistant needs live model schemas, pricing, account information, and execution tools:
Start with PoYo Integrations, or go directly to the setup guide for Claude, Cursor, Codex, or VS Code.

14. Support

Use the support entry in the PoYo dashboard for the fastest account-aware assistance, or email [email protected].

Developer Support

Recommended support channels are available directly from the dashboard’s bottom-left menu. Discord is the fastest option. What you get:
  • Private, 1-on-1 channels
  • Your data and conversations remain confidential
  • Faster and more technical responses
Support hours: UTC 21:00 - UTC 17:00 (next day). Email is available (slower): [email protected].

15. Stability Expectations

We provide access to top-tier, highly competitive APIs at very aggressive pricing. That said:
  • We are not perfect
  • Our overall stability may be slightly lower than official providers
  • This is a conscious trade-off
In practice, PoYo.ai is stable enough to support production workloads and long-term business growth, but we believe in setting realistic expectations upfront.

16. About the Team

PoYo.ai is built by a small startup team.
  • We move fast
  • We care deeply about developer experience
  • We are constantly improving
At the same time, we acknowledge that:
  • Not everything is perfect
  • We can’t satisfy every use case immediately
Your feedback helps us improve - and we genuinely appreciate it.