Welcome to KIE. This guide walks you through the essential information you need to start integrating KIE 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.1. Available Models & Playground#
You can find the latest supported models on our Market 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 here: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. Creating and Securing Your API Key#
Create and manage your API keys here:Important security notes:Never expose your API key in frontend code (browser, mobile apps, public repositories).
Treat your API key as a secret.
Rate limits per key (hourly, daily, and total usage caps)
IP whitelist support, allowing only approved server IPs to access the API
Every API request must include the correct headers:If these headers are missing or incorrect, you may receive:{"code":401,"msg":"You do not have access permissions"}
5. Logs & Task Details#
You can inspect all your historical tasks here:For each task, you can view:Final results or error details
6. Data Retention Policy#
Please note our retention rules:Generated media files: stored for 14 days, then automatically deleted
Log records (text / metadata): stored for 2 months, then automatically deleted
7. Asynchronous Task Model#
All generation tasks on KIE are asynchronous.A successful request returns:A 200 OK response only means the task was successfully created. It does not mean the task is completed.
Provide a callback (webhook) URL in the request, or
Actively poll the "query record info" API using the task_id
8. 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
Requests will be rejected with HTTP 429
Rejected requests will not enter the queue
If you consistently hit 429 errors, you may contact support to request a higher limit — approvals are handled cautiously.
9. Developer Support#
The recommended support channels are available directly from the dashboard (bottom-left menu):Your data and conversations remain confidential
Faster and more technical responses
UTC 21:00 – UTC 17:00 (next day)You may also email us at support@kie.ai, but this is not the preferred or fastest option.
10. Stability Expectations#
We provide access to top-tier, highly competitive APIs at very aggressive pricing.Our overall stability may be slightly lower than official providers
This is a conscious trade-off
11. About the Team#
KIE is built by a small startup team.We care deeply about developer experience
We are constantly improving
Not everything is perfect
We can't satisfy every use case immediately
