Newsletter
Join the Community
Subscribe to our newsletter for the latest news and updates
Unified AI API gateway for image, video, and audio generation.
HiAPI is a unified AI API gateway for image, video, and audio generation. It provides a single endpoint and schema to call leading generative models, with persistent artifact storage, task tracking, and callbacks. It is designed for developers and AI agents, offering MCP, Skills, and llms.txt integration.
/v1/tasks endpoint with your API key. Pass the model name, input parameters, storage preference, and optional callback URL.Example curl request:
curl https://api.hiapi.ai/v1/tasks \
-H "Authorization: Bearer $HIAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-2/text-to-image",
"input": {
"prompt": "a glass speaker, studio light"
},
"storage": "persistent",
"callback": {
"url": "https://example.com/cb",
"when": "final"
}
}'
@beta and @pro indicate cost level.Every model lists its price up front. Model names may include @beta or @pro suffixes to indicate cost level. Volume discounts are available for larger usage; contact sales at hi@hiapi.ai.
Which models does HiAPI support? HiAPI supports selected image and video generation models, with audio on the roadmap. Browse the full list on the models page.
How do persistent artifact links work? Set storage to persistent and generated outputs are stored for you and returned as durable links in the task result.
Can I use callbacks instead of polling? Yes. Provide a callback URL and HiAPI notifies you when the task reaches its final state.
Can I try models before integrating? Yes. Use the Playground on each model page to explore parameters and example outputs before writing code.