Skip to main content
All endpoints use base URL https://api.deapi.ai and require authentication via Authorization: Bearer <API_KEY> header.
Each POST endpoint has a corresponding /price endpoint to estimate costs before execution.

​
Images

MethodEndpointDescriptionDocs
POST/api/v2/images/generationsGenerate image from text prompt→
POST/api/v2/images/generations/priceCalculate image generation price→
POST/api/v2/images/editsEdit/transform an image→
POST/api/v2/images/edits/priceCalculate image edit price→
POST/api/v2/images/ocrExtract text from image (OCR)→
POST/api/v2/images/ocr/priceCalculate OCR price→
POST/api/v2/images/background-removalsRemove image background→
POST/api/v2/images/background-removals/priceCalculate bg removal price→
POST/api/v2/images/upscalesUpscale image resolution→
POST/api/v2/images/upscales/priceCalculate image upscale price→

​
Videos

MethodEndpointDescriptionDocs
POST/api/v2/videos/generationsGenerate video from text prompt→
POST/api/v2/videos/generations/priceCalculate video generation price→
POST/api/v2/videos/animationsAnimate image into video→
POST/api/v2/videos/animations/priceCalculate animation price→
POST/api/v2/videos/audio-syncsGenerate video from audio + prompt→
POST/api/v2/videos/audio-syncs/priceCalculate audio-sync price→
POST/api/v2/videos/replacementsReplace character in video→
POST/api/v2/videos/replacements/priceCalculate replacement price→
POST/api/v2/videos/upscalesUpscale video resolution→
POST/api/v2/videos/upscales/priceCalculate video upscale price→

​
Audio

MethodEndpointDescriptionDocs
POST/api/v2/audio/speechGenerate speech from text (TTS)→
POST/api/v2/audio/speech/priceCalculate TTS price→
POST/api/v2/audio/musicGenerate music from text→
POST/api/v2/audio/music/priceCalculate music price→
POST/api/v2/audio/transcriptionsTranscribe audio/video (unified)→
POST/api/v2/audio/transcriptions/priceCalculate transcription price→

​
Embeddings

MethodEndpointDescriptionDocs
POST/api/v2/embeddingsGenerate text embeddings→
POST/api/v2/embeddings/priceCalculate embedding price→

​
Prompt Enhancement

AI-powered prompt optimization tools. These endpoints share the v1 URL path — v2 clients call them without any change in authentication or rate limits.
MethodEndpointDescriptionDocs
POST/api/v1/client/prompt/imageImage prompt booster→
POST/api/v1/client/prompt/videoVideo prompt booster→
POST/api/v1/client/prompt/speechSpeech prompt booster→
POST/api/v1/client/prompt/image2imageImage-to-image prompt booster→
GET/api/v1/client/prompts/samplesGenerate sample prompts→

​
Utilities

MethodEndpointDescriptionDocs
GET/api/v2/account/balanceGet current account balance→
GET/api/v2/jobs/{job_request}Check job status and get results→
GET/api/v2/modelsList all available models→

​
Workflow

Typical API usage follows this pattern:
1

Check available models

Call GET /api/v2/models to get current models and their parameters.
2

Calculate price (optional)

Call the /price endpoint with your parameters to estimate cost.
3

Submit job

Call the main endpoint (e.g., POST /api/v2/images/generations). Response contains request_id.
4

Poll or receive via webhook

Call GET /api/v2/jobs/{request_id} or use webhooks / WebSockets for push updates.
5

Download result

When status is done, use result_url to download your generated content.

​
Response Formats

{
  "data": {
    "request_id": "c08a339c-73e5-4d67-a4d5-231302fbff9a"
  }
}
Response structure varies by endpoint. See individual endpoint documentation for exact schemas.
See Errors for detailed error handling documentation.