deAPI
deAPI is an OpenAI-compatible inference API for open-source models — image, video, audio, music, embeddings, OCR. $5 free, no card.
Punteggio
60
Valutazione Utente
3.0
Supporto Gratuito/Prova
Non Supportato
Prezzo Iniziale
--
Ultimo Aggiornamento
ago 14, 2026
Panoramica
Cos'è deAPI?
Generate images, create videos, clone voices, transcribe YouTube — through one AI inference API and one billing account. deAPI serves 25 open-source AI models across every non-LLM modality, so you don't need to juggle five providers for a single product. ─── TWO WAYS TO CONNECT ─── • OpenAI-compatible endpoint — drop-in for the OpenAI Python and Node SDKs. Change base_url and api_key, keep everything else. • Native REST v2 API — covers everything the OpenAI spec doesn't: video, music, OCR, voice cloning, voice design, and more. ─── IMAGE · 7 MODELS ─── Flux.1 Schnell, FLUX.2 Klein, Z-Image-Turbo, Z-Anime Distill, image editing, background removal, AI upscaling. From $0.00136/image. ─── VIDEO · 7 MODELS ─── Text-to-video, image-to-video, audio-to-video with LTX. Character replacement with Wan2.2-Animate. Video upscaling up to 4x. From $0.00174/clip. ─── AUDIO · 9 MODELS ─── • TTS — Kokoro (40+ voices, 7 languages), Chatterbox (23 languages), 3× Qwen3 TTS. Voice cloning from a 5-15s clip. Voice design from text. From $0.77/1M chars. • Music — ACE-Step: full tracks with lyrics, BPM, key, time signature, style transfer. • Transcription — WhisperLargeV3, 80 MB uploads (3x OpenAI), URL ingest from YouTube, TikTok, Twitch, Kick, X. From $0.021/hour. ─── TEXT · 2 MODELS ─── OCR with Nanonets. Embeddings with BGE-M3 (1024 dims, 8192 tokens) for RAG and semantic search. From $0.000068/1K tokens. ─── PRICING ─── Pay-as-you-go, no subscription. $5 free credit on signup, no card required. Any top-up unlocks Premium: 300 RPM per endpoint, no daily cap. ─── FOR DEVELOPERS ─── Python SDK, n8n node, MCP server for Claude/Cursor/ChatGPT. Webhooks (HMAC-signed), WebSocket live previews, or polling. Distributed verified worker network — data in RAM only, no disk writes.
A cosa serve deAPI?
Funzionalità Principali
- OpenAI-compatible API — drop-in for OpenAI Python and Node SDKs, just change base_url
- 25+ open-source AI models across image, video, audio, and text modalities
- Image generation with Flux.1 Schnell, FLUX.2 Klein, Z-Image-Turbo, and Z-Anime Distill — from $0.00136/image
- Image editing, AI background removal, and image upscaling
- Text-to-speech with 5 models: Kokoro (40+ voices), Chatterbox (23 languages), and 3 Qwen3 TTS variants
- Voice cloning from a 5-15 second reference audio clip
- Voice design — create entirely new voices from text descriptions
- Music generation with ACE-Step: lyrics, BPM, key, time signature, and style transfer
- Transcription with WhisperLargeV3 — 80 MB uploads (3x OpenAI) or URL ingest from YouTube, TikTok, Twitch, Kick, X
- Video generation, image-to-video, and audio-to-video sync with LTX models
- Video character replacement with Wan2.2-Animate
- Video upscaling up to 4x with 3 dedicated models
- OCR for text extraction from images with Nanonets
- Text embeddings with BGE-M3 (1024 dims) for RAG and semantic search
- Python SDK, n8n node, MCP server for Claude/Cursor/ChatGPT
- Pay-as-you-go with $5 free credit on signup, no card required
Come usare deAPI?
─── GETTING STARTED ─── 1. Sign up at https://app.deapi.ai/register — $5 free credit, no card required. 2. Copy your API key from the dashboard (starts with dpn-sk-). ─── OPTION A · OPENAI SDK (FASTEST START) ─── Install the OpenAI SDK (pip install openai or npm install openai), set base_url to https://oai.deapi.ai/v1 and use your deAPI key. Everything else stays the same — works for image generation, image edits, TTS, transcription, embeddings, and video. ─── OPTION B · NATIVE REST V2 API ─── POST to https://api.deapi.ai/api/v2 endpoints with your prompt, model, and parameters. The API returns a request_id for async retrieval. Native v2 unlocks features beyond the OpenAI spec: music generation, video character replacement, audio-to-video, OCR, background removal, voice cloning, and voice design. ─── CHECK COST BEFORE RUNNING ─── Every endpoint has a /price route (e.g. POST /api/v2/images/generations/price) that returns the exact cost for your parameters before you commit. ─── RETRIEVE RESULTS ─── • Polling — GET /api/v2/jobs/{request_id} • Webhooks — set webhook_url, receive HMAC-signed POST on completion • WebSockets — connect to soketi.deapi.ai for real-time progress and live previews Full docs: https://docs.deapi.ai Python SDK: pip install deapi-python-sdk
Strumenti Alternativi
Nessuno strumento alternativo trovato
Pro & Contro
Nessun Dato
Casi d'Uso
- Generate product images and lifestyle shots from text prompts at $0.00136 each
- Remove backgrounds from e-commerce photos at $0.00035 per image
- Create short launch reels by animating a still image into video
- Replace characters in stock video with brand mascots using AI
- Generate voice-overs for tutorials with cloned voices from a short reference clip
- Create background music with lyrics, tempo, and key control for short-form video
- Transcribe YouTube interviews with timestamps for $0.021 per hour
- Extract text from scanned invoices and documents with OCR
- Build RAG indexes with embeddings at $0.000068 per 1K tokens
Recensioni Utenti
3.0
su 5
3.0
Nessuna recensione ancora
Sii il primo a recensire questo strumento!