embeddings 2
deAPI is an OpenAI-compatible inference API for open-source models — image, video, audio, music, embeddings, OCR. $5 free, no card.
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.
Open-source vector database and search engine for similarity search in AI applications.
Qdrant is an open-source vector database and vector search engine written in Rust. It provides fast and scalable vector similarity search service with convenient API. It blends vector similarity with custom logic using Score Boosting Reranker. Qdrant integrates with all leading embeddings and frameworks, turning embeddings or neural network encoders into full-fledged applications for matching, searching, recommending, and more.
