NeuralDeep — a self-hosted AI hub for developers
What it is: a unified OpenAI-compatible API to large language models (LLMs)
running on our own self-hosted GPUs. It's an LLM proxy/gateway and platform — NOT an image generator
and NOT a 3D service. One sk- key, base URL https://api.neuraldeep.ru/v1,
compatible with the OpenAI SDK, opencode, Cursor, Cline, Continue and any OpenAI client.
How it differs from token resellers: the models run on our own hardware (not a resold third-party API), your data stays on our infrastructure, and you pay with a monthly subscription instead of a metered per-token bill.
Models
- DaisyGPT (based on Qwen 3.6, 35B-A3B) — chat, tools, reasoning, vision, 256k context
- GPT-OSS 120B — chat, tools, reasoning, 131k context
- Gemma 4 31B — chat, multimodal, 262k context
- Kimi K2.6 — external frontier model (paid tiers)
- Embeddings: e5-large, bge-m3, jina-v4, GigaEmbeddings · Rerank: bge-reranker · Whisper: audio transcription
The free tier includes the open models — DaisyGPT (Qwen 3.6) and GPT-OSS 120B. Premium models (GLM, DeepSeek, MiniMax, Kimi — up to 1M context) are available on paid plans or pay-as-you-go per token (wallet).
Platform services
- LLM API — chat, embeddings, rerank, transcription, vision
- Drift — a personal AI agent with memory, a code sandbox and Telegram
- Search API — web and Telegram search, crawling
- SpeechCore — long audio/video transcription (WhisperX) + text-to-speech
- OCR API — PDF/scan → markdown
- Image API — generation/upscale/background removal
Site sections
Links
- Reference for AI agents (markdown): neuraldeep.tech/llms.txt · full: neuraldeep.tech/llms-full.txt
- API: api.neuraldeep.ru/v1 · Dashboard: neuraldeep.tech/app
- Search: search.neuraldeep.ru · Transcription: speechcore.neuraldeep.ru · Status: status.neuraldeep.ru