NeuralDeep — self-hosted AI hub: OpenAI-compatible LLM proxy & API

OpenAI-compatible API to open-source LLMs: qwen3.6, qwen3.8, embeddings and whisper on our own self-hosted GPUs; gpt-oss-120b, Gemma 4, Kimi K2.6 via third-party upstreams. A flat subscription instead of per-token billing — plus an AI agent and search.

Part of NeuralDeep — a self-hosted AI hub: an OpenAI-compatible API to LLMs on our own GPUs, an AI agent and web search under one subscription.

Home · API docs · Models · Pricing · Benchmarks

Machine-readable reference for AI agents: llms.txt · full: llms-full.txt

https://neuraldeep.ru/en