# NeuralDeep — LLM API

> Self-hosted OpenAI-compatible LLM gateway on our own GPUs. Chat, embeddings, rerank,
> transcription (Whisper), vision, OCR, image generation, web/Telegram search, TTS (speech synthesis),
> STT for long audio/video (SpeechCore). One `sk-` key.
> Base URL: `https://api.neuraldeep.tech/v1`. Auth: `Authorization: Bearer $YOUR_KEY`.

Full reference (single markdown file, drop it into an agent's system prompt): https://neuraldeep.tech/llms-full.txt
Human version (UI): https://neuraldeep.tech/docs

## Quick start
```bash
curl https://api.neuraldeep.tech/v1/chat/completions \
  -H "Authorization: Bearer $YOUR_KEY" -H "Content-Type: application/json" \
  -d '{"model":"gpt-oss-120b","messages":[{"role":"user","content":"hi"}],"max_tokens":500}'
```

## Models
- gpt-oss-120b — chat · tools · reasoning · 131k ctx · MXFP4 on 2×RTX 4090 48 GB
- qwen3.8-27b — chat · qwen3 tools · reasoning · 256k ctx · dense 27B · on RTX PRO 6000 96GB in Russia · vision (4 image/prompt)
- qwen3.6-35b-a3b — chat · qwen3 tools · reasoning · 256k ctx · MoE 35B/3B-active · BF16 on 2× RTX 4090 48GB · vision (1 image/prompt)
- gemma-4-31b — chat · tools · multimodal (image/video) · 262k ctx · Google Gemma 4 · on our own GPUs
- e5-large — multilingual embedding · 1024-dim · 3 replicas
- bge-m3 — multilingual embedding · 1024-dim · 8k ctx
- bge-reranker — cross-encoder rerank
- whisper-1 — WhisperX large-v3-turbo · multilingual · word timestamps · RTF ~16×
- qwen3-tts / espeech — TTS speech synthesis · /v1/audio/speech · 8 voices · 10 languages · RU with stress marks

## Sections
> Full text of every section is in one file https://neuraldeep.tech/llms-full.txt (grep by `## <name>`).
> Below — deep-links to each section of the human docs (anchors docs#<id>).

Hub API:
- Text · chat — https://neuraldeep.tech/docs#chat
- Vectorization — https://neuraldeep.tech/docs#vector
- Reranking — https://neuraldeep.tech/docs#rerank
- Transcription — https://neuraldeep.tech/docs#transcribe
- Image recognition — https://neuraldeep.tech/docs#vision
- Structured output — https://neuraldeep.tech/docs#structured
- Agents · tools — https://neuraldeep.tech/docs#agents
- Search · Search API — https://neuraldeep.tech/docs#search
- OCR · documents — https://neuraldeep.tech/docs#ocr
- Images · Image API — https://neuraldeep.tech/docs#images
- PII anonymization · PII Guard — https://neuraldeep.tech/docs#guardrails
- SpeechCore · STT — https://neuraldeep.tech/docs#speechcore
- Speech synthesis · TTS API — https://neuraldeep.tech/docs#tts
- Book · search and MCP — https://neuraldeep.tech/docs#book-api

Drift API:
- Drift · overview — https://neuraldeep.tech/docs#drift-api
- Files + sandbox preview — https://neuraldeep.tech/docs#drift-files
- Your own tools, skills, MCP — https://neuraldeep.tech/docs#drift-caller-tools
- Tasks · proactive — https://neuraldeep.tech/docs#drift-tasks
- Agent builder — https://neuraldeep.tech/docs#agent-hosting
- Memory · memory — https://neuraldeep.tech/docs#drift-memory
- Isolation and security — https://neuraldeep.tech/docs#drift-security

Limits:
- Limits · errors — https://neuraldeep.tech/docs#limits

Reference:
- Streaming — https://neuraldeep.tech/docs#streaming
- SDK · Python / JS — https://neuraldeep.tech/docs#sdk
- Privacy — https://neuraldeep.tech/docs#privacy

## Ecosystem
- [NeuralDeep Search — free AI deep-research search](https://search.neuraldeep.ru/) · its own /llms.txt
- [SpeechCore — audio/video transcription (WhisperX) + TTS](https://speechcore.neuraldeep.tech/) · its own /llms.txt
- [Skills & MCP catalog for RU agents](https://neuraldeep.ru/skills)
- [Service status](https://status.neuraldeep.ru/)

## Optional
- [Dashboard — keys, limits, privacy toggles](https://neuraldeep.tech/app)