New: SLMs outperform frontier LLMs on narrow enterprise tasks by up to 34% — Read the ScaleDown AI benchmark →
Products
⚡ Platform 🧠 Model Catalog 📖 Documentation
Solutions
🏥 Healthcare ⚖️ Legal 📈 Finance 🔧 Manufacturing
More
📊 Benchmarks 💳 Pricing 🔑 Sign In Deploy a model →
Documentation

From zero to
production in 60s.

Everything you need to deploy, fine-tune, route, and observe SLMs and LLMs on Quantum Junction.

Quickstart → API Reference
🚀

Quickstart

Deploy your first model in under 60 seconds. Covers installation, authentication, and your first inference call.
📡

API Reference

Full OpenAI-compatible REST API documentation. Deployments, inference, fine-tuning, and routing endpoints.
🐍

Python SDK

The official Quantum Junction Python SDK. Async-first, type-annotated, fully compatible with LangChain and LlamaIndex.
Quickstart

Deploy your first SLM in 60 seconds

Three steps: install the SDK, authenticate, deploy.

1. Install the SDK

# pip install pip install quantumjunction

2. Set your API key

export QJ_API_KEY="qj_your_key_here" # or in Python: import quantumjunction as qj client = qj.Client(api_key="qj_...")

3. Deploy and call a model

# Deploy a model from HuggingFace dep = client.deployments.create( model="hf/microsoft/phi-3-mini-4k", hardware="a10g", ) # Call it — OpenAI-compatible resp = client.chat.completions.create( model=dep.id, messages=[{"role": "user", "content": "Classify this ICD code: J18.9"}] ) print(resp.choices[0].message.content)
API Reference

OpenAI-compatible REST API

All endpoints follow the OpenAI API specification. Drop in your Quantum Junction API key and base URL — your existing code works without modification.

# Base URL https://api.quantumjunction.com/v1 # Authentication header Authorization: Bearer qj_your_key # Chat completions (OpenAI-compatible) POST /chat/completions POST /completions POST /embeddings # Model management GET /deployments POST /deployments GET /deployments/{id} DELETE /deployments/{id} # Fine-tuning POST /fine-tuning/jobs GET /fine-tuning/jobs/{id} # Routing POST /route # smart SLM/LLM routing

SDKs

Official SDKs for Python, TypeScript/Node, and Go. All async-first, fully typed. Compatible with LangChain, LlamaIndex, and Haystack.

Webhooks

Subscribe to deployment events, fine-tuning job completion, and inference anomalies via webhook. HMAC-signed payloads.

OpenAI drop-in

Change two lines — your base_url and api_key — and your existing OpenAI-based code runs on Quantum Junction with no other changes.

Ready to deploy your exact-fit model?

Start free in under 60 seconds. No GPU reservations. No minimum commits.

Deploy now — it's free → Read the docs