Quick Start
Quickstart
Most Popular
Create an account, prepare training data, fine-tune a model in Fine-tune Studio, deploy it, and call the API in minutes.
Getting Started by Role
Find the best starting point based on your role: Developer, Data Scientist, DevOps, or Product Manager.
Introduction
Understand the platform at a glance and the integrated products that make up LLMTune.
Core Features
Coding Plans
New
Get a fixed quota of AI requests for coding in Cursor and other IDEs. Choose from Basic, Med, or Pro Vibe Coder plans.
Pricing & Billing
Understand costs, plans, and how to optimize your spending.
Core Concepts
Learn how workspaces, model configuration, and usage metering fit together.
Security & Compliance
Learn about workspace isolation, access control, API key security, audit logs, and data privacy.
Documentation
API Reference
Integrate LLMTune programmatically with REST endpoints, authentication, and OpenAI-compatible inference.
Fine-tuning Guide
Follow the full workflow for launching a training job in Fine-tune Studio with all training methods and modalities.
Deploy & Monitor
Use LLMTune Deploy to promote fine-tuned models to endpoints, manage versions, and control traffic.
Evaluate Models
Test models with single prompts, compare fine-tuned vs. base models side-by-side, and run batch evaluations.
Troubleshooting
Resolve common issues with training, deployment, and API usage.
Resources
Tutorials
Build real-world applications with step-by-step tutorials.
Glossary
Look up key terms and concepts used in LLMTune documentation.
Roadmap
Track what is actively shipping and what is queued next for the platform.
FAQ
Find answers to the most common workspace, training, deployment, and API questions.
Framework Integrations
Integrate LLMTune with LangChain, LlamaIndex, and the OpenAI SDK.