Outlines

Key Features

What the engine gives you out of the box, in plain language.

• OpenAI-Compatible API
• NVIDIA GPU
• AMD GPU
• Apple Silicon
• CPU Inference
• Quantization
• Continuous Batching
• Multi-GPU
• Desktop GUI
• One-Line Install
• Structured Output
• Streaming

• Schema-constrained output

  Pass a Pydantic model or JSON schema and get matching output back.

• Regex and grammar control

  Constrain output to a pattern or a formal grammar when JSON is not enough.

• Backend-agnostic

  Run on top of Transformers, vLLM, and other engines.

Where It Shines

The jobs this engine is best suited for.

• Reliable JSON output

  Extract structured data from text without parsing failures.

• Tool and function calls

  Force arguments to match a function signature exactly.

• Data pipelines

  Feed downstream systems output that always matches the expected shape.

Frequently Asked Questions