Try for free

Grill is the full context engine — ingestion, chunking, and querying for one fixed monthly price.

Every account starts with 10,000 free pages and 10,000 queries a month — no plan required to try Grill.

Show prices:

Free plan

Free

For trying Grill on real workloads — no credit card required.

Free
  • Queries 10,000 / month
  • Ingest —  
  • Burst 10,000 pages
  • Storage 10,000 pages
Try for free
Solo builder

Starter

For small projects getting a RAG pipeline off the ground.

€89 / month
  • Queries 75,000 / month
  • Ingest 200 pages / day
  • Burst 40,000 pages
  • Storage 175,000 pages
Get started
Small team

Professional

For teams shipping production agents on real workloads. Our most popular option.

€199 / month
  • Queries 200,000 / month
  • Ingest 450 pages / day
  • Burst 100,000 pages
  • Storage 500,000 pages
Get started
Small business

Business

For growing businesses scaling RAG across multiple products.

€399 / month
  • Queries 400,000 / month
  • Ingest 900 pages / day
  • Burst 200,000 pages
  • Storage 1,000,000 pages
Get started
High volume

Advanced

For high-volume deployments with demanding workloads.

€719 / month
  • Queries 800,000 / month
  • Ingest 1,800 pages / day
  • Burst 400,000 pages
  • Storage 1,900,000 pages
Get started

Features
Included in every Grill plan.

Ingestion & chunking

  • Grill ingest from console, URL, API, SDK, CLI, and MCP server.
  • Patented structure-aware chunking, OCR-aware on scanned PDFs.
  • 50+ filetypes supported including tables and visual content.

Initial burst uploads

  • Your ongoing ingest allowance (pages / day) covers steady-state operation. On top of it, every plan includes a one-time "burst upload" allowance during your first few months — bring in your existing corpus without touching the daily limit.
FreeStarterProfessionalBusinessAdvanced
10,000 pages40,000 pages100,000 pages200,000 pages400,000 pages

Retrieval & query

  • End-to-end retrieval and ranking out of the box.
  • SDK, REST API, and MCP server for direct agent integration.
  • Hierarchical chunks returned with full source context.

Integration

  • Drop in alongside LangChain, LlamaIndex, or any agent stack.
  • OpenAPI spec + typed SDKs.

Reliability & support

  • Uptime SLA on paid plans.
  • Email + chat support; dedicated channel from Business tier.