Simple, transparent pricing

Choose the plan that's right for you

Free trial with limitations

Free

Single application (no deployment)
Limited retrieval optimization
Limited generation optimization
Support for limited foundation models
Support for structured and unstructured data
Natural language database queries
Set your own PineCone and OpenAI keys to remove limitations on the number of files, hyperparameter combinations, and benchmark answers

For teams ready to scale

USD 499

20 Applications with 5 cloud deployments
Retrieval optimization including identification of the optimal chunking strategy, embedding options, distance metrics, query preprocessing, and reranking methods
Generation optimization including identification of the best prompts and the most suitable LLMs
Support for major foundation models
Support for structured and unstructured data
Natural language database queries
Metadata filtering
Access to beta features
Optional: $200/month consultation support add-on per application

Custom solutions for large teams

Contact Sales

Unlimited Applications & Deployments
Everything in Pro Package plus the following:
Automatic embedding and LLM fine-tuning with Grid search and Bayesian optimization
Ability to deploy at scale on QL cloud
Extensive Custom Support by top LLM experts
Custom-built optimized applications by our LLM experts over your data

Features	Starter	Pro	Enterprise
Core Features
Prompt Optimization Prompt Optimization focuses on enhancing the instructions given to a language model (LLM) to improve the quality of its outputs.
Retrieval Optimization Retrieval optimization involves the strategic identification of optimal chunking methodologies, embedding techniques, distance metrics, query preprocessing methods, and reranking approaches to significantly enhance information retrieval efficacy.
API & Keys
Data & Applications
Team & Users
Advanced Features

Please note that the costs for the LLM API and Vector Database API are exclusive and not included in the base subscription fee