Pricing

Flow

Optimize your AI workflows without the complexity
$2
per million tokens
Includes:
5 million tokens/mth free
Basic summarization
Real-time chunking
Send the whole document at once or in pieces - we'll automatically detect and chunk it for you
Standard queue
Burst requests may treated individually during high demand periods
Standard support
Email or Slack - we'll respond within a business day.
Semantic anchoring
Limited compounding benefits across queries
Embedding management
Caching
Save on token costs by caching frequently occurring text
Perfect for:
One-shot research
Processing support tickets
Maximizing context windows
Content moderation
Data scrubbing

Form

Build lasting value from every interaction.
$5
per million tokens
Includes:
Everything in Flow
Preserves relationships across documents, enabling reliable information flow between AI systems and maintaining context integrity over time
Semantic anchoring
Caching
Save on token costs by caching frequently occurring text
Priority queue
Get faster processing during high-demand periods with batched requests and guaranteed response times.
Advanced metadata
Attach custom fields, track versioning, and maintain rich context for each interaction.
Priority Support and Onboarding
Direct access to our technical team and personalized onboarding to optimize your implementation.
Embedding Management
Custom infrastructure
Perfect for:
Multi-agent systems
Access long-form blog building tools
Building RAG systems
Access long-form blog building tools
Training data generation and maintenance
Access long-form blog building tools

Foundation

Full control and specialized optimizations.
Custom
per million tokens
Includes:
Everything in Foundation
All features from our Foundation tier included, with enterprise-grade infrastructure
Dedicated servers
Your own isolated compute resources for consistent performance and maximum security.
Deployable on premises
Full deployment within your security perimeter, meeting the strictest compliance requirements.
Embedding management
Complete control over embedding models, including custom model support and version management.
Model routing
Intelligent routing between different models based on task requirements and cost optimization.
White glove set up
Full implementation support from our technical team, including custom integration assistance
Access to domain specialization
Specialized models and optimizations for your industry vertical (legal, financial, healthcare).
Dedicated support
24/7 support access with guaranteed response times and a dedicated technical account manager.
Perfect for:
Customer facing systems
Access long-form blog building tools
Enterprise knowledge bases
Access long-form blog building tools
Meta-agent workflows
Access long-form blog building tools

Calculator

Cut LLM Costs with RAG

See how much you could save by using Retrieval-Augmented Generation (RAG) to optimize your AI operations. Lower costs, higher accuracy, better business outcomes.

Stay on the cutting edge.

Stay up to date on what we add next.

Thank you! Your submission has been received!
Something went wrong while submitting the form. Take a look and try again.