LoginGet a DemoStart for FreeLogin
DocsPricing

Pricing that scales with your workload

Choose on‑demand, usage-based pricing for flexibility, or provisioned throughput for guaranteed performance with monthly commitments.

Plans & Pricing

On-demand

Pay-as-you-go pricing that scales with your usage of the platform

Claim your $25 in free credits

Query:

Approx. $0.05 per query
(Actual price depends on total tokens processed)


Document ingestion:

$48.50 per 1,000 pages

Get started

Provisioned throughput

Guaranteed capacity for predictable throughput performance

Model unit:

Each model unit provides a guaranteed minimum throughput and can be purchased with a monthly minimum commitment

Contact sales

Compare features

Platform management

Number of users

Unlimited

Number of workspaces

Unlimited

Number of agents

Unlimited

Number of datastores

Unlimited

Number of workspaces

1

User roles and admin permissions

Document access entitlements

SOC2 Type II compliance

HIPAA compliance

SAML / SSO

Role-based access control (RBAC)

Usage analytics

Usage analytics

Pipeline observability

Uptime SLA

Pipeline observability

Data ingestion

Support for simple text documents

Support for complex docs, charts, and images

Support for unstructured data

Support for structured data

Contact sales

UI-based ingestion

Continuous data ingestion

Contact sales

Data integrations

Maximum of 1

Standard data retention

Custom data retention

Contextual AI agents

Query optimization

Reformulates and decomposes query for better retrieval

Retrieve

Gets relevant docs from knowledge base

Rerank

Reorders relevant docs by relevance

Filtering

Selects top-k most relevant docs

Generate

Produces response using selected docs

Groundedness & safety

Evaluates whether generated response is supported by retrieved docs

Tokens per second (TPS) throughput Commitment

Deployment

Contextual SaaS

Customer VPC

Contact sales

Components

Component APIs pricing overview

For AI teams needing more flexibility to work with their existing RAG architecture, Contextual AI provides powerful platform primitives as component APIs with usage-based pricing.

Parse

Our multi-stage document understanding pipeline for converting unstructured content into AI-ready formats

Price

  • Basic (text only): $3 / 1,000 pages
  • Standard (multimodal): $40 / 1,000 pages

Rerank

State-of-the-art instruction-following reranker, providing greater control over how retrieved knowledge is prioritized

Price

  • Rerank-v2: $0.05 per million tokens
  • Rerank-v2-mini: $0.02 per million tokens

Generate

The most grounded large language model in the world, engineered specifically to minimize hallucinations

Price

  • Input: $3 / 1M tokens
  • Output: $15 / 1M tokens

LMUnit

Our evaluation-optimized model for preference, direct scoring, and natural language unit test evaluation

Price

  • Input: $3 / 1M tokens