Pricing

Start free. Pay for what you need to approve it.

The Open SDK is free, self-hosted, and yours to read line by line. Everything above it is the shared intelligence that keeps building, testing, and governing your agents underneath — and every number on this page is pulled from the same rate table the platform actually bills against.

Open

Individual engineer, no procurement

$0 — free

+5,000 welcome tokens on signup

  • Vouchstone Open SDK + standalone harness runtime
  • Self-hosted, bring your own LLM keys
  • Command-line tools to build and test agents
  • No credit card or account required to start
Get started
Most common

Platform

Team self-serving past free tier

$59/seat/mo + metered overage

Minimum 50 seats · +2,000 tokens/seat/mo included

  • Hosted extraction pipeline, self-serve KG wizard
  • Wiki, Company Brain + Council
  • Agent Studio, Agent Harness, Evals, and Guardrails included
  • Monthly token allowance per seat, then metered overage
Get started

Enterprise

Security/compliance-gated rollout

$59/seat/mo + $15,000/agent/yr

Minimum 50 seats · +2,000 tokens/seat/mo included

  • Everything in Platform
  • Agent Optimization tuning, custom rules for agent behavior, full autonomy control
  • Fine-grained access controls, dedicated budget, exportable audit trail
  • Dedicated support team
Get started

Sovereign & Air-Gapped

Highly regulated industries

Contact us

Custom annual license — priced per engagement

  • Everything in Enterprise
  • Signed, fully self-hosted deployment package
  • Turnkey self-hosted LLM inference — no external API calls, ever
  • Custom annual license, scoped and quoted per engagement
Talk to us

Implementation acceleration and messy-data-estate modeling are available as an optional services add-on layered on any paid tier — never a required entry point. Not sure which tier fits? Run the free pre-assessment for a computed recommendation.

Full metered rate table

Platform and Enterprise seats include 2,000 tokens/seat/mo — usage beyond that draws from this same rate table (1 USD = 100 Vouchstone tokens). This is the exact same rate table the backend bills against, not a marketing approximation.

OperationCost (Vouchstone tokens)≈ USD (100 tokens = $1)
Agent execution — simple chat15$0.15
Agent execution — complex (tools/RAG)75$0.75
Agent execution — advanced multi-step reasoning150$1.50
Create an agentFree
Update an agentFree
Workflow run — base25$0.25
Workflow — additional step10$0.10
Workflow run — complex (conditionals)100$1.00
Create a workflowFree
Update a workflowFree
Collective coordination — base75$0.75
Collective — additional agent25$0.25
Collective — consensus mechanism50$0.50
Memory query (semantic search/retrieval)5$0.05
Memory store — per 100 vectors10$0.10
Memory store — per 1K vectors50$0.50
Memory — advanced vector search8$0.08
Memory consolidation job25$0.25
Document ingested20$0.20
Document chunk created5$0.05
Document indexed15$0.15
External API call2$0.02
Integration sync (Slack, JIRA, etc.)10$0.10
Integration event received5$0.05
Webhook trigger3$0.03
LLM input — per 1K tokens2$0.02
LLM output — per 1K tokens6$0.06
LLM embedding — per 1K tokens1$0.01
Decision graph traversal30$0.30
Decision graph — node evaluated5$0.05
Decision graph — conditional branch8$0.08
Optimization Studio — DSPy run250$2.50
Fine-tuning job1,000$10.00
Fine-tuning job — large model2,000$20.00
A/B test variant50$0.50
Storage — per GB/month25$0.25
Bandwidth — per GB10$0.10

Show your work

Every quote from the pre-assessment is computed from the same public formula — no negotiated black box. Here it is worked through for one illustrative scenario: a compliance-evidence rollout across Jira, Confluence, GitHub, and Slack, 12,000 documents, 2,500 governed agent actions a month.

Recommended tier

platform

Computed price (monthly)

$2,413 – $2,975

Your inputs
Connectors selectedjira, confluence, github, slack
Use casecompliance_evidence
Estimated document count12,000
Estimated monthly agent actions2,500
Sovereign / air-gapped requiredNo
Industry
Revenue Band
Employee Band
Geography
RegulatoryNone
Scale scoring
Connector count4
Document volume index (0-3)2
Action volume index (0-3)1
Connector index (0-3)1.2
Use-case complexity weight1.4
Base Scale Score1.96
Employee Band Nudge0
Revenue Band Nudge0
Composite scale score (0-~4.2)1.96
Modeling assumptions
Extraction passes per document5
Avg. input tokens / document pass3,000
Avg. output tokens / document pass500
Avg. input tokens / agent action4,000
Avg. output tokens / agent action400
Ingestion cost amortized over (months)3
Price computation
LLM pricing model used for COGSclaude-sonnet-5
Total ingestion input tokens180,000,000 tokens
Total ingestion output tokens30,000,000 tokens
Ingestion compute cost (COGS)$990
Monthly agent-action input tokens10,000,000 tokens
Monthly agent-action output tokens1,000,000 tokens
Monthly agent-action compute cost (COGS)$45
Amortized ingestion cost / month330
Total monthly recurring COGS$375
Gross-margin multiplier (low)2.5×
Gross-margin multiplier (high)
Estimated Seats25
Estimated Seats Was DefaultedNo
Seat Price Usd Monthly59
Seat Price Total Usd Monthly1,475
Metered component (low)$937.5
Metered component (high)$1,500

Every dollar figure on this page traces back to a real backend constant served by GET /api/v1/billing/rates or GET /api/v1/pre-assessment/example — nothing here is hardcoded in the frontend, and a backend test asserts these numbers can never silently drift from what the platform actually bills.