Transparent pricing
Simple pricing for AI you can trust. Viewers free, and unlimited AI credits included.
Free
See what your team and AI can find together. No card required.
Get startedIncludes:
- 1 project, 3 canvases
- Up to 5 users
- Daily AI credit limits (limited models)
- 1 database/MCP connection, web search, file uploads
- 2 automations
- Community support
Pro
Everything a small team needs to dig into their business.
Viewers free
Get startedEverything in Free, plus:
- Unlimited AI credits*
- Unlimited canvases, projects, reports & automations
- 3 database/MCP connections
- Shared agent skills & context
- 4GB compute capacity (Python VM & dataset extract size)
- Slack integration and MCP client
- Email, Slack or Teams support
Enterprise
Run Count at scale across your organization.
Get in touchEverything in Pro, plus:
- Unlimited editors
- Choose your own models or bring your own API keys
- Unlimited database connections
- Governed semantic layer & admin change approvals
- Up to 32GB compute capacity
- REST API
- Workspace telemetry
- User groups, row-level security & embedded analytics
- SSO, SCIM, HIPAA, EU/US data residency
*98% of teams never need to top up their AI credits.
Workspace users
Everyone in your workspace, whatever their role.
User roles
Owners, Admins and Editors are billable seats. Viewers and Report Viewers are free.
Projects
Group canvases by team or topic.
Canvases
Infinite workspaces for exploring and presenting data.
Reports & dashboards
Publish from your canvases.
Scheduled reports
Send reports by email and Slack on a schedule.
Agent automations
Scheduled runs of Count's agent.
Custom templates
Reusable canvas templates.
Version history
Snapshot and restore previous versions.
Custom fonts and styles
Keep every canvas on brand.
Public sharing
Share canvases via link.
Domain whitelisting
Auto-join for your team.
Internal embedding
Embed canvases in Notion, Confluence and similar tools.
User groups
Manage access by group.
Row-level permissions
Control which rows each user can see.
White-label embedded analytics
Embed Count in your own product, under your brand.
AI credits
Count matches every step to the right model, balancing cost and performance. *98% of teams never need a top-up.
Credit top-ups
Available if you need them.
Model selection
Count picks the best model for each step. Enterprise can also choose its own.
Bring your own API key
Anthropic, OpenAI, Google, or custom endpoints.
Database & MCP connections
BigQuery, Snowflake, Postgres and more, plus MCP connections.
dbt integration
dbt Core and dbt Cloud.
Web search
Let the agent search the web.
File upload
CSV, PDF, Excel, Word and more.
Google Sheets
Import data from Google Sheets.
Slack integration
Ask Count's agent from Slack.
Count MCP server
Control Count from Claude, Cursor or VS Code.
Canvas and query REST API
Programmatic access to canvases and queries.
Workspace management REST API
Control workspace members and permissions.
Agent context
Context at workspace, project and data source level.
Agent skills
Shared, reusable skills for the agent.
Count Metrics
Semantic layer, compatible with Apache Ossie.
Change approvals
Review changes to context, skills and metrics.
Agent prompt analytics
See what your team asks the agent.
Compute layer capacity
The largest table Count's DuckDB compute layer can hold, so less load lands on your database.
Python VM size
Memory for Python cells.
Scheduled query caching
Set refresh rules for cached queries.
SOC 2 and GDPR
Security and data protection on every plan.
No model training on your data
On every plan.
Google and Microsoft login
Sign in with Google or Microsoft.
SSO
Single sign-on with your identity provider.
SCIM provisioning
Sync users from your directory.
Session duration controls
Enforce logout policies.
Data residency controls
Choose US or EU hosting.
HIPAA compliance
Healthcare security standards.
Export controls
Restrict data exports.
Community support
Access to the Slack community.
Email, Slack, and Teams support
Direct access to the success team.
Onboarding
Guided implementation for your team.
Custom training programs
Tailored education programs for your team.
FAQ
Count combines an AI workspace with a BI tool. Like AI workspaces such as Dust or LangDock, it gives your team agent skills and MCP connections. Like BI tools such as Looker, Lightdash or Sigma, it has live reports, a semantic layer and native database connections. On top of both, it adds Python, real-time collaboration and hallucination detection, so one platform can replace your BI tool and your AI workspace.
Chatbots like Claude, ChatGPT and Gemini are built for one person asking one question. Count adds what analytical work needs on top: live reports, a semantic layer, native database connections, real-time collaboration and no usage caps. Above all, Count is built for answers you can trust. Every claim is traced to its source, assumption or inference, so hallucinations are caught before anyone acts on them.
In three ways. First, AI makes research and analysis dramatically faster, so your team can answer any question they have instead of waiting on an analyst. Second, Count's analytics engine runs computation efficiently, taking day-to-day queries off your warehouse so you pay less for compute. Third, Count cuts the errors and hallucinations that make other AI tools slow to trust. We estimate checking AI outputs costs the average knowledge worker $6–8k a year, a saving traditional chatbots can't offer. How Count's analytics engine works →
Pro and Enterprise include AI credits on a fair-use basis. Count matches every step to the right model, balancing cost and performance, so 98% of teams never need a top-up. If you do, top-ups are available with spend controls. Free workspaces have a daily AI credit limit. Enterprise can also choose its own models or bring its own AI API keys.
Owners, Admins and Editors are the seats you pay for: they build with SQL, Python, low-code and Count's AI agent. Viewers can explore and collaborate in canvases, and Report Viewers see the presentation layer only; both are free. Admins are available on Enterprise.
All major debit and credit cards are accepted. You can manage billing directly from your workspace settings.
Yes. You can add or remove seats at any time through your workspace settings. Changes are prorated automatically.
Count is SOC2, GDPR, and HIPAA certified with up-to-date security procedures. Your data is never used for training AI models.