--- title: "Understand Grafana Assistant pricing and usage | Grafana Cloud documentation" description: "Learn how Grafana Assistant pricing works, what is billed, and where to find current rates." --- > For a curated documentation index, see [llms.txt](/llms.txt). For the complete documentation index, see [llms-full.txt](/llms-full.txt). # Understand Grafana Assistant pricing and usage Grafana Assistant is billed based on usage. Grafana Assistant Investigations is currently in public preview and has no charge. This article explains how pricing works, defines billing terms, and shows you where to find current rates and included usage. Pricing details and plan tiers change over time. Refer to the [Grafana pricing page](/pricing/) for the latest rates and what each plan includes. Different plan types offer different pricing structures and included usage, including free tiers for trial and limited use. ## Before you begin - Confirm you can open Assistant and Assistant Investigations in your stack. - Connect with your Grafana Labs account contact for billing and usage questions. ## Understand what is billed Assistant and Assistant Investigations are separate products with independent billing. Each product has its own billing unit and pricing model. Assistant billing depends on your plan and usage. This billing is independent from other Grafana Cloud features like visualization or IRM. If you use Assistant from a self-managed Grafana deployment, usage is still tracked against the paired Grafana Cloud stack. The LLM plugin is open source and has no charge. ## Know the pricing model The pricing model uses different billing units for each product. Grafana Cloud offers different plan types for Assistant, including self-serve and contracted options. Each plan type has different pricing structures and included usage allowances. Refer to the [Grafana pricing page](/pricing/) for current plan details and what’s included in each tier. ### Active users An active user is anyone who sends a message to Assistant, presses an action button like **Explain this panel**, connects through the [Grafana Cloud MCP server](/docs/grafana-cloud/machine-learning/assistant/configure/cloud-mcp), or uses another Assistant feature within the billing period. The billing period is one month. ### Token-based usage Grafana Assistant uses token-based usage. A token is the basic unit of content processed by an AI model. Token usage is counted across Assistant surfaces, including integrations, Slack, Microsoft Teams, service accounts, and the gcx CLI. For Pro plan users, token limits aren’t set by default. Administrators can configure monthly token limits to manage Assistant usage for their stack. If a configured limit is reached, Assistant prevents further use for that limit until the next monthly reset or until an administrator changes it. For Free plan users, monthly token limits are enforced as hard limits. When usage reaches a limit, Assistant prevents further use for that limit until the next monthly reset. ### Investigation limits Grafana Assistant Investigations includes a soft limit for investigations per user each month. Grafana Labs may reach out when usage stays above this limit so you can agree on the path forward. ### Grafana Labs support usage When Grafana Labs employees work on your stack on behalf of your organization, their Assistant activity doesn’t count toward active users or your stack’s token usage. This applies when Grafana Labs staff provide support or troubleshooting assistance. ### Volume discounts Volume discounts are available for contracted accounts. Assistant and Assistant Investigations are billed separately, so discounts are applied per product rather than bundled across both. ## Understand conversation limits Grafana Assistant shows the current state of limits that affect your current conversation or your ability to send messages. Each conversation includes a context limit indicator that shows how much of the chat fits in the current context window. If a conversation gets close to the model’s context window, Assistant may compact the conversation. If a request exceeds the context window, Assistant may offer to start a new chat with a summary. When monthly usage reaches 75% of a configured limit, Assistant shows a warning indicator in the chat input with current usage details. When a limit is exhausted, Assistant shows a limit message and prevents further use for that limit until it resets or the limit is changed. ## View organization usage analytics The Usage Analytics dashboard helps you track consumption and plan your budget before billing begins. Navigate to **Assistant > Usage** to access the Usage Analytics dashboard. This dashboard shows active users, messages, investigations, and total used tokens for your stack. Access to this page requires `grafana-assistant-app.usage:read`. By default, `grafana-assistant-app.usage:read` is included in the **Assistant Admin** role, and that role is granted to the Grafana organization **Admin** basic role. You can also view your current usage against limits for tokens and investigations directly in the dashboard. This visibility helps you track how close you are to reaching limits associated with your plan. You can filter the dashboard by time range to understand adoption patterns and usage trends. Use the time range picker to select Last 7 days, Last 30 days, or Last 90 days. This helps you plan budgets and communicate with stakeholders about expected costs. Ask your Grafana Labs contact for usage summaries if you don’t have access to Usage Analytics. Your contact can provide reports and help you understand your usage patterns. ## Control organization access and limits You can manage who has access to Assistant and configure usage limits. Use the limits controls to set monthly user and token limits, or use RBAC to restrict access to specific users and teams. ### Set usage limits Navigate to **Assistant > Usage**, open the **Active Users** view, and click **Edit limits** to configure the maximum unique users per month for your stack. Set the monthly active user limit to 0 to disable the cap and allow unlimited active users. When you set a positive number, the system tracks monthly active users against this cap. The settings display your current monthly active users count alongside the configured limit. You can also configure monthly token limits from the **Tokens** view by clicking **Edit limits**. Token limits are entered in millions of tokens and can apply to the whole stack, to the default per-user limit, and to the shared service account total. In Grafana Cloud, you can also set per-user token limits for specific teams. If a user belongs to multiple teams with token limits, the highest per-user team limit applies. The stack limit applies to total token usage across the stack, regardless of per-user, team, or service account limits. The limits controls require the `grafana-assistant-app.usage:write` permission. By default, this permission is also included in the **Assistant Admin** role. Click **Save** to apply your changes. ### Restrict access with RBAC Use role-based access control (RBAC) to restrict Assistant access to specific users or teams. You can modify custom roles to include or exclude Assistant permissions. This gives you fine-grained control over who can use Assistant features. Changing basic role definitions to remove Assistant access may have other impacts on user permissions. Contact Grafana Labs support if you need help with RBAC configuration. Your support contact can review your requirements and recommend the best approach for restricting access or managing costs. ## Billing Billing for Grafana Assistant started on January 1, 2026. Assistant Investigations continues to be free during the public preview. Review your usage dashboard regularly to understand patterns and budget accordingly. To restrict access or adjust usage caps, refer to [Control organization access and limits](#control-organization-access-and-limits). ## Next steps - [Grafana pricing page](/pricing/) - [Connect AI agents with Cloud MCP](/docs/grafana-cloud/machine-learning/assistant/configure/cloud-mcp) - [Run investigations](/docs/grafana-cloud/machine-learning/assistant/guides/investigation)