--- title: "Configure your model prices | Grafana Cloud documentation" description: "Set the prices you pay for LLM models so Agent Observability cost figures match your contract." --- > For a curated documentation index, see [llms.txt](/llms.txt). For the complete documentation index, see [llms-full.txt](/llms-full.txt). # Configure your model prices Agent Observability estimates the cost of each generation from its token usage and a price for the model that served it. By default, it uses public list prices from the model card catalog. If you pay a different price, set your own price for that model. Examples are a negotiated rate, a committed-use discount, a reseller agreement, or a model the catalog doesn’t carry. Agent Observability uses your price for the generations it receives from then on. ## How your prices apply Your price for a provider and model replaces the catalog price for that pair: - **It replaces the catalog price completely.** Agent Observability doesn’t fill in missing token types from the catalog. Set a price for every token type your contract covers. A token type without a price isn’t charged. - **It applies from the moment you set it.** Generations that Agent Observability already received keep the cost they were given. - **A change adds a new price.** To change a price, set a new one. The earlier price still covers the period when it applied. - **Prices are in USD per million tokens**, the way providers publish them. You can also set a per-call fee, and long-context prices. When a call’s input, including cached tokens, is above the long-context threshold, every token in that call is charged at the long-context prices. A token type without a long-context price keeps its normal price. Set a price to `0` when a token type is free. Omitting a base price also contributes no cost, but you must supply at least one base token price or per-call fee to save a model price. A long-context price alone isn’t enough. For a long-context price, `0` makes that token type free above the threshold; omitting it keeps the base price. ## Where you see your prices Cost figures in **Analytics**, **Agents**, **Conversations**, and **Needs attention** use your prices. In a conversation, each call is priced at the price in force when it ran. The cost tooltip says whether a figure comes from your prices or from public list prices. Grafana Assistant also uses your prices when it answers questions about cost, and so do the cost reports you schedule with **Add report**. Experiment trials also use your prices when Agent Observability calculates a missing cost from linked conversation usage. It uses the rate in force at each model’s latest generation in that conversation, or the catalog price if you haven’t set a rate for that period. Costs supplied by your test runner stay unchanged. For details, refer to [Interpret experiment costs](/docs/grafana-cloud/observe-and-act/agent-observability/evaluate-and-improve/experiments/#interpret-experiment-costs). Some figures still use public list prices: - Filtering or breaking down cost by a label other than provider, model, or agent calculates cost from token counts at list prices. The page shows a **Cost shown at list prices** notice when this happens. - LLM judge cost estimates use catalog prices, because Agent Observability runs judges with its own provider credentials. ## Who can see your prices Your prices aren’t secret from people who can view Agent Observability data. Anyone with the `grafana-agento11y-app.data:read` permission sees costs calculated with your prices, and can work out a price by dividing a cost by its tokens. The conversation view also reads your prices to price each call. Only users with the `grafana-agento11y-app.pricing:write` permission can set, list, or delete them. ## Before you begin Before you set your prices, make sure you have the following: - [gcx](https://github.com/grafana/gcx) 1.4.0 or later, logged in to your Grafana Cloud stack. - The `grafana-agento11y-app.pricing:write` permission. The Agent Observability Admin role includes it, and Grafana Admins have that role by default. For more information, refer to [Configure RBAC](/docs/grafana-cloud/observe-and-act/agent-observability/privacy-and-access/security/#configure-rbac). ## Set a price for a model Use the provider and model names exactly as Agent Observability shows them, for example in the provider and model filters on **Analytics**. sh ![Copy code to clipboard](/media/images/icons/icon-copy-small-2.svg) Copy ```sh gcx agento11y model-rates create --provider --model \ --price-input --price-output ``` Replace the following: - PROVIDER: the provider, for example `openai`. - MODEL: the model, for example `gpt-5`. - INPUT\_PRICE: what you pay in USD per million input tokens. - OUTPUT\_PRICE: what you pay in USD per million output tokens. If your contract has other charges, add `--price-cache-read`, `--price-cache-write`, or `--price-request`. For a long-context tier, add `--long-context-threshold` and the `--long-context-price-*` flags. ## List your prices To review the prices you set and when each took effect, run: sh ![Copy code to clipboard](/media/images/icons/icon-copy-small-2.svg) Copy ```sh gcx agento11y model-rates list ``` ## Delete a price To delete a price, find the time it took effect in the `list` output, then run the following command. gcx asks you to confirm before it deletes the price. sh ![Copy code to clipboard](/media/images/icons/icon-copy-small-2.svg) Copy ```sh gcx agento11y model-rates delete --provider --model \ --effective-from ``` Replace EFFECTIVE\_FROM with the time from the `list` output. After you delete the price in force, Agent Observability uses your previous price for that model, or the catalog price if there’s none. Dashboards keep the costs they already calculated. A conversation prices each call from your remaining prices, so the calls the deleted price covered show the price that applies without it. ## Next steps - [Optimize cost and performance](/docs/grafana-cloud/observe-and-act/agent-observability/observe-and-troubleshoot/cost-optimization) - [Monitor agents with analytics](/docs/grafana-cloud/observe-and-act/agent-observability/observe-and-troubleshoot/dashboards)