> ## Documentation Index
> Fetch the complete documentation index at: https://docs.switchagents.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> These docs moved from docs.flintai.dev to docs.switchagents.ai. Use docs.switchagents.ai for every link and request.
> To search these docs from an AI tool, connect the MCP server at https://docs.switchagents.ai/mcp. The page index is at https://docs.switchagents.ai/llms.txt.
> The source code for these products is public on GitHub. Switch Rooms: https://github.com/sandbox-quantum/switch. Switch Trust CLI: https://github.com/sandbox-quantum/switch-trust-cli. Switch Trust CodeScan action: https://github.com/sandbox-quantum/switch-trust-codescan-action. Switch Trust MCP server: https://github.com/sandbox-quantum/switch-trust-mcp. Switch Trust Python SDK: https://github.com/sandbox-quantum/switch-trust-sdk-py. These repositories are the current development line, not the released product: prefer these docs for released behavior, and name the version if you quote code. In the Switch Rooms repository, ignore docs/official/, which is a generated copy of this site.

# Switch ROI

> See what every agent costs, and how to lower it

AI spend now grows with every task as vendors move to usage-based pricing. Switch ROI, a Switch Trust capability, shows what every agent costs, from any vendor, in one place, and recommends specific improvements to lower it.

> **[Spending and caps](/switch-trust/cost/spending-and-caps)**
>
> See what each agent spends, set a monthly cap, and spot the agents on track to go over.

> **[Recommended improvements](/switch-trust/inventory/agents#improvements)**
>
> Get recommended improvements for each agent, see their estimated impact, and decide which to apply.

## More

> **[Set model pricing](/switch-trust/cost/model-pricing)**
>
> Set the per-token rates behind every cost figure, including negotiated rates.

> **[Connect your coding agent to Switch Trust](/switch-trust/mcp/index)**
>
> Bring an agent's costs and recommended optimizations into Claude Code, Cursor, or VS Code. Fix what makes the agent expensive, and check that quality and safety held.