---
title: Action Gateway Pricing (public)
description: Action Gateway charges $0.10 per 1,000 tool invocations, with included tool search and separate charges for code execution and paid tools.
product: Managed Agents
url: https://docs.digitalocean.com/products/managed-agents/action-gateway/details/pricing/
last_updated: "2026-10-01"
---

> **For AI agents:** The documentation index is at [https://docs.digitalocean.com/llms.txt](https://docs.digitalocean.com/llms.txt). Markdown versions of pages use the same URL with `index.html.md` in place of the HTML page (for example, append `index.html.md` to the directory path instead of opening the HTML document).

# Action Gateway Pricing (public)

Action Gateway gives applications and AI agents governed access to tens of thousands of tools through a managed MCP endpoint or SDK. See [What You Can Build](https://docs.digitalocean.com/products/managed-agents/agent-harness-runtime/details/what-you-can-build/index.html.md) for example use cases of Action Gateway with Harness Runtime.

Action Gateway charges $0.10 per 1,000 standard SaaS or MCP tool invocations. Tool search (`action_search`) is included at no additional charge, while code execution and paid tools have separate charges.

## Pricing by Capability

| Capability | Pricing |
|---|---|
| Tool invocation | $0.10 per 1,000 tool calls |
| Tool search (`action_search`) | Included; no tool-call charge |
| Code execution (`action_code`) | Separate compute and memory charges; see [sandbox pricing](https://docs.digitalocean.com/products/managed-agents/agent-harness-runtime/details/pricing/index.html.md). |
| Exa web search (`exa_web_search`) | $10.10 per 1,000 tool calls: $10.00 per 1,000 web search calls plus $0.10 per 1,000 gateway invocations |
| Exa web fetch (`exa_web_fetch`) | $3.10 per 1,000 tool calls: $3.00 per 1,000 web fetch calls plus $0.10 per 1,000 gateway invocations |
| TypeSafe Jev model through Action Gateway | [Serverless Inference pricing for Jev](https://docs.digitalocean.com/products/inference/details/pricing/index.html.md#serverless-inference-pricing) plus $0.10 per 1,000 gateway tool calls. Expand **TypeSafe AI Models** for current model rates. |

The Exa prices include the gateway invocation charge. The additional web search and web fetch charges match the [Serverless Inference built-in web tool rates](https://docs.digitalocean.com/products/inference/details/pricing/index.html.md#tools-usage).

TypeSafe Jev is a Serverless Inference model, with model ID `typesafe-jev-1.13.0`, that you can invoke through Action Gateway. Calls through Action Gateway incur both the model’s inference charges and the gateway tool invocation charge.

Tool-call prices exclude model inference and any separately billed execution services. Other paid search and partner tools have provider-specific charges in addition to gateway pricing.

## Prepayment and Related Charges

Some Action Gateway tools, including Exa web search and web fetch, require a positive [prepaid balance](https://docs.digitalocean.com/products/managed-agents/action-gateway/how-to/manage-ag-prepayment/index.html.md). Prepayment is not required for every tool. A tool that does not require prepayment still incurs its applicable tool-call charges. Usage charges for tools that require prepayment draw from your credits and balances in the [standard order](https://docs.digitalocean.com/products/managed-agents/action-gateway/how-to/manage-ag-prepayment/index.html.md#shared-balance) as they run.

There is no per-session or per-product spend limit for Action Gateway. A looping or compromised agent using tools that require prepayment can drain your prepaid balances quickly. When all your balances are empty, the gateway blocks calls to those tools until you add funds. Tools that do not require prepayment are not blocked by the gateway’s balance check.

When you use Action Gateway from a [Harness Runtime](https://docs.digitalocean.com/products/managed-agents/agent-harness-runtime/index.html.md) session, compute and workspace storage are [billed under Harness Runtime](https://docs.digitalocean.com/products/managed-agents/agent-harness-runtime/details/pricing/index.html.md). Model inference passes through to [Inference](https://docs.digitalocean.com/products/inference/details/pricing/index.html.md) billing when you use DigitalOcean-hosted models.