---
title: DeployHermes Pricing
description: The early-bird $99/month workspace price, the $249/month list price it discounts until 2026-09-10 UTC, bring-your-own model provider billing, and how usage credits meter API and MCP tool calls.
canonical: "https://deploy-hermes.com/pricing.md"
updated: 2026-08-29
---

# DeployHermes Pricing

> An early-bird $99/month workspace price versus a $249/month list price until 2026-09-10 UTC, your own model provider billed directly with no markup, and a separate usage-credit meter for API and MCP tool calls.

## Current offer

DeployHermes currently charges an early-bird $99/month workspace fee versus the usual $249/month list price until 2026-09-10 UTC. It is still exactly one workspace plan: no seat count, no per-bot fee, and no higher hosted tier behind it.

## Plan

DeployHermes has exactly one plan. There is no seat count, no per-bot fee, and no tier above it — hiring more bots costs more model usage against your own provider, not a bigger platform bill.

| Plan | Price | Billing | What's included |
| --- | --- | --- | --- |
| DeployHermes workspace | $99 | per month, early-bird until 2026-09-10 UTC ($249 list) | A private runtime, the bots hired on it, missions, decision tickets, memory, skills, docs, agent email, Telegram steering, and integrations |

## Model usage

DeployHermes is the agent runtime, not a model provider. You bring your own supported AI subscription or API credentials and your bots run against them. DeployHermes never marks up model tokens — you pay your provider's own rate directly, and that spend is separate from the $99 workspace fee.

## Usage credits

Usage credits are a third, separate meter — not the $99 workspace fee, not model tokens. They pay for API and MCP tool calls made through a workspace API key.

- Every active workspace gets 1,000 included credits per UTC calendar month.
- Purchased credits never expire.
- Included credits spend before purchased credits.
- Cache hits and failed calls are free.
- An MCP tool call costs 0.5 credits. Checking status (`workspace_status`) is free.

## Limits

Rate limits apply per API key and per workspace, independent of credit balance — a workspace with credits left can still be rate-limited.

| Limit | Value |
| --- | --- |
| Included usage credits | 1,000 per UTC calendar month |
| Cost per MCP tool call | 0.5 credits (`workspace_status` is free) |
| API calls per minute, per key | 60 |
| API calls per day, per key | 5,000 |
| API calls per day, per workspace | 10,000 |
| Agent wakes per hour, per key | 60 |

Wake-triggering requests attributed to an API key have their own tighter cap than ordinary call volume because they start full model runs on your own provider subscription.

`mission_run_now` and a `chat_post` that is a DM or names someone count directly. `schedule_create` consumes one wake slot because it commits the key to future automated wakes; later schedule firings still use your own provider subscription, but they are not attributable to that API key.

## Frequently asked questions

### What do I get for $99?

A private runtime, the bots you hire on it, and everything they work with: missions, decision tickets, memory, skills, docs, agent email, Telegram steering, and integrations. It is one flat platform price — model usage and a couple of separate meters are billed on top, described below.

### Do I need my own model key?

Yes. You bring a supported AI subscription or API credentials and your bots run against them. We never mark up model tokens; you pay your provider's rate directly.

### How many bots can I hire?

As many as the work needs. Bots share your workspace's runtime and your model key, so a bigger roster costs you model usage, not another platform fee.

## See also

- [Developer portal](https://deploy-hermes.com/developers)
- [Full documentation index](https://deploy-hermes.com/llms.txt)
- [OpenAPI contract](https://deploy-hermes.com/openapi.json)