docs: pricing docs fix (#5791)

* fix: patch pricing

* fix: point out byok

* fix: updated

* fix: another boost
This commit is contained in:
Charles Packer
2025-10-28 12:33:24 -07:00
committed by Caren Thomas
parent 60226ad203
commit c17a06ebb2
3 changed files with 92 additions and 0 deletions

View File

@@ -464,6 +464,7 @@ navigation:
# path: pages/cloud/models.mdx
- page: Custom API Keys
path: pages/cloud/api_keys.mdx
hidden: true
- page: Role-Based Access Control
path: pages/cloud/rbac.mdx
- section: Deploying Agents

View File

@@ -0,0 +1,28 @@
---
title: Bring-Your-Own API Keys
subtitle: Connect your own API keys for supported model providers (OpenAI, Anthropic, etc.)
slug: guides/cloud/custom-keys
---
<Note>
To generate a **Letta API key** (which you use to interact with your agents on Letta Cloud), visit your [account settings](https://app.letta.com/settings/profile) page.
</Note>
<Note>
BYOK is only available on enterprise plans.
</Note>
## Using Your Own API Keys
Connect your own API keys for supported providers (OpenAI, Anthropic, Gemini) to Letta Cloud through the [models page](https://app.letta.com/models). When you have a custom API key (successfully) registered, you will see additional models listed in the ADE model dropdown.
### Selecting Your Custom Provider
After you connect your own OpenAI / Anthropic / Gemini API key, make sure to select your custom provider in the ADE under "Your models".
For example, after connecting your own OpenAI API key, you will see multiple OpenAI models but with different providers ("Letta hosted" vs "Your models") - if you want to use your own OpenAI API key, you need to select the copy of the model associated with your custom provider.
### Billing and Quotas
Requests made using your custom API keys **do not count** towards your monthly request quotas or usage-based billing. Instead, you'll be billed directly by the provider (OpenAI, Anthropic, etc.) according to their pricing for your personal account.
Note that direct provider pricing will likely differ from Letta Cloud rates, and requests through your own API key may cost more than those made through Letta Cloud's managed services.

View File

@@ -0,0 +1,63 @@
---
title: Plans & Pricing
subtitle: Guide to pricing and model usage for Free, Pro, and Enterprise plans
slug: guides/cloud/plans
---
<Note>
Upgrade your plan and view your usage on [your account page](https://app.letta.com/settings/organization/usage)
</Note>
## Available Plans
<CardGroup>
<Card
title="Free"
subtitle="For getting started"
>
- **5,000** monthly credits
- Access the Letta API
- Edit agents visually in the ADE
- **2** agent templates
- **1 GB** of storage
</Card>
<Card
title="Pro ($20 / month)"
subtitle="For shipping agents in production"
>
- **20,000** monthly credits
- Pay-as-you-go credit overage
- Unlimited agents
- **20** agent templates
- **10 GB** of storage
</Card>
</CardGroup>
<Note>
For organizations with higher volume needs, our Enterprise plan offers increased quotas, dedicated support, role-based access control (RBAC), SSO (SAML, OIDC), and private model deployment options.
[Contact our team](https://forms.letta.com/request-demo) to learn more.
</Note>
## What are credits?
Credits are a standard cost unit for resources in Letta, such as LLM inference and CPU cycles. When agents run on Letta, they make LLM model requests and execute tools. Model requests consume credits at a rate depending on the model tier (standard vs. premium) and whether Max Mode is enabled for longer context sizes. Tool executions that run in Letta are charged at a flat rate per second of execution. See up-to-date credit pricing for available models [here](https://app.letta.com/settings/organization/models).
## What tools are executed by Letta?
Sandbox code execution and execution of custom tools run inside of Letta, so incur a credit cost for CPU time. Remote MCP tools are executed by the MCP tool provider, so do not have a credit cost. Letta built-in tools are executed for free.
## How do monthly credits work?
Your Letta agents use large language models (LLMs) to reason and take actions. These model requests consume credits from your monthly balance (or additional purchased credits). Your balance of monthly credits refreshes every month.
## What is Max Mode?
Certain models have the ability to run with extended context windows. Turning on Max Mode extends the context window of the model driving your Letta agent beyond the 100k default, which may help when working with large files or codebases, but will increase cost (credit use) and latency.
## What's the difference between the Letta API and open source Letta?
The Letta API Platform is our fully-managed service for stateful agents, handling all agent infrastructure and state management to create scalable agent services. The Letta API Platform also has additional features beyond the open source such as durable execution for long-running agents, built-in sandboxing, agent templates, optimized vector search, message indexing, and observability.
## Can I transfer my agents between open source and cloud?
Yes, the Letta API Platform supports [agent file](https://docs.letta.com/guides/agents/agent-file), which allows you to move your agents freely between self-hosted instances of the Letta open source and the Letta platform.