Pricing

Letta Agent is free to use with your own API keys, for example from OpenAI, Anthropic, or OpenRouter. You can also connect Letta Agent to coding plans such as the ChatGPT (Codex) coding plan and zAI coding plans.

To connect your existing plans, simply use /connect in the CLI/TUI, or click “Connect model providers” in the bottom-left menu in the desktop app. See our models guide for more information.

Cloud features

Letta Agent is fully open source and can run without a login / account, including with local models. Using Constellation features such as chat.letta.com, remote environments, managed state, and Letta Auto inference require signing in with /login (or via the desktop app).

Creating an account on Constellation is free. Free accounts support up to three agents with managed state.

LLM gateway

Agents connected to Constellation can use the built-in LLM gateway to access a variety of model providers at passthrough (non-markup) API pricing. Simply navigate to your usage page and enable pay-as-you-go credit purchasing.

Agents managed through Constellation can also use BYOK for supported providers and coding plans through the LLM gateway, but cannot use local inference (e.g. Ollama / LM Studio).

Plans

Personal plans are designed for hands-on use in Letta Agent and chat.letta.com. Developer plans are usage-based for teams building on the Letta API with API keys and automated workloads.

Personal Plans

Free

Get started at no cost.

$0 /month

• Limited agents
• Limited usage of Letta Auto
• Bring your own API keys and external coding plans

View quickstart ↗

Pro

For personal use.

$20 /month

• Letta Auto weekly + monthly quota
• Pay-as-you-go overage
• Up to 20 stateful agents

Get Pro ↗

Developer Plans

Pricing on the Letta API Platform is usage-based. LLM usage is charged based on the underlying token costs of the model used.

API Plan

For teams building on the Letta API.

$20 /month

• Unlimited agents
• $0.10 / active agent / mo
• $0.00015 / sec tool execution
• API key authentication
• Pay-as-you-go LLM usage

Get started ↗

Teams / Enterprise

Enterprise

For organizations with higher volume needs.

Custom

• Volume-based pricing
• Increased quotas
• Role-based access control
• SAML/OIDC SSO
• Dedicated support

Contact us ↗

If you would like to configure managed per-seat pricing for Letta Agent for your business, please contact us.

What is Letta Auto?

Letta Auto selects frontier models that balance general intelligence, coding knowledge, and speed. To use Letta Auto, select Auto in the model selector, or choose one of the more specialized routes for specific applications: Auto Chat for non-coding workloads, or Auto Fast for a model that’s optimized for additional speed over intelligence.

How much usage do I need?

Your ideal plan will vary depending on how you use your agents. Workloads that involve heavy tool use and token generation (e.g. coding or computer use tasks) will drain quota faster.

• Chat users: Often stay within the Pro tier limits
• Limited coding users: May fit within Pro depending on workloads
• Casual coding users (a few hours per day): Typically ~$100/mo+ usage
• Power users (long sessions, many parallel agents): Often approach or exceed $200+/mo in total usage

For agent power users (many hours of coding per day, or heavy automated use), we highly recommend combining Letta Agent with an external coding plan, such as the zAI coding plan, or ChatGPT coding plan (ChatGPT Plus/Pro).

What happens when I reach my Letta Auto limit?

When you exceed your included weekly or monthly usage, you can continue at pay-as-you-go API rates, available through purchasing credits. You can upgrade your plan, add credits, and configure auto-top up in your account’s usage dashboard.

Team Plans

Teams and organizations can purchase seats for individuals using “Team Plans”. Our personal plans are for personal use only and cannot be shared between individuals. Contact us for more information.

Personal Plans vs Developer Plans

Personal Plan quotas are intended for non-automated, personal/individual usage through chat.letta.com or Letta Agent (desktop app, Letta Code CLI, and remote environments mode). The schedules and channels features native to Letta Code are supported exceptions to our automated use policy.

Developer Plans are for developers and teams building applications on top of the Letta API with automated workloads. They use API key authentication with usage-based credit pricing.

All plans support BYOK (bring your own API keys).

---

Frequently asked questions

Can I use my own API keys?

Yes. All plans support bringing your own API keys (BYOK). When you connect your own keys (via /connect in Letta Code), usage goes directly through your provider account instead of consuming Letta credits.

What’s the difference between Personal Plans and Developer Plans?

Personal Plans are for individual, hands-on use via Letta Agent or the chat interface. They provide usage quotas that reset monthly. Personal Plan quotas require OAuth authentication (signing in via the Letta chat app or Letta Code).

Developer Plans are for developers and teams building applications on top of the Letta API with automated workloads. They use API key authentication with purely usage-based credit pricing.

Can I use a Developer Plan with Letta Agent?

Yes. You can use a Developer Plan with Letta Agent; Letta Agent will draw down credits according to model usage from your balance.

We recommend most users use Personal Plans for Letta Agent. Personal Plans include Letta Auto quota and can enable auto top-up or additional usage when quota is exceeded.

What are credits?

Credits are a standard cost unit for resources in Letta, such as LLM inference and CPU cycles. Model requests consume credits at a rate depending on model API pricing. For current model pricing, see app.letta.com/models.

How is tool execution charged?

Server-side tools on the Letta API incur a credit cost for CPU time. On the API Plan, tool execution is billed at $0.00015/sec. Remote MCP tools are executed by the MCP provider, so they do not have a credit cost. Letta built-in tools are free, with the exception of web search/fetch tools. Client-side tools, such as bash tools in Letta Code, run on your machine, so they do not incur a credit cost.

What are the usage limits for my plan?

The free tier includes a limited number of total agents and LLM requests with rotating free models. Personal Plans include monthly usage quotas that scale with each tier. Developer Plans are pay-as-you-go and can be managed from your usage dashboard.

Paid plan users can view current usage in the account dashboard.

What happens when I reach my limit?

On Personal Plans, you can continue using Letta with pay-as-you-go pricing for additional models or overage. On Developer Plans, all usage is pay-as-you-go; you’ll be notified by email when approaching your spending limit.

Where can I ask more questions?

Reach out to support@letta.com, or join our community on Discord.