Pricing

The CLI is free. The desktop app is $3

One licence for the desktop app. Everything runs on your machine, against local models or your own API keys, so there is no usage to meter and nothing to top up.

Terminal
CLI
Free · forever
  • The full agent, in one Rust binary
  • Local models, or your own API keys
  • Open source · no account needed
$curl -fsSL https://lucidtrain.com/install.sh | sh

or: pip install lucid-train

Desktop app
2 months free
Lucid Train
$2.50/mo
billed $30 a year
  • Everything in the CLI, in a native app
  • Design, Diagram, Audit and Dashboards
  • Local models, or your own API keys
  • 7-day free trial · no card up front
Start your 7-day trial

Every model call goes straight from your machine to whichever provider you configure. We never see your code, and there is no usage bill to read.

Price vs the frontier

What you'd pay with your own key.

The same everyday coding work, sorted by list price per million output tokens. You pay these directly to whichever provider you configure, or nothing at all when you run a local model.

$lucid-train models --compare --sort price
on a Lucid plan your own API key
modelcoding signal$ / 1M outputcontext
DeepSeek V4 Pro
Lucid · DeepSeek
80.6%
SWE-bench Verified
$0.87/1M
1M
GLM 5.2
Lucid · Z.ai
68.8
AA Coding Index
$3.00/1M
1M
Kimi K2.7 Code
Lucid · Moonshot
> GPT-5.4
SWE-bench Pro (vendor)
$3.50/1M
256K
Claude Opus 4.8
Anthropic · API key
88.6%
SWE-bench Verified
$25.00/1M
1M
GPT-5.5
OpenAI · API key
frontier
coding / reasoning
$30.00/1M
1.05M

Frontier coding runs $25–$30 per 1M output tokens. Lucid's models land $0.87–$3.50, which is 7×–34× cheaper, for the same everyday coding work. One monthly bill, no API keys.