Letta with an uncensored model
To run Letta with an uncensored model, connect an OpenAI-compatible provider with /connect and pick an abliterated model with /model.
lettaSettings
> /connect
OpenAI-compatible API
Base URL https://api.silkcompute.com/v1
API key <your Silk Compute key>- OpenAI format
- /connect, OpenAI-compatible API
- Anthropic format
- Not documented
- Tool calling
- Required of the endpoint
- Streaming
- Not documented
- Browser use
- Not documented
- Memory
- Memory filesystem
Labels link to Letta's own docs, read November 18, 2026. Compare all 11
Point the agent only at systems, files and accounts you own or are allowed to test.
Deploy it
3 steps, with Kimi K3.1 Pro.
- 01
Install Letta Code. It needs Node.js 22.19 or newer.
Terminalnpm install -g @letta-ai/letta-code letta - 02
Connect the endpoint. Letta asks for a base URL and an API key. The endpoint must support Chat Completions and tool calling.
See letta above - 03
Pick the model. Type /model and choose kimi-k3.1-pro-uncensored.
Settings> /model
Which model
In this setup
Kimi K3.1 Pro
Long runs, image and video input
- Id
kimi-k3.1-pro-uncensored- Per 1M in / out
- $3.50 / $8.00
DeepSeek V4.1 Flash 1017
Value, image input
- Id
deepseek-v4.1-flash-1017-uncensored- Per 1M in / out
- $0.24 / $0.90
The config uses the Silk Compute base URL, which serves both models with a 1,048,576-token context.