DeepSeek

To use Letta with the DeepSeek API, set the environment variable DEEPSEEK_API_KEY=...

You can use Letta with DeepSeek if you have a DeepSeek account and API key. Once you have set your DEEPSEEK_API_KEY in your environment variables, you can select what model and configure the context window size.

Please note that R1 doesn’t natively support function calling in DeepSeek API and V3 function calling is unstable, which may result in unstable tool calling inside of Letta agents.

The DeepSeek API for R1 is often down. Please make sure you can connect to DeepSeek API directly by running:

$curl https://api.deepseek.com/v1/chat/completions \
>  -H "Content-Type: application/json" \
>  -H "Authorization: Bearer $DEEPSEEK_API_KEY" \
>  -d '{
>        "model": "deepseek-reasoner",
>        "messages": [
>          {"role": "system", "content": "You are a helpful assistant."},
>          {"role": "user", "content": "Hello!"}
>        ],
>        "stream": false
>      }'

Enabling DeepSeek as a provider

To enable the DeepSeek provider, you must set the DEEPSEEK_API_KEY environment variable. When this is set, Letta will use available LLM models running on DeepSeek.

Using the docker run server with DeepSeek

To enable DeepSeek models, simply set your DEEPSEEK_API_KEY as an environment variable:

$# replace `~/.letta/.persist/pgdata` with wherever you want to store your agent data
>docker run \
>  -v ~/.letta/.persist/pgdata:/var/lib/postgresql/data \
>  -p 8283:8283 \
>  -e DEEPSEEK_API_KEY="your_deepseek_api_key" \
>  letta/letta:latest

Using letta run and letta server with DeepSeek

To chat with an agent, run:

$export DEEPSEEK_API_KEY="..."
>letta run

To run the Letta server, run:

$export DEEPSEEK_API_KEY="..."
>letta server

To select the model used by the server, use the dropdown in the ADE or specify a LLMConfig object in the Python SDK.

Built with