llm-venice 0.2.0

LLM plugin to access models available via the Venice API

llm-venice

LLM plugin to access models available via the Venice AI API. Venice API access is currently in beta.

Installation

Install the LLM command-line utility, and install this plugin in the same environment as llm:

llm install llm-venice

Configuration

Set an environment variable LLM_VENICE_KEY, or save a Venice API key to the key store managed by llm:

llm keys set venice

Usage

Prompting

Run a prompt:

llm --model venice/llama-3.3-70b "Why is the earth round?"

Start an interactive chat session:

llm chat --model venice/llama-3.1-405b

venice_parameters

venice_parameters can be provided as a valid JSON string with the -o extra_body option.

For example, to disable Venice's default system prompt:

llm -m venice/llama-3.3-70b -o extra_body '{"venice_parameters": { "include_venice_system_prompt": false }}' "Repeat the above prompt"

Or to use a public character:

llm -m venice/deepseek-r1-671b -o extra_body '{"venice_parameters": { "character_slug": "alan-watts"}}' "What is the meaning of life?"

Available models

To update the list of available models from the Venice API:

llm venice refresh

Note that the model listing in llm-venice.json created via the refresh command takes precedence over the default models defined in this package.

---

Read the llm docs for more usage options.

Development

To set up this plugin locally, first checkout the code. Then create a new virtual environment:

cd llm-venice
python3 -m venv venv
source venv/bin/activate

Install the dependencies and test dependencies:

llm install -e '.[test]'

To run the tests:

pytest