LLM plugin for models hosted by Chutes AI
First, install the LLM command-line utility.
Now install this plugin in the same environment as LLM.
llm install llm-chutesYou will need an API key from Chutes AI. You can obtain one from their platform.
You can set that as an environment variable called CHUTES_API_KEY, or add it to the llm set of saved keys using:
llm keys set chutesEnter key: <paste key here>
To list available models, run:
llm models listYou should see a list that looks something like this:
chutes: chutes/deepseek-ai/DeepSeek-R1
chutes: chutes/deepseek-ai/DeepSeek-V3-0324
chutes: chutes/NousResearch/DeepHermes-3-Mistral-24B-Preview
chutes: chutes/moonshotai/Kimi-K2-Instruct
chutes: chutes/Qwen/Qwen3-32B
...
To run a prompt against a model, pass its full model ID to the -m option, like this:
llm -m chutes/deepseek-ai/DeepSeek-R1 "Five spooky names for a pet tarantula"You can set a shorter alias for a model using the llm aliases command like so:
llm aliases set deepseek chutes/deepseek-ai/DeepSeek-R1Now you can prompt the model using:
llm -m deepseek "What is the meaning of life?"The llm models -q chutes command will display all available models, or you can use this command to see more detailed information:
llm chutes modelsOutput starts like this:
- id: deepseek-ai/DeepSeek-R1
name: deepseek-ai/DeepSeek-R1
context_length: 163,840
supports_schema: True
pricing: input $0.27216/M, output $0.27216/M
- id: deepseek-ai/DeepSeek-V3-0324
name: deepseek-ai/DeepSeek-V3-0324
context_length: 163,840
supports_schema: True
pricing: input $0.27216/M, output $0.27216/MAdd --json to get back JSON instead:
llm chutes models --jsonTo refresh the cached list of models from the Chutes AI API:
llm chutes refreshTo set up this plugin locally, first checkout the code. Then create a new virtual environment:
cd llm-chutes
python3 -m venv venv
source venv/bin/activateNow install the dependencies and test dependencies:
llm install -e '.[test]'To run the tests:
pytestThis plugin connects to the Chutes AI API at https://llm.chutes.ai/v1/
Apache License 2.0