Skip to main content

llm-chutes

PyPI Changelog Tests License

LLM plugin for models hosted by Chutes AI

Installation

First, install the LLM command-line utility.

Now install this plugin in the same environment as LLM.

llm install llm-chutes

Configuration

You 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 chutes
Enter key: <paste key here>

Usage

To list available models, run:

llm models list

You 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-R1

Now you can prompt the model using:

llm -m deepseek "What is the meaning of life?"

Listing models

The llm models -q chutes command will display all available models, or you can use this command to see more detailed information:

llm chutes models

Output 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/M

Add --json to get back JSON instead:

llm chutes models --json

Refreshing models

To refresh the cached list of models from the Chutes AI API:

llm chutes refresh

Development

To 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/activate

Now install the dependencies and test dependencies:

llm install -e '.[test]'

To run the tests:

pytest

API Endpoint

This plugin connects to the Chutes AI API at https://llm.chutes.ai/v1/

License

Apache License 2.0

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

llm_chutes-0.1.0.tar.gz (6.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

llm_chutes-0.1.0-py3-none-any.whl (6.0 kB view details)

Uploaded Python 3

File details

Details for the file llm_chutes-0.1.0.tar.gz.

File metadata

  • Download URL: llm_chutes-0.1.0.tar.gz
  • Upload date:
  • Size: 6.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.6

File hashes

Hashes for llm_chutes-0.1.0.tar.gz
Algorithm Hash digest
SHA256 5dc34daf156583275699d46c07532414576c096950f73e973772bc310f1fcbdd
MD5 64520e452c81c7047ea7694b59df8be1
BLAKE2b-256 a2e04f10ed87c9a24793b6da82cb4843a2079a40687ade69657680c16d231b73

See more details on using hashes here.

File details

Details for the file llm_chutes-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: llm_chutes-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 6.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.6

File hashes

Hashes for llm_chutes-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 960c92677ca1b78cfa40cc2e7573963695b5fbafdad86c95be270b909c8a3e97
MD5 a92abdd22a682f65966263f07d8b41a1
BLAKE2b-256 05ea5ba4271e2efb36b59b7978163c96236fa36ca5e16352e5633ea3d87dc1af

See more details on using hashes here.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 files

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page