Skip to main content

llm-tiyuvta

PyPI Changelog Tests License

LLM plugin for tiyuvta — prepaid open-weight-model inference with one price per model, no subscription.

Every model on the endpoint speaks the identical OpenAI-compatible API: streaming, tool calling, structured output, and vision where the model has eyes. The plugin reads the live model catalog, so new models appear without a plugin update.

Installation

Install this plugin in the same environment as LLM:

llm install llm-tiyuvta

Configuration

Get an API key from inference.tiyuvta.ai, then:

llm keys set tiyuvta
# Paste key here

You can also set it as the TIYUVTA_KEY environment variable — note that a key stored with llm keys set takes precedence over the environment variable.

Models appear in llm models once a key is configured.

Usage

Run a prompt (short aliases work — qwen3.8-27b for tiyuvta/qwen/qwen3.8-27b):

llm -m qwen3.8-27b "Three reasons the sky looks blue"

Chat interactively:

llm chat -m qwen3.8-27b

Vision — attach an image:

llm -m qwen3.8-27b "describe this" -a photo.jpg

Tools and schemas work the way they do for any OpenAI-compatible LLM model:

llm -m qwen3.8-27b --schema 'name, bullet_points: three key points' "summarize: ..."

List the models the endpoint currently serves:

llm tiyuvta models

Refresh the cached catalog after a new model launches:

llm tiyuvta refresh

Development

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

cd llm-tiyuvta
python -m venv venv
source venv/bin/activate

Now install the dependencies and test dependencies:

llm install -e '.[test]'

To run the tests:

pytest

Download files

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

Source Distribution

llm_tiyuvta-0.1.0.tar.gz (9.9 kB view details)

Uploaded Source

Built Distribution

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

llm_tiyuvta-0.1.0-py3-none-any.whl (9.5 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: llm_tiyuvta-0.1.0.tar.gz
  • Upload date:
  • Size: 9.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for llm_tiyuvta-0.1.0.tar.gz
Algorithm Hash digest
SHA256 46d616e35d7eeb83ddfce4a431ce500edff196e3935672fdd950bbc50c964df6
MD5 52b9f6077e46adc787089fd6d4e425fc
BLAKE2b-256 eb5bf0ef0770e5a95a1cb27bfb3640fb4f86275590791f32b768809bd5a3a286

See more details on using hashes here.

Provenance

The following attestation bundles were made for llm_tiyuvta-0.1.0.tar.gz:

Publisher: publish.yml on avifenesh/llm-tiyuvta

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

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

File metadata

  • Download URL: llm_tiyuvta-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 9.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for llm_tiyuvta-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 1e7b2abbed5544ce89636958b1e585f40411d75f43e053115377164c18559309
MD5 d02fda781a7c2caed97a132fa48120a0
BLAKE2b-256 3ba8af3c21b8de9b3212e086b851fe846aff3d5413f3268d059b6652bcf568e9

See more details on using hashes here.

Provenance

The following attestation bundles were made for llm_tiyuvta-0.1.0-py3-none-any.whl:

Publisher: publish.yml on avifenesh/llm-tiyuvta

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

0.1.1

2 files

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