Skip to content

Add Requesty provider#688

Open
Thibaultjaigu wants to merge 1 commit into
valentinfrlch:mainfrom
Thibaultjaigu:add-requesty-provider
Open

Add Requesty provider#688
Thibaultjaigu wants to merge 1 commit into
valentinfrlch:mainfrom
Thibaultjaigu:add-requesty-provider

Conversation

@Thibaultjaigu

Copy link
Copy Markdown

Adds Requesty as a provider, mirroring the existing OpenRouter provider as closely as possible.

Requesty (https://requesty.ai) is an OpenAI-compatible LLM router (base URL https://router.requesty.ai/v1, provider/model naming), so it reuses the shared OpenAI provider class with a different base URL — exactly how OpenRouter is wired.

Changes:

  • custom_components/llmvision/const.py: ENDPOINT_REQUESTY and DEFAULT_REQUESTY_MODEL (openai/gpt-4o-mini), mirroring the OpenRouter constants.
  • custom_components/llmvision/providers.py: "Requesty" in the default-model map and a provider_name == "Requesty" dispatch branch returning OpenAI(..., endpoint={"base_url": ENDPOINT_REQUESTY}).
  • custom_components/llmvision/config_flow.py: Requesty added to the provider selector and an async_step_requesty config step mirroring async_step_openrouter.
  • custom_components/llmvision/strings.json + translations/en.json: Requesty UI strings mirroring the OpenRouter step.
  • README.md: Requesty added to the supported-providers list.

The default model id is verified live on Requesty.

I work at Requesty. This mirrors the existing OpenRouter provider as closely as possible. Happy to adjust or close it if it's not a fit.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant