feat: add Requesty as an OpenAI-compatible provider#82
Open
Thibaultjaigu wants to merge 1 commit into
Open
Conversation
Mirror the existing OpenRouter wiring for Requesty (https://router.requesty.ai/v1), an OpenAI-compatible LLM gateway: - routes/models.py: add "requesty" to valid_providers - backend/setup.py: add Requesty to PROVIDER_DEFAULTS (feeds the setup wizard provider picker and CLI setup) - templates/settings.html: add Requesty option to the model provider select
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Adds Requesty (https://requesty.ai) as a named OpenAI-compatible LLM provider, mirroring the existing OpenRouter wiring 1:1. Requesty is an OpenAI-compatible gateway with the same
provider/modelnaming convention already used for OpenRouter.https://router.requesty.ai/v1(/v1/chat/completions,/v1/models)Authorization: Bearer <key>provider/model(e.g.openai/gpt-4o-mini) — same as OpenRouterChanges
routes/models.py: add"requesty"to thevalid_providerstuple in the model-create route.backend/setup.py: add arequestyentry toPROVIDER_DEFAULTS(default base URLhttps://router.requesty.ai/v1, API key required). This data row feeds both the web setup wizard provider picker (templates/setup.htmliteratesproviders.items()) and the CLI setup wizard, so no separate picker edits are needed there.templates/settings.html: add a<option value="requesty">Requesty</option>to the model provider<select>, matching the other static options.No new dependencies; the existing OpenAI-compatible request/model-discovery path is reused unchanged.
Tested live
Against
https://router.requesty.ai/v1with a real key:POST /v1/chat/completions(modelopenai/gpt-4o-mini,max_tokens=32) → HTTP 200, validchat.completionresponse.GET /v1/models(the path the app uses for model discovery via{base_url}/models) → HTTP 200, OpenAI-shaped{"data":[...]}list (572 models).I work at Requesty. This mirrors the existing OpenRouter provider as closely as possible. Happy to adjust wording/placement or close it if it's not a fit.