Add Requesty as an OpenAI-compatible LLM provider - #765
Open
Thibaultjaigu wants to merge 1 commit into
Open
Conversation
Mirror the existing OpenRouter provider (lib/llm/core/providers/openrouter.js) for Requesty, an OpenAI-compatible LLM router. Registers a dedicated 'requesty' provider using the repo's existing createOpenAICompatible path with base URL https://router.requesty.ai/v1 and REQUESTY_API_KEY auth. Wires it through the client registry, model provider list, DB seed list, and provider logo map. Signed-off-by: Thibault Jaigu <thibault.jaigu@gmail.com>
✅ Deploy Preview for gleeful-palmier-13a6af ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add Requesty as an OpenAI-compatible LLM provider
This adds Requesty as a first-class LLM provider by mirroring the existing OpenRouter integration.
Requesty is an OpenAI-compatible LLM router that exposes 400+ models behind a single API using the same
provider/modelnaming convention as OpenRouter, so it slots into the existing provider architecture cleanly.Changes
lib/llm/core/providers/requesty.js—RequestyClientextendingBaseClient. Since there is no dedicated Requesty SDK (the OpenRouter provider uses@openrouter/ai-sdk-provider), this uses the repo's existingcreateOpenAICompatiblepath — the correct dedicated-provider form for an OpenAI-compatible router. Base URLhttps://router.requesty.ai/v1, Bearer auth viaREQUESTY_API_KEY.lib/llm/core/index.js— registerrequestyin the client map.constant/model.js— Requesty provider entry with default models (openai/gpt-4o-mini,openai/gpt-4o,anthropic/claude-sonnet-4-5,google/gemini-2.5-flash).lib/db/llm-providers.js— provider seed entry.lib/util/providerLogo.js— logo mapping + id normalization.public/imgs/providers/requesty.ico— provider icon.Testing
Verified live against the Requesty endpoint through the actual
RequestyClientcode path (transpiledbase.js+requesty.js,createOpenAICompatible+ AI SDKgenerateText): a call toopenai/gpt-4o-minireturned the expected completion. Prettier (the repo's formatting tool) passes on all touched files.Note: I couldn't find a committed README/docs provider list enumerating OpenRouter to add Requesty to — if there's a canonical provider list I missed, happy to update it.
Config: get a key at https://app.requesty.ai/api-keys, model list at https://app.requesty.ai/router/list, docs at https://docs.requesty.ai.
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.