✨ feat(provider): add OrcaRouter as a new model provider - #2
Closed
xilema2 wants to merge 1 commit into
Closed
Conversation
OrcaRouter is an adaptive LLM routing gateway that picks the best upstream per request via a LinUCB contextual bandit over cost, latency, and quality signals — one API key, 150+ frontier models from OpenAI, Anthropic, Google, DeepSeek, xAI, and more. - runtime: OpenAI-compatible factory with per-vendor reasoning protocol (Anthropic native `thinking`, others top-level `reasoning_effort`) and strips `temperature` / `top_p` / `top_k` for reasoning-only models that reject them - model fetcher: pulls the public /api/pricing catalog and computes USD/1M from `model_ratio` * 2 (the official QuotaPerUnit constant) - HTTP-Referer + X-Title attribution headers wired through - env: ORCAROUTER_API_KEY / ENABLED_ORCAROUTER - 22 unit tests covering reasoning routing, parameter stripping, pricing computation, and model filtering
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
OrcaRouter is an adaptive LLM routing gateway that picks the best upstream per request via a LinUCB contextual bandit over cost, latency, and quality signals — one API key, 150+ frontier models from OpenAI, Anthropic, Google, DeepSeek, xAI, and more.
thinking, others top-levelreasoning_effort) and stripstemperature/top_p/top_kfor reasoning-only models that reject themmodel_ratio* 2 (the official QuotaPerUnit constant)💻 Change Type
🔗 Related Issue
🔀 Description of Change
🧪 How to Test
📸 Screenshots / Videos
📝 Additional Information