feat(benchmarks): add OrcaRouter as an OpenAI-compatible provider - #334
Open
kuswardhanietidims-svg wants to merge 1 commit into
Open
Conversation
Wire OrcaRouter into the retrieval-accuracy benchmark's MODELS registry as a first-class entry. It is an OpenAI-compatible AI gateway, so the entry builds an OpenAI provider pointed at https://api.orcarouter.ai/v1 and uses the orcarouter/auto model id, letting the gateway route each prompt across models. Also document ORCAROUTER_API_KEY in .env.example and the setup notes in the benchmark README.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
The retrieval-accuracy benchmark's
MODELSregistry inbenchmarks/src/evaluate.tscurrently covers Anthropic, Google, OpenAI, and xAI. This adds OrcaRouter (orcarouter/auto) as a ready-made entry so TOON's token/accuracy numbers can be produced through an OpenAI-compatible AI gateway that routes every prompt across many models.OrcaRouter is an OpenAI-compatible AI gateway built for both models and agents. Like OpenRouter, it exposes a provider/model namespace across many models — but it also combines adaptive routing, automatic failover, zero-markup inference, observability, guardrails, and agent-tool governance behind the same endpoint. Mirroring how the existing
openai('gpt-5.4-nano')entry is wired, the new entry builds the provider withcreateOpenAI({ baseURL: 'https://api.orcarouter.ai/v1' })(via the chat-completions endpoint) and readsORCAROUTER_API_KEYfrom the environment, documented in.env.exampleand the benchmark setup notes.It also runs gateway-level, zero-trust security for AI agents on the same endpoint — screening every prompt/response and governing every tool call on a default-deny basis, with no application code changes.
Verification
tsc --noEmitclean,eslint .clean,vitest run767 tests pass (Node 24, same as CI)orcarouter/autothrough the actualMODELSregistry entry withORCAROUTER_API_KEY— real completion returned, answer matched ground truthDiscord: discord.gg/YEubt8enRA · X: https://x.com/OrcaRouter
I'm an engineer on the OrcaRouter team.