Skip to content

docs: add OrcaRouter as an OpenAI-compatible provider example - #1643

Open
bangla24bdrang-lab wants to merge 1 commit into
simonw:mainfrom
bangla24bdrang-lab:docs-add-orcarouter-provider
Open

bangla24bdrang-lab wants to merge 1 commit into
simonw:mainfrom
bangla24bdrang-lab:docs-add-orcarouter-provider

Conversation

@bangla24bdrang-lab

Copy link
Copy Markdown

Summary

Adds OrcaRouter as a documented example of an OpenAI-compatible AI gateway, alongside LocalAI and OpenRouter in docs/other-models.md.

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. Adding it as a documented provider means LLM users can use that stack directly, without treating OrcaRouter as an anonymous custom base URL. 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.

What changed

This updates docs/other-models.md with a new OrcaRouter section showing how to configure OrcaRouter models through extra-openai-models.yaml, mirroring the existing OpenRouter / AGIone examples.

The examples use full OrcaRouter model identifiers:

  • orcarouter/auto — the adaptive router endpoint
  • openai/gpt-5.5 — a vendor-prefixed model identifier

Why

OrcaRouter provides a single OpenAI-compatible endpoint for routing to frontier models through standard Bearer-token authentication, using the same provider/model namespace style as OpenRouter.

This fits the existing "OpenAI-compatible models" documentation pattern used for providers like LocalAI and OpenRouter.

Verification

  • Live-tested both example models (orcarouter/auto and openai/gpt-5.5) against https://api.orcarouter.ai/v1 with a real API key — both return 200 with a normal chat completion.
  • Ran the documented user flow end-to-end: llm keys set orcarouter, configured extra-openai-models.yaml, llm models shows both models, and llm -m orcarouter-auto '...' / llm -m orcarouter-gpt-5 '...' both returned a completion.
  • Test suite: 1105 passed.
  • Linters: black --check, ruff check ., mypy llm, and cog --check all pass.

Disclosure

I'm an engineer on the OrcaRouter team.

Discord: discord.gg/YEubt8enRA · X: https://x.com/OrcaRouter

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