docs: add OrcaRouter as a named OpenAI-compatible gateway provider - #221
Open
XiaoHuo888-hue wants to merge 1 commit into
Open
docs: add OrcaRouter as a named OpenAI-compatible gateway provider#221XiaoHuo888-hue wants to merge 1 commit into
XiaoHuo888-hue wants to merge 1 commit into
Conversation
Adds an OrcaRouter provider recipe to the configuration reference, mirroring the existing OpenRouter / Copilot / Bedrock sections. Documents the double-prefix model form LiteLLM needs to reach OrcaRouter's namespaced routing, plus the .env key and base-URL setup. Co-Authored-By: Claude <noreply@anthropic.com> Signed-off-by: XiaoHuo888 <sjh00112233@outlook.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds OrcaRouter as a named OpenAI-compatible gateway in the configuration reference, wired the same way the existing OpenRouter provider section is documented. OrcaRouter is an OpenAI-compatible gateway: one API key (keys start with
sk-orca-) unlocks 150+ models from OpenAI, Anthropic, Google, DeepSeek, Qwen, MiniMax and xAI behind a singlehttps://api.orcarouter.ai/v1endpoint. 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.Changes
examples/configuration/README.md: new "OrcaRouter (OpenAI-compatible gateway)" subsection, mirroring the existing OpenRouter / Copilot / Bedrock provider sections. It documents the double-prefix model form LiteLLM needs (openai/openai/gpt-5.5— LiteLLM strips oneopenai/provider prefix and OrcaRouter sees the namespacedopenai/gpt-5.5) plus the<kb>/.envsetup (LLM_API_KEY+OPENAI_API_BASE).Why the double prefix?
OrcaRouter routes by provider-prefixed model IDs. LiteLLM strips the leading
openai/provider prefix before the request leaves, so the id OrcaRouter receives must still be namespaced — a baregpt-5.5is rejected with a 503.Verification
litellm.acompletionwithbase_url— the same call the agents SDKLitellmModelmakes):openai/openai/gpt-5.5→ 200, resolves togpt-5.5-2026-04-24openai/google/gemini-3-flash-preview→ 200openai/deepseek/deepseek-v4-flash→ 200openai/orcarouter/auto→ 200openai/gpt-5.5(single prefix) → 503, confirming the double-prefix requirementOPENAI_API_BASEis resolved byresolve_credential_bundleand threaded intoLitellmModel(base_url=...); LiteLLM also reads it natively for theopenai/provider.I'm an engineer on the OrcaRouter team.