feat: add OrcaRouter LLM model provider - #6689
Open
Marc-oss-hub wants to merge 1 commit into
Open
Conversation
Add OrcaRouter as a named model provider in MaxKB's provider registry, mirroring the existing Regolo/DeepSeek provider structure: - Register OrcaRouterModelProvider in ModelProvideConstants - Add orcarouter_llm_list with 8 curated models (orcarouter/auto, openai/gpt-5.5, google/gemini-3.5-flash, anthropic/claude-opus-4.8, grok/grok-4.3, deepseek/deepseek-v4-pro, minimax/minimax-m2.7, qwen/qwen3.7-max) - Add credential form with api_base defaulting to https://api.orcarouter.ai/v1 - Add OrcaRouterChatModel (OpenAI-compatible chat model) and provider icon OrcaRouter is an OpenAI-compatible AI gateway, so the LLM family is served through the existing BaseChatOpenAI path; no additional API-key handling beyond the standard credential form is required.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds OrcaRouter as a named model provider in the MaxKB provider registry, mirroring how the existing Regolo provider is wired. OrcaRouter is an OpenAI-compatible model routing gateway that exposes 150+ models from OpenAI, Anthropic, Google, DeepSeek, Qwen, MiniMax, xAI and others behind a single endpoint and API key. 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.
I'm an engineer on the OrcaRouter team.
What this changes
apps/models_provider/constants/model_provider_constants.py: registersOrcaRouterModelProviderinModelProvideConstantsapps/models_provider/impl/orcarouter_model_provider/orcarouter_model_provider.py: provider implementation with 8 curated models and the provider info/iconapps/models_provider/impl/orcarouter_model_provider/credential/llm.py: credential form (API URL defaulting tohttps://api.orcarouter.ai/v1, API key, temperature / max tokens params)apps/models_provider/impl/orcarouter_model_provider/model/llm.py:OrcaRouterChatModel(OpenAI-compatible, served through the existingBaseChatOpenAIpath)apps/models_provider/impl/orcarouter_model_provider/icon/orcarouter_icon_svg: provider iconWhy a separate provider rather than the OpenAI-compatible escape hatch
This mirrors how the Regolo aggregator is wired in this repo, so the model picker, docs and config reference stay consistent for users. OrcaRouter speaks the same OpenAI-compatible API, so the LLM family is served through the existing
BaseChatOpenAIpath — the provider is a thin base-URL swap plus a curated model catalog.How to use it
sk-orca-).https://api.orcarouter.ai/v1) and the API key.openai/gpt-5.5,anthropic/claude-opus-4.8,google/gemini-3.5-flash,deepseek/deepseek-v4-pro,minimax/minimax-m2.7orqwen/qwen3.7-max. The full catalog is at https://www.orcarouter.ai/models.Verification
/v1OpenAI-compatible chat/completions endpoint.IModelProvider/ModelInfo/ModelInfoManagemachinery (mirror ofRegoloModelProvider).