Skip to content

docs: add ChatOrcaRouter chat model integration #216

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
zhenjunchen-png wants to merge 3 commits into
base: main
Choose a base branch
from
Open

docs: add ChatOrcaRouter chat model integration #216

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
fcd6501
docs: add ChatOrcaRouter chat model integration
zhenjunchen-png May 29, 2026
2710e70
docs: reword ChatOrcaRouter model name step
zhenjunchen-png May 29, 2026
71445a9
docs: address review feedback on ChatOrcaRouter page
zhenjunchen-png May 29, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions en/SUMMARY.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -124,6 +124,7 @@
* [IBM Watsonx](integrations/langchain/chat-models/ibm-watsonx.md)
* [ChatOllama](integrations/langchain/chat-models/chatollama.md)
* [ChatOpenAI](integrations/langchain/chat-models/azure-chatopenai.md)
* [ChatOrcaRouter](integrations/langchain/chat-models/chatorcarouter.md)
* [ChatTogetherAI](integrations/langchain/chat-models/chattogetherai.md)
* [GroqChat](integrations/langchain/chat-models/groqchat.md)
* [Document Loaders](integrations/langchain/document-loaders/README.md)
Expand Down
1 change: 1 addition & 0 deletions en/integrations/langchain/chat-models/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ Chat models take a list of messages as input and return a model-generated messag
* [ChatOllama Funtion](broken-reference)
* [ChatOpenAI](azure-chatopenai.md)
* [ChatOpenAI Custom](broken-reference)
* [ChatOrcaRouter](chatorcarouter.md)
* [ChatTogetherAI](chattogetherai.md)
* [GroqChat](groqchat.md)
* [ChatSambanova](chat-sambanova.md)
24 changes: 24 additions & 0 deletions en/integrations/langchain/chat-models/chatorcarouter.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
# ChatOrcaRouter

## Description

OrcaRouter is an OpenAI-compatible LLM router that exposes 150+ models behind a single endpoint, with a workspace-configurable `auto` router that picks the best upstream per request based on price, latency, quality, and rate-limit signals.

## Prerequisites

1. Sign up at [https://www.orcarouter.ai](https://www.orcarouter.ai).
2. Create an API key at the [OrcaRouter console](https://www.orcarouter.ai/console). Keys begin with `sk-orca-`.
3. Browse the full model catalog at [https://www.orcarouter.ai/models](https://www.orcarouter.ai/models).

## Step by Step Guide

1. **Chat Models** > Drag the **ChatOrcaRouter** node.
2. Click **Connect Credential** and create a new credential with your OrcaRouter API key.
3. Pick a model from the **Model Name** dropdown, which is fetched live from the OrcaRouter catalog with `orcarouter/auto` as the default option (the workspace router). You can also type any model id from the [OrcaRouter catalog](https://www.orcarouter.ai/models).
4. Connect ChatOrcaRouter to an LLM Chain, Conversational Agent, or other downstream node and run the chatflow.

## Routing notes

- `orcarouter/auto` is a virtual router name, not a model. Configure its routing strategy (`cheapest`, `balanced`, `quality`, `adaptive`, `gated_adaptive`) and pool membership at [https://www.orcarouter.ai/console/routing](https://www.orcarouter.ai/console/routing).
- Reasoning models such as `anthropic/claude-opus-4.8`, the OpenAI `gpt-5` family, and `deepseek/deepseek-reasoner` reject the `temperature` field. Leave **Temperature** blank for those models.
- For self-hosted [OrcaRouter-O2](https://github.com/Continuum-AI-Corp/OrcaRouter-O2) deployments, override the **Base Path** under *Additional Parameters*.