knoten / builtin / ai / aidependencies / llm
Chat OpenRouter
Route to hundreds of models across providers through OpenRouter.
Dieser Inhalt ist noch nicht in deiner Sprache verfügbar.
Give an AI node access to hundreds of models from many providers (Anthropic, OpenAI, Google, Meta, Mistral and more) with one OpenRouter API key.
What it does
Section titled “What it does”Chat OpenRouter is a model you plug into the Model slot of an AI node, such as the Tools Agent or Basic LLM Chain. It does not run on its own and has no output. When the AI node runs, it sends its messages to OpenRouter, which passes them to the model you chose and returns the reply. You pay OpenRouter, from one balance, whatever the model.
- Temperature is 0 when you leave it empty, so answers are focused and repeatable.
- Replies are capped at Max Tokens (4096 by default). This also stops OpenRouter from reserving credit for a model’s whole output window, which can fail on a small balance.
- A failed request is retried up to Max Retries times (2 by default). A request that gets no answer within 60 seconds fails.
When to use it
Section titled “When to use it”- You want to try or compare models from several providers without an account at each.
- You want one bill and one key for all your AI nodes.
- You want free or very cheap models that OpenRouter lists.
Inputs and settings
Section titled “Inputs and settings”| Einstellung | Typ | Was es bewirkt |
|---|---|---|
| Model (erforderlich) | Text | The OpenRouter model slug, e.g. anthropic/claude-3.5-sonnet. |
| Authentication (erforderlich) | Credential | Use your OpenRouter API key as a Bearer token. |
| Options | Group | The options to use with the model. |
| Options › Temperature | Number | The temperature to use for the model. |
| Options › Max Retries | Number | The maximum number of retries to use for the model. Standard: 2 |
| Options › Max Tokens | Number | The most tokens the model may generate in one reply. Defaults to 4096, which keeps providers from reserving credit for the whole output window. Standard: 4096 |
Model is OpenRouter’s model slug, in the form provider/model, for example anthropic/claude-3.5-sonnet. Copy it from the model’s page on OpenRouter.
Outputs
Section titled “Outputs”This node has no output port. It plugs into a slot on another node instead of passing items along.
- Model slot of Tools Agent, Q&A Agent, RAG Agent, Basic LLM Chain, Indexer, Text Classifier, Sentiment Analysis, Summarization, Information Extractor, Guardrails, Auto-fixing Output Parser
The AI node you connect it to produces the output. Chat OpenRouter only decides which model answers.
Dependencies and credentials
Section titled “Dependencies and credentials”- Authentication (connection): required. See Connect OpenRouter.
In Authentication, use a Bearer Token credential that holds your OpenRouter API key. Create the key at openrouter.ai/keys. See Create a credential.
Example workflow
Section titled “Example workflow”- A Context Menu trigger on selected text.
- Sentiment Analysis with Text
{{ $input.selectionText }}. - Chat OpenRouter in its Model slot, Model
anthropic/claude-3.5-sonnet. - Browser Notification with Message
{{ $input.sentiment }}.
Common issues
Section titled “Common issues”- “Model parameter is required and cannot be empty”. Fill in Model.
- A 402 error. Your OpenRouter balance is too low for the request. Add credit, or lower Max Tokens.
- A “not a valid model ID” error. The slug is wrong. Copy it exactly from OpenRouter, including the
provider/part. - A 401 error. The key is wrong or deleted. Create a new key and update the credential.
Related nodes
Section titled “Related nodes”- Chat Anthropic, Chat OpenAI: go to one provider directly.
- Tools Agent: an agent that can use tools and memory.
- Sentiment Analysis: tell if a text is positive, negative or neutral.