Anthropic Connector
Description
Anthropic is an artificial intelligence safety company that develops and provides Claude, a family of large language models. This component allows sending chat messages to Claude, counting tokens, and managing available models.
API Documentation
This component was built using the Anthropic Messages API.
Connections
Anthropic API
key: anthropicSetup Steps
To generate an API key:
- Navigate to API Keys and select create key
- Enter the API key value into the connection configuration of the integration.
| Input | Notes | Example |
|---|---|---|
| API Key | Your Anthropic API key. |
Data Sources
List Models
List all available Claude models. | key: selectModel | type: picklist
| Input | Notes | Example |
|---|---|---|
| Connection | The Anthropic API connection to use. |
Example Payload for List Models⤓
Actions
Chat
Start a new conversation with Claude. | key: chat
| Input | Notes | Example |
|---|---|---|
| Connection | The Anthropic API connection to use. | |
| Message | The message to send in the conversation. | What is the capital of France? |
| Max Tokens | Maximum number of tokens to generate (default: 4096). | 1000 |
| Model | The Claude model to use. | claude-sonnet-4-6 |
| System Prompt | A system prompt to set the context and behavior for the conversation. | You are a helpful AI assistant that specializes in answering questions about science. |
| Temperature | Randomness of the output (0-1, default: 1). Note: temperature is not supported on Claude Opus 4.7+ models and will return a 400 error if set to a non-default value. | 0.7 |
Example Payload for Chat⤓
Count Tokens
Count the number of tokens in a message or conversation. | key: countTokens
| Input | Notes | Example |
|---|---|---|
| Connection | The Anthropic API connection to use. | |
| Message | The message to send in the conversation. | What is the capital of France? |
| Model | The Claude model to use. | claude-sonnet-4-6 |
Example Payload for Count Tokens⤓
Get Model
Get details of a specific Claude model. | key: getModel
| Input | Notes | Example |
|---|---|---|
| Connection | The Anthropic API connection to use. | |
| Model | The Claude model to use. | claude-sonnet-4-6 |
Example Payload for Get Model⤓
List Models
List all available Claude models. | key: listModels
| Input | Notes | Example |
|---|---|---|
| Connection | The Anthropic API connection to use. | |
| Fetch All | When true, automatically fetches all pages of results. The Limit, After ID, and Before ID inputs are ignored. | false |
| Pagination | Cursor and page-size controls for paging through results. |
Example Payload for List Models⤓
Raw Request
Send raw HTTP request to Anthropic. | key: rawRequest
| Input | Notes | Example |
|---|---|---|
| Connection | The Anthropic API connection to use. | |
| Data | The HTTP body payload to send to the URL. | {"exampleKey": "Example Data"} |
| File Data | File Data to be sent as a multipart form upload. | [{key: "example.txt", value: "My File Contents"}] |
| File Data File Names | File names to apply to the file data inputs. Keys must match the file data keys above. | |
| Form Data | The Form Data to be sent as a multipart form upload. | [{"key": "Example Key", "value": new Buffer("Hello World")}] |
| Header | A list of headers to send with the request. | User-Agent: curl/7.64.1 |
| Max Retry Count | The maximum number of retries to attempt. Specify 0 for no retries. | 0 |
| Method | The HTTP method to use. | |
| Query Parameter | A list of query parameters to send with the request. This is the portion at the end of the URL similar to ?key1=value1&key2=value2. | |
| Response Type | The type of data you expect in the response. You can request json, text, or binary data. | json |
| Retry On All Errors | If true, retries on all erroneous responses regardless of type. This is helpful when retrying after HTTP 429 or other 3xx or 4xx errors. Otherwise, only retries on HTTP 5xx and network errors. | false |
| Retry Delay (ms) | The delay in milliseconds between retries. This is used when 'Use Exponential Backoff' is disabled. | 0 |
| Timeout | The maximum time that a client will await a response to its request | 2000 |
| URL | Input the path only (/models), The base URL is already included (https://api.anthropic.com/v1). For example, to connect to https://api.anthropic.com/v1/models, only /models is entered in this field. | /models |
| Use Exponential Backoff | Specifies whether to use a pre-defined exponential backoff strategy for retries. When enabled, 'Retry Delay (ms)' is ignored. | false |
Example Payload for Raw Request⤓
Changelog
2026-08-14
- Corrected the Limit range on the List Models action from 1-3 to 1-1000 to match Anthropic's documented maximum; Fetch All now pages at 1000 records instead of 3
- Updated the default model from claude-3-5-sonnet-latest to claude-sonnet-4-6 across all actions
- Grouped pagination inputs on the List Models action into a Pagination structured object, with Fetch All remaining a top-level toggle
- Added output schemas to the Chat, Count Tokens, Get Model, and List Models actions for improved field mapping during configuration
- Added inline action calling support across all actions for improved example output during configuration
2026-04-30
Updated spectral version
2026-03-31
Various modernizations and documentation updates
2026-03-25
- Updated documentation and various modernizations
2025-05-21
Initial release of Anthropic component with AI chat completion, token counting, and model management capabilities