Skip to content
For LLMsView as Markdown·

Anthropic

Generate text with Claude models via the Anthropic Messages API.

DetailValue
CategoryAI
Base URLhttps://api.anthropic.com/v1
AuthenticationAPI Key
Endpoints4
Connector keyanthropic

Using Anthropic in a workflow

  1. Go to Connections and click New Connection.
  2. Pick Anthropic from the marketplace.
  3. Enter your credentials (see Authentication above for what's expected).
  4. In a workflow, drop an API Call node and select this connection.
  5. Pick the operation you need from the Operation dropdown — the full list is below.

Available endpoints

EndpointSummary
POST /messagesCreate a message
POST /messages/batchesCreate a message batch
GET /messages/batches/{batch_id}Get batch status
GET /messages/batchesList message batches

Each endpoint is documented in full below. Use the outline on the right to jump to one.

POST /messages

Create a message

DetailValue
Operation IDai.createMessage
MethodPOST
Path/messages

Parameters

No parameters.

Request Body

FieldType
modelstring
max_tokensinteger
messagesarray

Using this endpoint in a workflow

  1. Add an API Call node to your workflow.
  2. Pick your Anthropic connection from the Connection dropdown.
  3. In the Operation dropdown, select ai.createMessage.
  4. Fill in the parameter fields that appear. Use {{...}} to reference upstream values.

Required fields are marked — fill them or the call will fail at runtime.

What it returns

The API Call node writes the response to the workflow context:

{
  status: 200,
  success: true,
  data: { ...response body from the API... },
  latencyMs: 142
}

Reference response fields downstream as {{nodeId.data.path}}. The exact response shape is documented on the upstream Anthropic API reference.

POST /messages/batches

Create a message batch

DetailValue
Operation IDai.createBatch
MethodPOST
Path/messages/batches

Parameters

No parameters.

Request Body

FieldType
requestsarray

Using this endpoint in a workflow

  1. Add an API Call node to your workflow.
  2. Pick your Anthropic connection from the Connection dropdown.
  3. In the Operation dropdown, select ai.createBatch.
  4. Fill in the parameter fields that appear. Use {{...}} to reference upstream values.

Required fields are marked — fill them or the call will fail at runtime.

What it returns

The API Call node writes the response to the workflow context:

{
  status: 200,
  success: true,
  data: { ...response body from the API... },
  latencyMs: 142
}

Reference response fields downstream as {{nodeId.data.path}}. The exact response shape is documented on the upstream Anthropic API reference.

GET /messages/batches/{batch_id}

Get batch status

DetailValue
Operation IDai.getBatch
MethodGET
Path/messages/batches/{batch_id}

Parameters

NameLocationTypeRequired
batch_idpathstringYes

Using this endpoint in a workflow

  1. Add an API Call node to your workflow.
  2. Pick your Anthropic connection from the Connection dropdown.
  3. In the Operation dropdown, select ai.getBatch.
  4. Fill in the parameter fields that appear. Use {{...}} to reference upstream values.

Required fields are marked — fill them or the call will fail at runtime.

What it returns

The API Call node writes the response to the workflow context:

{
  status: 200,
  success: true,
  data: { ...response body from the API... },
  latencyMs: 142
}

Reference response fields downstream as {{nodeId.data.path}}. The exact response shape is documented on the upstream Anthropic API reference.

GET /messages/batches

List message batches

DetailValue
Operation IDai.listBatches
MethodGET
Path/messages/batches

Parameters

NameLocationTypeRequired
limitqueryintegerNo

Using this endpoint in a workflow

  1. Add an API Call node to your workflow.
  2. Pick your Anthropic connection from the Connection dropdown.
  3. In the Operation dropdown, select ai.listBatches.
  4. Fill in the parameter fields that appear. Use {{...}} to reference upstream values.

What it returns

The API Call node writes the response to the workflow context:

{
  status: 200,
  success: true,
  data: { ...response body from the API... },
  latencyMs: 142
}

Reference response fields downstream as {{nodeId.data.path}}. The exact response shape is documented on the upstream Anthropic API reference.