Claude

Node catalog Artificial intelligence

On this page

Multimodal chat and analysis via Anthropic

Usage and specifics

Select a provider credential, an accessible model and prompts. Image, document and structured JSON support depend on model capabilities. Output exposes text, model, usage, json and attachmentsProcessed. A suggested default model is not a guarantee of availability.

Technical type : ai_claude. Runtime : nodulz.

Credentials and prerequisites

Create and configure the credential : anthropic

Create credentials in your nodulz instance’s Credentials area, then select them on the node. Availability depends on ownership and sharing. See the credentials guide for access and rotation.

Parameters

Names below are technical keys. Defaults are not a ready-to-run configuration: complete fields required by your operation. Paths containing [] describe list items; some fields depend on the selected mode.

Parameter	Type	Default	Values / limits
`credentialId`	`string`	-	-
`model`	`string`	`"claude-sonnet-5"`	-
`systemPrompt`	`string`	`""`	-
`userPrompt`	`string`	`""`	-
`temperature`	`number`	-	-; ≥ 0, ≤ 2
`maxTokens`	`number`	-	-; ≥ 1
`timeoutSeconds`	`number`	-	-; ≥ 1, ≤ 3600
`attachments`	`array`	`[]`	-
`attachments[].kind`	`enum`	`"text"`	`text`, `image_url`, `image_base64`, `document_url`, `document_base64`
`attachments[].sourceMode`	`enum`	`"manual"`	`manual`, `node`, `file`
`attachments[].source`	`string`	`""`	-
`attachments[].mimeType`	`string`	-	-
`attachments[].name`	`string`	-	-
`messages`	`array`	`[]`	-
`messages[].role`	`enum`	`"user"`	`user`, `assistant`, `system`
`messages[].content`	`string`	`""`	-
`responseFormat`	`enum`	`"text"`	`text`, `json`
`jsonSchema`	`string`	`""`	-

Configuration help

credentialId AI credential: API key stored on the Credentials page for this provider.
model Model: Model identifier at the provider (e.g. gpt-4o, claude-3-5-sonnet).
systemPrompt System prompt: System instructions sent to the model before the user prompt.
userPrompt User prompt: Main message - {{…}} expressions allowed.
temperature Temperature: Requested creativity (0 to 2). Leave empty for the model default. This parameter is omitted for OpenAI and Azure reasoning models that do not support it.
maxTokens Max tokens: Maximum output tokens, including reasoning for applicable models. Truncated responses fail: increase this limit or shorten the request.
timeoutSeconds Timeout (seconds): Maximum time for one model call, including attachments. From 1 to 3,600 seconds; defaults to 120. Cancelling the workflow also cancels the call.
responseFormat Response format: Free text or structured JSON (optional schema).
jsonSchema JSON schema (optional): Optional JSON schema to constrain and validate the json output. Use a model that supports structured outputs. For OpenAI strict mode: root object, required fields and additionalProperties set to false. Nonconforming output fails.

Examples

User prompt

Initial configuration

Initial catalog configuration example, to adapt before running. Keep secrets in credentials.

json

{
  "model": "claude-sonnet-5",
  "systemPrompt": "",
  "userPrompt": "",
  "attachments": [],
  "messages": [],
  "responseFormat": "text",
  "jsonSchema": ""
}

Verification

Test with representative data. Check node output in the inspector and logs, then use editor mapping for downstream fields. A trigger test with a simulated payload does not validate external service delivery.