AI & researchAggregateCodeExecute WorkflowExecute Workflow TriggerExecution Data

Submit batch request to Anthropic

Configured with Aggregate, Execute Workflow, Execute Workflow Trigger, Execution Data, and additional nodes. Review the connections and setup before adapting this template.

Download workflow JSON View files on GitHub ↗27 nodes · MIT

Workflow preview

Icons describe general node roles, inferred from node types. Inspect the parameters for the configured action.

Drag to pan; use + and − to zoom. Reconstructed from the exported node positions; nothing runs here. Dashed lines represent non-main connections. Full node names and notes appear below.

How it works

The exported workflow contains the following configured nodes. Their connections are shown above; inspect the JSON for the complete logic, expressions, and external actions.

Workflow node names, types, and operations
Node	Category	Type	Operation
Submit batch	Web / API	HTTP Request	POST
Check batch status	Web / API	HTTP Request	See node parameters
When Executed by Another Workflow	Trigger	Execute Workflow Trigger	See node parameters
Get results	Web / API	HTTP Request	See node parameters
Parse response	Code	Code	See node parameters
If ended processing	Routing	If	See node parameters
Batch Status Poll Interval	Wait	Wait	See node parameters
Run example	Trigger	Manual Trigger	See node parameters
One query example	Transform	Edit Fields	See node parameters
Delete original properties	Transform	Edit Fields	See node parameters
Construct 'requests' array	Transform	Aggregate	See node parameters
Set desired 'anthropic-version'	Transform	Edit Fields	See node parameters
Execute Workflow 'Process Multiple Prompts in Parallel with Anthropic Claude Batch API'	Subworkflow	Execute Workflow	See node parameters
Build batch 'request' object for single query	Code	Code	See node parameters
Simple Memory Store	Data store	Memory Buffer Window	See node parameters
Fill Chat Memory with example data	Data store	Memory Manager	See node parameters
Build batch 'request' object from Chat Memory and execution data	Code	Code	See node parameters
Load Chat Memory Data	Data store	Memory Manager	See node parameters
First Prompt Result	Integration	Execution Data	See node parameters
Second Prompt Result	Integration	Execution Data	See node parameters
Split Out Parsed Results	Transform	Split Out	See node parameters
Filter Second Prompt Results	Routing	Filter	See node parameters
Filter First Prompt Results	Routing	Filter	See node parameters
Join two example requests into array	Transform	Merge	See node parameters
Append execution data for single query example	Transform	Edit Fields	See node parameters
Append execution data for chat memory example	Transform	Edit Fields	See node parameters
Truncate Chat Memory	Data store	Memory Manager	See node parameters

Setup

Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
Connect your own credentials through n8n’s credential store. Replace REPLACE_WITH_* values with your resource identifiers.
Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
Run with synthetic data and harmless destinations. Enable triggers only after checking the actual outputs.

Requirements

An n8n instance with the listed node types and compatible versions. Service-connected workflows may require accounts, credentials, or paid APIs.

Credential types declared in the source

anthropicApi

Workflow notes

Parse response

JSONL separated by newlines

This workflow automates sending batched prompts to Claude using the Anthropic API. It submits multiple prompts at once and retrieves the results.

How to use

Call this workflow with array of requests

{
    "anthropic-version": "2023-06-01",
    "requests": [
        {
            "custom_id": "first-prompt-in-my-batch",
            "params": {
                "max_tokens": 100,
                "messages": [
                    {
                        "content": "Hey Claude, tell me a short fun fact about video games!",
                        "role": "user"
                    }
                ],
                "model": "claude-3-5-haiku-20241022"
            }
        }
    ]
}

Results

This workflow returns an array of results with custom_ids.

[
    {
        "custom_id": "first-prompt-in-my-batch",
        "result": {
            "message": {
                "content": [
                    {
                        "text": "Did you know that the classic video game Tetris was...",
                        "type": "text"
                    }
                ],
                "id": "msg_01AiLiVZT18XnoBD4r2w9x2t",
                "model": "claude-3-5-haiku-20241022",
                "role": "assistant",
                "stop_reason": "end_turn",
                "stop_sequence": null,
                "type": "message",
                "usage": {
                    "cache_creation_input_tokens": 0,
                    "cache_read_input_tokens": 0,
                    "input_tokens": 45,
                    "output_tokens": 83
                }
            },
            "type": "succeeded"
        }
    }
]

Set desired 'anthropic-version'

2023-06-01

Execute Workflow 'Process Multiple Prompts in Parallel with Anthropic Claude Batch API'

See above

Retrieve Message Batch Results

User guide

Environment setup

For Chat History Node

anthropic-version

Documentation

When making API requests, you must send an anthropic-version request header. For example, anthropic-version: 2023-06-01 (latest supported version)

Append execution data for single query example

custom_id, model and max tokens

Truncate Chat Memory

ensure clean state

Submit batch request to Anthropic

Purpose and structure

This folder contains the Submit batch request to Anthropic workflow. Its executable nodes use aggregate, code, executeWorkflow, executeWorkflowTrigger, executionData, filter, httpRequest, if, manualTrigger, memoryBufferWindow, memoryManager, merge, set, splitOut, wait. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.

Setup

Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.

Entry points

When Executed by Another Workflow, Run example

Verification

Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.

Attribution

https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Wait/0826_Wait_Splitout_Automation_Webhook.json MIT; preserve source notices.

Canvas section labels

These name areas of the original canvas; they do not include explanatory instructions.

Usage example
Submit batch request to Anthropic
Loop until processing status is 'ended'
Example usage with Chat History Node
Example usage with single query string
Example usage with Chat History Node (result)
Example usage with single query string (result)

More in AI & research

"Hey Siri, Ask Agent" workflow #️⃣Nostr #damus AI Powered Reporting + Gmail + Telegram (G) - Email Classification

Node categories in this workflow

How it works

Setup

Requirements

Credential types declared in the source

Workflow notes

This workflow automates sending batched prompts to Claude using the Anthropic API. It submits multiple prompts at once and retrieves the results.

How to use

Results

Retrieve Message Batch Results

Environment setup

anthropic-version

Submit batch request to Anthropic

Purpose and structure

Setup

Entry points

Verification

Attribution

Canvas section labels

More in AI & research