# Cold Email Rewriter - AI Variants for Outbound A/B Tests (`fetchcraft/cold-email-rewriter`) Actor

Rewrite cold-email drafts into 2 to 5 AI variants with different angles, hooks, and tones. Bring your own LLM key (Gemini free, Groq free, Anthropic paid). Designed for outbound A/B tests, sequence variants, and inbox-fatigue mitigation. Pay per variant. Free preview.

- **URL**: https://apify.com/fetchcraft/cold-email-rewriter.md
- **Developed by:** [Emily Ward](https://apify.com/fetchcraft) (community)
- **Categories:** Marketing, AI, Lead generation
- **Stats:** 2 total users, 1 monthly users, 78.6% runs succeeded, NaN bookmarks
- **User rating**: No ratings yet

## Pricing

$100.00 / 1,000 cold email rewrite generateds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event

## What's an Apify Actor?

Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md):

```bash
npm install apify-client
```

In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md):

```bash
pip install apify-client
```

In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md):

````bash
# MacOS / Linux
curl -fsSL https://apify.com/install-cli.sh | bash
# Windows
irm https://apify.com/install-cli.ps1 | iex
```bash

In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md).

If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).


# README

## Cold Email Rewriter + Reply Rate Predictor

**Paste a cold email draft. Get back a predicted reply rate plus 3 stronger variants tuned for different buyer responses.**

Powered by Claude Sonnet 4.6. Pay only per rewrite. No subscription.

### What you get back per draft

| Field | Description |
| --- | --- |
| `original_reply_rate` | Predicted reply rate of your original draft (0 to 100) |
| `original_diagnosis` | One paragraph explaining what holds your draft back |
| `variants` | 3 rewritten variants, each hitting a different angle |
| `best_variant_subject` | The variant with the highest predicted reply rate |
| `best_variant_reply_rate` | The reply rate predicted for that best variant |

Each variant includes its own subject, body, angle (specificity / brevity / social proof / curiosity / contrarian), predicted reply rate, and reasoning.

### Pricing

Pay per rewrite generated, $0.10 USD per draft processed (you get 3 variants per rewrite).

You only pay for successful results. Failed drafts (malformed JSON, API errors) are not charged.

Typical use:
- 10 drafts: $1.00
- 50 drafts: $5.00
- 500 drafts: $50.00

Compare to Smartwriter at $59/mo or Lavender at $29/mo subscription minimums.

### How to use it

1. Click **Try for free** at the top of this page.
2. Paste your cold email drafts into the `drafts` field (array of `{subject, body}` objects).
3. Write a paragraph describing your audience (role, company size, what they care about).
4. Pick how many variants per draft (1 to 5, default 3).
5. Hit **Start**. Results stream into the dataset as each rewrite finishes.

### Use cases

- **SDR teams**: A/B test 3 angles per outreach campaign without writing copy by hand.
- **Founders**: Sanity-check your cold emails before sending. Know which subject lines actually work.
- **Agencies**: Deliver rewritten cold-email sequences to clients in minutes, not days.
- **Marketing teams**: Generate variant libraries for sequence tools like Smartlead, Lemlist, Instantly.

### What this actor does NOT do

- It does not send emails. Use Smartlead, Lemlist, or SMTP for sending.
- It does not generate emails from scratch. It rewrites existing drafts. For greenfield personalization, use the [AI Sales Personalizer Actor](https://apify.com/fetchcraft/ai-sales-personalizer).
- It does not personalize per recipient. It improves the template. For per-recipient personalization, use the Sales Personalizer.

### Companion: AI Sales Personalizer

Build the personalized opener once per company with the Sales Personalizer ($0.15/result), then rewrite the surrounding template with this actor ($0.10/rewrite). Together they replace Lavender + Smartwriter + the human copy editor.

### Tags

`ai` `cold-email` `copywriting` `sales` `sdr` `outreach` `claude` `b2b` `email-marketing` `ab-testing`

---

Made with Claude Sonnet 4.6 by Emily Ward, Cancel Costs.


### Integrations

This actor works out of the box with every Apify-supported integration:

- **API**: call via Apify API or any official SDK (Python, JavaScript, PHP, .NET). Returns a clean dataset URL.
- **Schedule**: set a daily, weekly, or custom cron cadence in Apify Console. Combine with `notification` for fresh feeds.
- **Webhooks**: wire `ACTOR.RUN.SUCCEEDED` to Slack, Discord, Zapier, Make, n8n, Pipedream, or any HTTPS endpoint.
- **MCP**: this actor is discoverable through Apify's hosted MCP server at `mcp.apify.com` for Claude, Cursor, Cline, Windsurf, and other MCP clients.
- **n8n / Make / Zapier**: native HTTP-Request integration. Trigger the actor on schedule, pipe results to Google Sheets, Airtable, your CRM, or any database.

### Try it free

Every Apify user gets **$5/month in free platform credits** (around 250 events at this actor's per-event price). Run preview mode first to confirm output shape before scaling.

New to Apify? [Sign up here](https://apify.com/sign-up?fpr=fetchcraft) to get free credits on signup.

### What's New

- 2026-06-03: Metadata, categories, and SEO refreshed. Latest version live on Apify Store.

### Last Updated

2026-06-03

# Actor input Schema

## `drafts` (type: `array`):

List of cold email drafts to rewrite. Each item has a subject and body. The AI predicts reply rate and generates 3 stronger variants per draft.
## `audience_description` (type: `string`):

Who you are writing to. Role, company size, what they care about. The AI uses this to tune variants for their language and priorities.
## `variants_per_draft` (type: `integer`):

How many rewritten variants to generate per input draft. Higher = more A/B options but higher cost.
## `max_concurrency` (type: `integer`):

How many drafts to process in parallel.
## `llm_provider` (type: `string`):

Pick which LLM you want. Gemini is recommended (1500 free requests/day at https://aistudio.google.com/apikey). Groq also good (14400 free/day at https://console.groq.com/keys). Leave blank to use the actor owner's configured key (if any).
## `llm_api_key` (type: `string`):

Paste the API key for the provider you selected. Never leaves the Apify run, never logged. Free tier providers (Gemini, Groq) give thousands of free results per day.

## Actor input object example

```json
{
  "drafts": [
    {
      "subject": "Quick question about your tech stack",
      "body": "Hi {{first_name}},\n\nI noticed your team uses Snowflake and I think we could help cut your cloud spend. We've helped other companies save 30%+ on similar workloads.\n\nWould you be open to a quick 15-min chat next week?\n\nBest,\nAlex"
    }
  ],
  "audience_description": "Heads of Data and CTOs at series B to series D SaaS companies (100 to 500 employees), focused on cloud cost control and FinOps maturity.",
  "variants_per_draft": 3,
  "max_concurrency": 5,
  "llm_provider": ""
}
````

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "drafts": [
        {
            "subject": "Quick question about your tech stack",
            "body": "Hi {{first_name}},\n\nI noticed your team uses Snowflake and I think we could help cut your cloud spend. We've helped other companies save 30%+ on similar workloads.\n\nWould you be open to a quick 15-min chat next week?\n\nBest,\nAlex"
        }
    ],
    "audience_description": "Heads of Data and CTOs at series B to series D SaaS companies (100 to 500 employees), focused on cloud cost control and FinOps maturity."
};

// Run the Actor and wait for it to finish
const run = await client.actor("fetchcraft/cold-email-rewriter").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "drafts": [{
            "subject": "Quick question about your tech stack",
            "body": """Hi {{first_name}},

I noticed your team uses Snowflake and I think we could help cut your cloud spend. We've helped other companies save 30%+ on similar workloads.

Would you be open to a quick 15-min chat next week?

Best,
Alex""",
        }],
    "audience_description": "Heads of Data and CTOs at series B to series D SaaS companies (100 to 500 employees), focused on cloud cost control and FinOps maturity.",
}

# Run the Actor and wait for it to finish
run = client.actor("fetchcraft/cold-email-rewriter").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "drafts": [
    {
      "subject": "Quick question about your tech stack",
      "body": "Hi {{first_name}},\\n\\nI noticed your team uses Snowflake and I think we could help cut your cloud spend. We'\''ve helped other companies save 30%+ on similar workloads.\\n\\nWould you be open to a quick 15-min chat next week?\\n\\nBest,\\nAlex"
    }
  ],
  "audience_description": "Heads of Data and CTOs at series B to series D SaaS companies (100 to 500 employees), focused on cloud cost control and FinOps maturity."
}' |
apify call fetchcraft/cold-email-rewriter --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "command": "npx",
            "args": [
                "mcp-remote",
                "https://mcp.apify.com/?tools=fetchcraft/cold-email-rewriter",
                "--header",
                "Authorization: Bearer <YOUR_API_TOKEN>"
            ]
        }
    }
}

```

## OpenAPI specification

```json
{
    "openapi": "3.0.1",
    "info": {
        "title": "Cold Email Rewriter - AI Variants for Outbound A/B Tests",
        "description": "Rewrite cold-email drafts into 2 to 5 AI variants with different angles, hooks, and tones. Bring your own LLM key (Gemini free, Groq free, Anthropic paid). Designed for outbound A/B tests, sequence variants, and inbox-fatigue mitigation. Pay per variant. Free preview.",
        "version": "0.1",
        "x-build-id": "6UrMfWCcOdECAX7jQ"
    },
    "servers": [
        {
            "url": "https://api.apify.com/v2"
        }
    ],
    "paths": {
        "/acts/fetchcraft~cold-email-rewriter/run-sync-get-dataset-items": {
            "post": {
                "operationId": "run-sync-get-dataset-items-fetchcraft-cold-email-rewriter",
                "x-openai-isConsequential": false,
                "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
                "tags": [
                    "Run Actor"
                ],
                "requestBody": {
                    "required": true,
                    "content": {
                        "application/json": {
                            "schema": {
                                "$ref": "#/components/schemas/inputSchema"
                            }
                        }
                    }
                },
                "parameters": [
                    {
                        "name": "token",
                        "in": "query",
                        "required": true,
                        "schema": {
                            "type": "string"
                        },
                        "description": "Enter your Apify token here"
                    }
                ],
                "responses": {
                    "200": {
                        "description": "OK"
                    }
                }
            }
        },
        "/acts/fetchcraft~cold-email-rewriter/runs": {
            "post": {
                "operationId": "runs-sync-fetchcraft-cold-email-rewriter",
                "x-openai-isConsequential": false,
                "summary": "Executes an Actor and returns information about the initiated run in response.",
                "tags": [
                    "Run Actor"
                ],
                "requestBody": {
                    "required": true,
                    "content": {
                        "application/json": {
                            "schema": {
                                "$ref": "#/components/schemas/inputSchema"
                            }
                        }
                    }
                },
                "parameters": [
                    {
                        "name": "token",
                        "in": "query",
                        "required": true,
                        "schema": {
                            "type": "string"
                        },
                        "description": "Enter your Apify token here"
                    }
                ],
                "responses": {
                    "200": {
                        "description": "OK",
                        "content": {
                            "application/json": {
                                "schema": {
                                    "$ref": "#/components/schemas/runsResponseSchema"
                                }
                            }
                        }
                    }
                }
            }
        },
        "/acts/fetchcraft~cold-email-rewriter/run-sync": {
            "post": {
                "operationId": "run-sync-fetchcraft-cold-email-rewriter",
                "x-openai-isConsequential": false,
                "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
                "tags": [
                    "Run Actor"
                ],
                "requestBody": {
                    "required": true,
                    "content": {
                        "application/json": {
                            "schema": {
                                "$ref": "#/components/schemas/inputSchema"
                            }
                        }
                    }
                },
                "parameters": [
                    {
                        "name": "token",
                        "in": "query",
                        "required": true,
                        "schema": {
                            "type": "string"
                        },
                        "description": "Enter your Apify token here"
                    }
                ],
                "responses": {
                    "200": {
                        "description": "OK"
                    }
                }
            }
        }
    },
    "components": {
        "schemas": {
            "inputSchema": {
                "type": "object",
                "required": [
                    "drafts",
                    "audience_description"
                ],
                "properties": {
                    "drafts": {
                        "title": "Email drafts",
                        "type": "array",
                        "description": "List of cold email drafts to rewrite. Each item has a subject and body. The AI predicts reply rate and generates 3 stronger variants per draft."
                    },
                    "audience_description": {
                        "title": "Audience description (one paragraph)",
                        "minLength": 20,
                        "maxLength": 1500,
                        "type": "string",
                        "description": "Who you are writing to. Role, company size, what they care about. The AI uses this to tune variants for their language and priorities."
                    },
                    "variants_per_draft": {
                        "title": "Variants per draft",
                        "minimum": 1,
                        "maximum": 5,
                        "type": "integer",
                        "description": "How many rewritten variants to generate per input draft. Higher = more A/B options but higher cost.",
                        "default": 3
                    },
                    "max_concurrency": {
                        "title": "Max parallel requests",
                        "minimum": 1,
                        "maximum": 20,
                        "type": "integer",
                        "description": "How many drafts to process in parallel.",
                        "default": 5
                    },
                    "llm_provider": {
                        "title": "LLM provider (bring your own key)",
                        "enum": [
                            "",
                            "gemini",
                            "groq",
                            "cerebras",
                            "openrouter",
                            "huggingface",
                            "anthropic"
                        ],
                        "type": "string",
                        "description": "Pick which LLM you want. Gemini is recommended (1500 free requests/day at https://aistudio.google.com/apikey). Groq also good (14400 free/day at https://console.groq.com/keys). Leave blank to use the actor owner's configured key (if any).",
                        "default": ""
                    },
                    "llm_api_key": {
                        "title": "Your LLM API key (paired with llm_provider above)",
                        "type": "string",
                        "description": "Paste the API key for the provider you selected. Never leaves the Apify run, never logged. Free tier providers (Gemini, Groq) give thousands of free results per day."
                    }
                }
            },
            "runsResponseSchema": {
                "type": "object",
                "properties": {
                    "data": {
                        "type": "object",
                        "properties": {
                            "id": {
                                "type": "string"
                            },
                            "actId": {
                                "type": "string"
                            },
                            "userId": {
                                "type": "string"
                            },
                            "startedAt": {
                                "type": "string",
                                "format": "date-time",
                                "example": "2025-01-08T00:00:00.000Z"
                            },
                            "finishedAt": {
                                "type": "string",
                                "format": "date-time",
                                "example": "2025-01-08T00:00:00.000Z"
                            },
                            "status": {
                                "type": "string",
                                "example": "READY"
                            },
                            "meta": {
                                "type": "object",
                                "properties": {
                                    "origin": {
                                        "type": "string",
                                        "example": "API"
                                    },
                                    "userAgent": {
                                        "type": "string"
                                    }
                                }
                            },
                            "stats": {
                                "type": "object",
                                "properties": {
                                    "inputBodyLen": {
                                        "type": "integer",
                                        "example": 2000
                                    },
                                    "rebootCount": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "restartCount": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "resurrectCount": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "computeUnits": {
                                        "type": "integer",
                                        "example": 0
                                    }
                                }
                            },
                            "options": {
                                "type": "object",
                                "properties": {
                                    "build": {
                                        "type": "string",
                                        "example": "latest"
                                    },
                                    "timeoutSecs": {
                                        "type": "integer",
                                        "example": 300
                                    },
                                    "memoryMbytes": {
                                        "type": "integer",
                                        "example": 1024
                                    },
                                    "diskMbytes": {
                                        "type": "integer",
                                        "example": 2048
                                    }
                                }
                            },
                            "buildId": {
                                "type": "string"
                            },
                            "defaultKeyValueStoreId": {
                                "type": "string"
                            },
                            "defaultDatasetId": {
                                "type": "string"
                            },
                            "defaultRequestQueueId": {
                                "type": "string"
                            },
                            "buildNumber": {
                                "type": "string",
                                "example": "1.0.0"
                            },
                            "containerUrl": {
                                "type": "string"
                            },
                            "usage": {
                                "type": "object",
                                "properties": {
                                    "ACTOR_COMPUTE_UNITS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "DATASET_READS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "DATASET_WRITES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "KEY_VALUE_STORE_READS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "KEY_VALUE_STORE_WRITES": {
                                        "type": "integer",
                                        "example": 1
                                    },
                                    "KEY_VALUE_STORE_LISTS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "REQUEST_QUEUE_READS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "REQUEST_QUEUE_WRITES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "DATA_TRANSFER_INTERNAL_GBYTES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "DATA_TRANSFER_EXTERNAL_GBYTES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "PROXY_SERPS": {
                                        "type": "integer",
                                        "example": 0
                                    }
                                }
                            },
                            "usageTotalUsd": {
                                "type": "number",
                                "example": 0.00005
                            },
                            "usageUsd": {
                                "type": "object",
                                "properties": {
                                    "ACTOR_COMPUTE_UNITS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "DATASET_READS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "DATASET_WRITES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "KEY_VALUE_STORE_READS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "KEY_VALUE_STORE_WRITES": {
                                        "type": "number",
                                        "example": 0.00005
                                    },
                                    "KEY_VALUE_STORE_LISTS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "REQUEST_QUEUE_READS": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "REQUEST_QUEUE_WRITES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "DATA_TRANSFER_INTERNAL_GBYTES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "DATA_TRANSFER_EXTERNAL_GBYTES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                                        "type": "integer",
                                        "example": 0
                                    },
                                    "PROXY_SERPS": {
                                        "type": "integer",
                                        "example": 0
                                    }
                                }
                            }
                        }
                    }
                }
            }
        }
    }
}
```