# Kagayaki Prism: AI TikTok Brand-Creator Matchmaker (`kagayaki/tiktok-brand-influencer-matchmaker`) Actor

Kagayaki Prism is an elite AI data engine that matches your brand to the perfect TikTok influencers. It automatically finds high-performing creators in your niche, checks if their audience fits your brand, and writes custom outreach messages so you can launch campaigns with zero manual scrolling. 🚀

- **URL**: https://apify.com/kagayaki/tiktok-brand-influencer-matchmaker.md
- **Developed by:** [Kagayaki Consult](https://apify.com/kagayaki) (community)
- **Categories:** Lead generation, Automation, Social media
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $1,500.00 / 1,000 matched creator results

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.

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

## 🚀 Kagayaki Prism: AI TikTok Brand-Creator Matchmaker

[![Platform: TikTok](https://img.shields.io/badge/Platform-TikTok-000000?style=for-the-badge&logo=tiktok&logoColor=white)](https://apify.com)
[![Category: AI Lead Gen](https://img.shields.io/badge/Category-AI--Lead--Gen-FF0050?style=for-the-badge&logo=ai&logoColor=white)](https://apify.com)
[![Export: Excel / CSV / JSON](https://img.shields.io/badge/Export-Excel%20%7C%20CSV%20%7C%20JSON-007ACC?style=for-the-badge)](https://apify.com)

> **Simple, predictable pricing: $1.50 per matched influencer profile.**

**Kagayaki Prism** is an autonomous, AI-driven platform orchestration engine engineered to instantly close the gap between enterprise brands and highly aligned content creators. By feeding raw, natural language business summaries into our Agentic AI layer, Prism automatically generates localized hyper-targeted search vectors, orchestrates underlying scraping layers, aggregates content density metrics, and mathematically rates creator alignment to extract high-quality, ready-to-use B2B lead pipelines.

---

### 💼 High-Value Business Use Cases

* **🌍 Global Multi-Market Campaigns:** Target whole economic blocks or comma-separated specific lists of country ISO codes (e.g., `ke,tz,ug`) simultaneously with automatic real-time query localization.
* **📈 Highly Targeted Influencer Tiering:** Filter across exact community sizes matching your budget targets from high-engagement **Nano** and **Micro** networks to broad-market **Macro** and **Mega** scales.
* **🏎️ Zero-Friction Sales Pipelines:** Eliminate weeks of manual scouting. Prism analyzes historical posting frequency against your specific niche keywords to output clean content density scores.
* **🤖 AI-Generated Platform Outreach:** Every single discovered profile includes a hyper-personalized, high-converting outreach DM pitch tailored directly to that specific creator's tone and localized region.

---

### 📖 How Prism Thinks: A Simple Walkthrough

To see how Kagayaki Prism operates under the hood, let's look at how it runs using a concrete example optimized for the East African market.

#### 👟 The Optimized Input Profile
Imagine you are launching a footwear line and provide the engine with this description:
> *"Affordable, trendy streetwear sneakers, canvas thrift-style shoes, and casual footwear targeting campus students and young corporate professionals in Nairobi. Focuses on budget-friendly fashion, everyday comfort, thrift-shopping aesthetics (Gikomba/Toi market vibes but curated), and urban lifestyle style-guides."*

When you hit execute, the engine evaluates your input parameters and intelligently routes the campaign down one of two clear structural paths based entirely on whether you provide a competitor's handle.

#### 🕵️ Path A: You Provide a Competitor Handle
If you include a specific competitor link or handle (for instance, `@bata_kenya` or a localized fashion boutique handle), Prism kicks off a specialized **Competitor Intelligence Phase**:
1. It pauses standard algorithmic keyword generation and deploys an isolated profile scraper directly to that competitor's timeline.
2. It reverse-engineers their most successful organic video posts—scanning their captions, analyzing their text overlays, and isolating their highest-performing local hashtags.
3. The background AI then seamlessly injects these proven real-world hooks directly into your brand strategy, ensuring your downstream discovery search is anchored against established market rivals.

#### 🌾 Path B: You Leave the Competitor Field Blank
If you leave the competitor input field completely empty, Prism's initialization wrapper cleanly catches it, safeguards the runtime sequence from breaking, and immediately pivots to **Multi-Tier Keyword Layering**:
1. The Agentic AI reads your brand profile description and splits its search strategy into distinct focus layers.
2. First, it extracts **Tier-1 Direct Product Terms** (like `streetwear sneakers Nairobi` or `thrift style shoes Kenya`).
3. Simultaneously, it maps out **Tier-2 Demographic Lifestyle Crossovers**. It understands that your audience hangs out with lifestyle creators, so it generates broader search targets like `Nairobi campus fashion lookbook` or `Get Ready With Me Nairobi style guide`.
4. Finally, it launches a unified search grid swarm. This lets you discover high-impact lifestyle creators who perfectly influence your target shoppers, even if those creators have never explicitly reviewed a shoe on camera before.

Once either path completes its search strategy phase, the engine pipes all discovered accounts through our OpenRouter Gemini evaluation pipeline, calculates their final alignment scores, and creates hyper-personalized outreach DMs written in natural local slang.

#### 🎯 What to Expect: Actionable Intelligence Insights
When the orchestration engine finishes its run, it converts raw social media noise into an actionable sales directory. Below is a structural breakdown of exactly how different creator profiles pass through the filter, showing how you can instantly target them based on their mathematical match profiles:

| 👤 Creator Handle | 📊 Match Score | 🏷️ Primary Content Niche | 💡 Best Campaign Strategy & Use Case |
| :--- | :---: | :--- | :--- |
| **@nairobi_thrift_queen** | **94%** | Thrift Hauls, GRWM, & Campus Lookbooks | **High-Volume Gifting:** Send 2-3 free pairs of sneakers for an unboxing and an authentic "Thrift Styling Challenge" video targeting campus students. |
| **@corporate_chic_ke** | **82%** | Office Lookbooks & Young Professional Vlogs | **Affiliate Product Reviews:** Feature comfortable, casual canvas shoes in a "Day in the Life of a Nairobi Corporate Marketer" video with a trackable discount code. |
| **@vocal_politics_ke** | **0%** | Local News commentary & Political Debates | **Auto-Filtered Out:** Bypassed completely by the engine's security and commercial intent safety layers to prevent wasted ad spend on misaligned niches. |

---

### ⚠️ Troubleshooting Anomaly: Handling Zero-Yield Runs

TikTok's content ecosystem varies heavily by industry. If your execution loop runs successfully but finishes with `Engine execution yielded 0 matching creators`, **your script did not crash.** Prism's strict alignment layer is working exactly as built, dropping low-relevance profiles to keep your lead export data clean.

#### Why Did it Yield 0?
* **The Merchant Pitfall:** In practical, hardware-heavy, or emerging spaces (like e-mobility, electronics parts, or commercial solar setups), the local accounts using those exact keywords are almost always retail merchants, wholesalers, or distribution shops. Because they publish transactional product sales posts rather than audience-facing lifestyle content, Prism's evaluator flags them as business pages and drops their score to `0`.
* **Hyper-Restricted Descriptions:** If you input a thin, flat description (e.g., *"Selling solar batteries"*), the strategy generator doesn't have enough context to build demographic anchors, leading to empty search results.

#### How to Expand and Explode Your Discovery Yield
1. **Inject Demographic Hooks:** Rewrite your description to focus on *who* uses the product and *how* it fits their daily life. Instead of *"Electric bikes in Nairobi"*, expand it to *"Eco-friendly daily commutes for tech professionals and smart urban mobility lifestyle choices in Nairobi."* This forces the engine to scrape local tech vloggers and urban lifestyle creators.
2. **Relax the Qualification Slider:** Lower your `minMatchScore` slider from a rigid `75%` down to a broader `35-40%`. This permits the engine to surface macro-demographic creators who can easily pivot into featuring your brand.
3. **Incorporate Crossover Niches:** Blend a physical object with the digital space it lives in (e.g., pairing custom laptop sleeves with local university study-vloggers, or water bottles with outdoor hiking creators).

---

### 🎛️ Input Configuration Parameters

Prism features a strictly validated, intuitive interface natively designed to protect execution cycles from human input error:

| 🏷️ Field Title | ⚙️ Technical Key | 🛠️ Form Element | 📖 Context & Instructions |
| :--- | :--- | :--- | :--- |
| **Brand Profile Description** | `brandDescription` | Textarea | Enter a detailed summary of your product, service, target audience, and localized objectives. |
| **Competitor TikTok Handle** | `competitorHandle` | Text Input | *Optional.* Target competitor profile (e.g., `@username`) to extract metadata strategy hooks. Leave blank to bypass. |
| **Target Global Region** | `targetRegion` | Dropdown Menu | Select the geographical market anchor to orient the background AI agent. |
| **Specific Country Code(s)** | `targetCountry` | Regex Field | Enter a single 2-letter ISO country code or a comma-separated list (e.g. `ke,tz,ug`). *Strict format validation enabled.* |
| **Influencer Audience Tier** | `influencerTier` | Dropdown Menu | Target scale: Nano (1k-10k), Micro (10k-100k), Macro (100k-500k), or Mega (500k+). |
| **Min Match Score Threshold** | `minMatchScore` | Slider (0-100%) | Set the minimum mathematical qualification percentage for final pipeline export. |
| **OpenRouter API Key** | `openRouterApiKey` | Password Mask | Secure API credential token utilized to run background Gemini evaluation pipelines. |

---

### 🔑 Step-by-Step OpenRouter API Key Setup

Kagayaki Prism leverages **OpenRouter** to query advanced AI evaluation neural networks (like Gemini 1.5 Flash/Pro) seamlessly and affordably. Follow these simple steps to obtain your API credential key:

1. **Create an Account:** Visit [OpenRouter.ai](https://openrouter.ai/) and sign up for a developer account via email, GitHub, or Google.
2. **Credit Your Account:** OpenRouter works on an incredibly cost-effective pay-as-you-go credit model. Navigate to **Dashboard -> Credit** and add a balance (as little as $5.00 is plenty for thousands of analytical runs).
3. **Generate API Key:** Navigate to the **Keys** section inside your dashboard sidebar and click **"Create Key"**.
4. **Name and Copy Key:** Give your key a descriptive tag (e.g., `Kagayaki-Prism`) and hit save. **Crucial:** Copy and Save the generated token string instantly (it starts with `sk-or-v1-...`). You will not be able to view this token again.
5. **Paste and Lock into Prism:** Enter this key directly into the protected `openRouterApiKey` field inside the Apify Console when triggering a run. Your input is fully masked and PGP-encrypted.

---

### 📊 Live Production Output Dossier (Excel / CSV / JSON)

Apify natively manages underlying dataset transformations on demand. When your execution loop completes, you can immediately download your structured B2B lead dataset straight into **Excel (.xlsx)** or **CSV** to integrate with your outreach or CRM setups.

Below is an authentic fashion/streetwear dataset payload generated using the shoe brand template:

```json

  {
    "creatorHandle": "@nairobi_thrift_queen",
    "profileUrl": "[https://www.tiktok.com/@nairobi_thrift_queen](https://www.tiktok.com/@nairobi_thrift_queen)",
    "creatorName": "Elsa Nyambura",
    "primaryNiche": "Thrift Hauls, GRWM, & Campus Style Lookbooks",
    "matchScore": 94,
    "contentDensityPercent": 100,
    "fitJustification": "Highly relevant campus lifestyle vlogger regularly breaking down Gikomba and Toi market thrift breakdowns. Consistently showcases urban streetwear aesthetics to an active Nairobi university student demographic, matching the exact target profile.",
    "avgViews": 62400,
    "avgLikes": 7100,
    "avgComments": 312,
    "samplePostCount": 6,
    "personalizedOutreachDM": "Wazi Elsa! Your recent Toi market thrift haul styling was top tier. We love how you layer streetwear looks. We are launching a premium curated casual footwear line in Nairobi built for campus comfort and want to get a couple pairs over to you for an unboxing showcase. Let us know if you're down to check them out!"
  }
````

***

### ⚡ Stop Scrolling, Start Launching: Let’s Build Your Pipeline Together

Are you a marketing manager, agency account director, or startup founder spending hours manually searching through TikTok to find the right creators for your brand?

Manual discovery is slow, tedious, and relies heavily on guesswork. **Kagayaki Prism** eliminates the operational legwork by converting your raw campaign goals into a verified, high-performing creator directory at a flat rate of **$5.00 per qualified profile**.

#### ✨ What We Deliver in Every Single Profile:

- 🎯 **Smart Alignment Scoring:** Evaluated via highly fine-tuned AI models against your exact target audience, brand values, and specific market metrics.
- 📈 **Content Density Verification:** Hard data analyzing the creator's historical posting volume and consistency inside your business vertical.
- ✍️ **Localized Outreach Copy:** Hyper-personalized pitches generated natively to match regional communication styles and natural local slang hooks so your messages actually get answered.

***

#### 🤝 We Offer High-Touch Consulting Services

If you want to completely skip the operational legwork, the Kagayaki team can manage the entire discovery and vetting process for you. Simply share your target audience and campaign objectives with us, and we will deliver a completely finalized, localized creator roadmap with ready-to-use outreach strategies tailored directly to your business.

##### 🧪 Claim a Free Sample Run

We will gladly run a complimentary **10-profile mini-scan** tailored to your active, live campaign brief so you can see the speed and accuracy of our insights firsthand.

📧 **Get in Touch:** \[kagayakiconsult@gmail.com] / \[https://forms.gle/zFWRUV2JSN8Gk6qJ6]

***

🚀 **Kagayaki** — *Bridging the gap between advanced technical engineering and business operations.* ✨

# Actor input Schema

## `brandDescription` (type: `string`):

Enter a detailed summary of your brand identity, product lines, value proposition, and target audience context.

## `competitorHandle` (type: `string`):

Enter a direct competitor's TikTok handle (e.g. @competitor\_brand). The engine will automatically reverse-engineer their high-performing campaigns to find similar creators.

## `targetRegion` (type: `string`):

Select the primary geographic market cluster to guide the engine's automated localization strategies.

## `targetCountry` (type: `string`):

Enter one or more 2-letter country codes separated by commas (e.g., 'ke' or 'ke,tz,ug').

## `influencerTier` (type: `string`):

Choose the target audience scale baseline for discovered creators.

## `minMatchScore` (type: `integer`):

The minimum AI alignment percentage score required to include a creator in your finalized export pipeline.

## `openRouterApiKey` (type: `string`):

Provide your secure OpenRouter API key to run background LLM evaluations.

## Actor input object example

```json
{
  "brandDescription": "Premium automotive dealership specializing in Japanese imports, luxury SUV models, and hybrid vehicles based in East Africa.",
  "targetRegion": "east_africa",
  "targetCountry": "ke",
  "influencerTier": "micro",
  "minMatchScore": 70
}
```

# 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 = {
    "brandDescription": "Premium automotive dealership specializing in Japanese imports, luxury SUV models, and hybrid vehicles based in East Africa.",
    "competitorHandle": "",
    "targetCountry": "ke",
    "openRouterApiKey": ""
};

// Run the Actor and wait for it to finish
const run = await client.actor("kagayaki/tiktok-brand-influencer-matchmaker").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 = {
    "brandDescription": "Premium automotive dealership specializing in Japanese imports, luxury SUV models, and hybrid vehicles based in East Africa.",
    "competitorHandle": "",
    "targetCountry": "ke",
    "openRouterApiKey": "",
}

# Run the Actor and wait for it to finish
run = client.actor("kagayaki/tiktok-brand-influencer-matchmaker").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 '{
  "brandDescription": "Premium automotive dealership specializing in Japanese imports, luxury SUV models, and hybrid vehicles based in East Africa.",
  "competitorHandle": "",
  "targetCountry": "ke",
  "openRouterApiKey": ""
}' |
apify call kagayaki/tiktok-brand-influencer-matchmaker --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "command": "npx",
            "args": [
                "mcp-remote",
                "https://mcp.apify.com/?tools=kagayaki/tiktok-brand-influencer-matchmaker",
                "--header",
                "Authorization: Bearer <YOUR_API_TOKEN>"
            ]
        }
    }
}

```

## OpenAPI specification

```json
{
    "openapi": "3.0.1",
    "info": {
        "title": "Kagayaki Prism: AI TikTok Brand-Creator Matchmaker",
        "description": "Kagayaki Prism is an elite AI data engine that matches your brand to the perfect TikTok influencers. It automatically finds high-performing creators in your niche, checks if their audience fits your brand, and writes custom outreach messages so you can launch campaigns with zero manual scrolling. 🚀",
        "version": "1.0",
        "x-build-id": "pyLZeC8AIGAMIh7et"
    },
    "servers": [
        {
            "url": "https://api.apify.com/v2"
        }
    ],
    "paths": {
        "/acts/kagayaki~tiktok-brand-influencer-matchmaker/run-sync-get-dataset-items": {
            "post": {
                "operationId": "run-sync-get-dataset-items-kagayaki-tiktok-brand-influencer-matchmaker",
                "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": {
                                "$ref": "#/components/schemas/inputSchema"
                            }
                        }
                    }
                },
                "parameters": [
                    {
                        "name": "token",
                        "in": "query",
                        "required": true,
                        "schema": {
                            "type": "string"
                        },
                        "description": "Enter your Apify token here"
                    }
                ],
                "responses": {
                    "200": {
                        "description": "OK"
                    }
                }
            }
        },
        "/acts/kagayaki~tiktok-brand-influencer-matchmaker/runs": {
            "post": {
                "operationId": "runs-sync-kagayaki-tiktok-brand-influencer-matchmaker",
                "x-openai-isConsequential": false,
                "summary": "Executes an Actor and returns information about the initiated run in response.",
                "tags": [
                    "Run Actor"
                ],
                "requestBody": {
                    "required": true,
                    "content": {
                        "application/json": {
                            "schema": {
                                "$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": {
                                    "$ref": "#/components/schemas/runsResponseSchema"
                                }
                            }
                        }
                    }
                }
            }
        },
        "/acts/kagayaki~tiktok-brand-influencer-matchmaker/run-sync": {
            "post": {
                "operationId": "run-sync-kagayaki-tiktok-brand-influencer-matchmaker",
                "x-openai-isConsequential": false,
                "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
                "tags": [
                    "Run Actor"
                ],
                "requestBody": {
                    "required": true,
                    "content": {
                        "application/json": {
                            "schema": {
                                "$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": [
                    "brandDescription",
                    "openRouterApiKey"
                ],
                "properties": {
                    "brandDescription": {
                        "title": "Brand Profile Description",
                        "type": "string",
                        "description": "Enter a detailed summary of your brand identity, product lines, value proposition, and target audience context."
                    },
                    "competitorHandle": {
                        "title": "Competitor TikTok Handle (Optional)",
                        "type": "string",
                        "description": "Enter a direct competitor's TikTok handle (e.g. @competitor_brand). The engine will automatically reverse-engineer their high-performing campaigns to find similar creators."
                    },
                    "targetRegion": {
                        "title": "Target Global Region",
                        "enum": [
                            "east_africa",
                            "west_africa",
                            "southern_africa",
                            "north_america",
                            "south_america",
                            "western_europe",
                            "eastern_europe",
                            "middle_east",
                            "east_asia",
                            "southeast_asia",
                            "oceania"
                        ],
                        "type": "string",
                        "description": "Select the primary geographic market cluster to guide the engine's automated localization strategies.",
                        "default": "east_africa"
                    },
                    "targetCountry": {
                        "title": "Specific Country Code(s)",
                        "pattern": "^[a-zA-Z]{2}(\\s*,\\s*[a-zA-Z]{2})*$",
                        "type": "string",
                        "description": "Enter one or more 2-letter country codes separated by commas (e.g., 'ke' or 'ke,tz,ug')."
                    },
                    "influencerTier": {
                        "title": "Influencer Audience Tier",
                        "enum": [
                            "nano",
                            "micro",
                            "macro",
                            "mega"
                        ],
                        "type": "string",
                        "description": "Choose the target audience scale baseline for discovered creators.",
                        "default": "micro"
                    },
                    "minMatchScore": {
                        "title": "Minimum Match Score Threshold",
                        "minimum": 0,
                        "maximum": 100,
                        "type": "integer",
                        "description": "The minimum AI alignment percentage score required to include a creator in your finalized export pipeline.",
                        "default": 70
                    },
                    "openRouterApiKey": {
                        "title": "OpenRouter API Key",
                        "type": "string",
                        "description": "Provide your secure OpenRouter API key to run background LLM evaluations."
                    }
                }
            },
            "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
                                    }
                                }
                            }
                        }
                    }
                }
            }
        }
    }
}
```
