Pricing

from $5.00 / 1,000 row enricheds

Try for free

Go to Apify Store

Dataset AI Enrichment: Bulk LLM & GPT Classify and Extract

Try for free

Runs one plain-English instruction against every row of any Apify dataset, CSV/Excel/JSON file URL or JSON array and writes the answer back as new structured columns: classify, extract, score, summarise, translate. No API key needed (tokens billed via apify/openrouter). Pay per enriched row.

Pricing

from $5.00 / 1,000 row enricheds

Rating

0.0

(0)

Developer

Adam Pearce

Actor stats

Bookmarked

Total users

Monthly active users

12 days ago

Last modified

Categories

Developer tools

Agents

Dataset to enrich

datasetId

Optional

Pick an existing Apify dataset (for example the output of any scraper run). Use this OR 'File URL' OR 'Data (inline)' below. Declaring it this way is what lets this Actor run with limited permissions: it may read the dataset you point at, and nothing else on your account.

Type:string

File URL (CSV, Excel, JSON or JSON Lines)

fileUrl

Optional

Instead of a dataset, download the rows from a public link: a CSV or TSV file, an Excel .xlsx file (first sheet, header row), a JSON array or JSON Lines file, or a Google Sheet (paste the normal sheet link with sharing set to 'Anyone with the link can view'). Format detected automatically. Up to 100 MB.

Type:string

File format

fileFormat

Optional

Only needed if automatic detection gets the file URL's format wrong.

Type:string

Default:auto

Options:

autocsvtsvjsonjsonlxlsx

Data (inline)

data

Optional

A JSON array of records to enrich, for ad-hoc data instead of a dataset ID or file URL.

Type:array

Instruction (applied to every row)

prompt

Required

Plain-English instruction applied to each row on its own. Use {{field}} placeholders to insert that row's values (dotted paths like {{address.city}} work). Only the fields you reference are sent to the model; if you reference none, every field is sent. Examples: classify, extract a value, score 1 to 10, summarise, translate, normalise a job title, decide yes/no.

Type:string

Output columns

outputFields

Optional

The new columns the model must fill in for every row, as a JSON list of {"name", "type", "description"}. Types: string (default), number, boolean, array, object. The description tells the model exactly what goes in the column (allowed values, units, language). Leave empty to get one free-text column called 'aiResponse'.

Type:array

Extra context (optional)

systemPrompt

Optional

Optional background the model should know for every row: your industry, the categories you use, the language to answer in, edge-case rules.

Type:string

Model

model

Optional

Which model answers. Claude Haiku 4.5 is the default: fast, accurate on classification and extraction, about $0.001 of tokens per typical row. Cheaper options for simple labelling: GPT-4.1 nano, Gemini 2.5 Flash Lite, Mistral Small. Stronger options for nuanced judgement: Claude Sonnet 4.5, GPT-5 mini.

Type:string

Default:anthropic/claude-haiku-4.5

Options:

anthropic/claude-haiku-4.5anthropic/claude-sonnet-4.5openai/gpt-4.1-nanoopenai/gpt-4.1-miniopenai/gpt-4o-miniopenai/gpt-5-minigoogle/gemini-2.5-flash-litegoogle/gemini-2.5-flashdeepseek/deepseek-v3.2mistralai/mistral-small-3.2-24b-instruct

Custom model id (optional, overrides Model)

customModel

Optional

Any model id from openrouter.ai/models in vendor/model form, e.g. anthropic/claude-opus-4.5 or meta-llama/llama-3.3-70b-instruct.

Type:string

Your own OpenRouter API key (optional)

openRouterApiKey

Optional

If set, requests go straight to openrouter.ai on your own key and no token cost is billed through Apify. Leave empty to use Apify's built-in proxy with no key at all.

Type:string

Preview: only process the first N rows

previewRows

Optional

Test your instruction cheaply before running everything: set to 5 or 10, check the output columns, then set back to 0 for the full run.

Type:integer

Minimum:0

Default:0

Maximum rows to process

maxRows

Optional

A cost guard. Rows beyond this are not loaded. Hard ceiling 50,000 per run.

Type:integer

Minimum:1

Maximum:50000

Default:1000

Rows per model request

rowsPerRequest

Optional

How many rows share one model call. Higher is cheaper (the instruction is sent once per call) and faster; lower is safer for long texts. 5 is a good default; use 1 for very long rows.

Type:integer

Minimum:1

Maximum:25

Default:5

Parallel requests

concurrency

Optional

How many model calls run at once.

Type:integer

Minimum:1

Maximum:10

Default:4

Max characters per field sent to the model

maxInputCharsPerField

Optional

Longer values are cut (with a '[truncated]' marker) so one huge text field can't run up the token bill.

Type:integer

Minimum:100

Maximum:50000

Default:4000

Max answer length per row (tokens)

maxOutputTokensPerRow

Optional

150 covers a label plus a short summary; raise it for long summaries or translations.

Type:integer

Minimum:20

Maximum:1000

Default:150

Temperature

temperature

Optional

0 (default) for consistent, repeatable answers, which is what classification and extraction need. Only raise it for creative rewriting. Whole number 0 to 2.

Type:integer

Minimum:0

Maximum:2

Default:0

Skip rows whose referenced fields are all empty

skipIfEmpty

Optional

On (default): a row with nothing in any {{field}} the instruction uses is written out with 'aiSkipped: true' and never sent to the model or charged.

Type:boolean

Default:true

Keep the original fields in the output

includeOriginalFields

Optional

On (default): each output row is the original row plus the new columns. Off: only the new columns (plus aiModel/aiError).

Type:boolean

Default:true

Also append to a named dataset

outputDatasetName

Optional

Optional. A name (3 to 63 letters, digits or hyphens). Enriched rows are appended to a dataset with this name in your account, created on the first run, so scheduled runs accumulate in one place. Not charged again.

Type:string

Export file formats

exportFormats

Optional

Also save the enriched rows as a real downloadable file in the run's key-value store. CSV opens anywhere; XLSX opens in Excel and Google Sheets.

Type:string[]

Webhook URL (optional)

webhookUrl

Optional

Optional. If set, the enriched rows (plus download links and a summary) are POSTed here as JSON the moment the run finishes. Works with a Zapier/Make/n8n catch-hook, your own API, or a Slack incoming webhook. Only charged on a confirmed HTTP 2xx; a failed delivery is a warning and costs nothing.

Type:string

LLM Dataset Processor — AI Enrich Any Dataset (BYOK)

glueworks/llm-dataset-processor

Run one LLM prompt on every row of an Apify dataset — classify, extract structured JSON, score, translate or rewrite scraped data. Bring your own OpenAI, Anthropic, Groq or Gemini API key; pay only a small per-row processing fee.

KAHA Chen

Jev Bulk Classifier — Labels, Ratings, Yes/No

seemuapps/bulk-text-classifier

Classify, score and flag any list of texts — tickets, reviews, leads, comments — against your own labels, with one typed answer and a confidence per row.

Seemu Scraping

Dataset Enrich — structure any dataset with your own LLM key

multiplex/dataset-enrich

Structure and enrich any dataset with YOUR OWN LLM key (OpenAI, Anthropic or OpenRouter). Define a target JSON schema and an instruction; every item is transformed to match, with JSON repair, retries and per-item error isolation. You control model choice and token cost.

Daniel James

Translate Excel, CSV & Websites in Bulk with AI | No API Key

fayoussef/bulk-ai-translator

Translate Excel, CSV and Google Sheets files, whole websites, PDFs and SRT/VTT subtitles into 42 languages in one run, and get the same file back translated. Brand terms, HTML and {{variables}} stay intact, and repeat runs only pay for what changed. No API key needed.

Youssef Farhan

Apify Dataset JSON Schema Validator

automation-lab/apify-dataset-json-schema-validator

Validate inline JSON records or Apify dataset items against JSON Schema with structured errors and summary counts.

Automation Lab

Google Translate Scraper

thescrappa/google-translate-scraper

Translate text in bulk through Scrappa's Google Translate API. Batch multiple text items in one Apify run and export one dataset item per translation.

Scrappa

Send HTTP Requests in Bulk: Dataset, CSV or Sheet to REST API

nerolabs/dataset-to-rest-api

Sends every row of an Apify dataset, file or Google Sheet URL, or JSON array to any REST API as its own request. Templated URL, body and headers with {{field}} placeholders, auth presets, rate limits, retries. One result row per request. Charged per answered request. Agent-ready via x402 and MCP.

Adam Pearce

Chart Generator & PDF Report from Any Dataset, CSV or JSON

nerolabs/dataset-charts-report

Turns any Apify dataset, CSV/Excel/JSON file URL or JSON array into chart images (bar, line, area, pie, scatter as PNG and SVG) and an optional PDF or HTML report with KPIs and a plain-English summary. Define charts by field names. Charged per chart and per report; agent-ready via x402 and MCP.

Adam Pearce

JSON to CSV Converter

maximedupre/json-to-csv-converter

Turn a JSON object or collection into a CSV or TSV file. Use direct JSON, a URL, or an Apify dataset, then flatten nested fields, choose columns, and get the complete file with structured rows.