AI for Every Row: Bulk LLM to Classify & Summarize Datasets
Pricing
from $1.40 / 1,000 row processeds
Run an LLM (GPT, Gemini and more) on every row of a dataset or JSON list, for AI enrichment and sentiment analysis: classify, tag, score, summarize or extract fields, chained after any scraper with datasetId. Answers validated against your schema or labels; $2 per 1,000 valid rows plus model tokens.
Versions follow MAJOR.MINOR.PATCH (src/version.py); Apify shows MAJOR.MINOR from .actor/actor.json.
Every run logs its version and records it in the RUN_STATS key-value record.
RUN_STATS keeps the reason as before.humble-echidna-<name>, and if that is
refused too it runs without memory for that run. Users' existing memory is untouched: the usual name is tried first.First release: an LLM on every row of a dataset or an inline JSON list, one call per row.
rows (inline JSON; a plain string is {"text": ...}) or any Apify dataset (datasetId, read with the
run's own token, only the top-level fields it needs; up to 20,000 rows per run).textFields are sent to the model, each as "field: value"; keepFields are copied to the output (kept)
for joins, with sourceIndex.labels (data.label, a strict enum), plain-English fields, or a JSON schema
(precedence schema > fields > labels). Every answer validated; invalid, empty and failed rows are rows with the
reason, never charged.mms_llm client, also used by
ai-extract 1.0.5): retries on 429/5xx, strict mode retried as a hint when a provider refuses it, a refusing proxy
stops the run.onlyNew: skips rows whose text the same setup (schema, instructions, model, text fields) already answered
validly; text hashes in the user's own ai-rows-seen store, remembered only after the row is in the dataset.row-processed), after the push; the max cost per run is honoured before a row is sent.
maxRows and maxTokensPerRow cap the token spend. A run near its timeout stops starting rows, saves the
memory and RUN_STATS, and ends cleanly.