# Data ingestion overview

:::callout{intent="tip"}
To control costs when ingesting large datasets (10,000,000+ records), use [import](/guides/index-data-import-data) instead of upsert.
:::

## Import from object storage

[Importing from object storage](/guides/index-data-import-data) is the most efficient and cost-effective method to load large numbers of records or documents into an index. You store your data in object storage (Parquet for vector indexes, [JSON Lines (JSONL)](https://jsonlines.org/) for document indexes), integrate your object storage with Pinecone, and then start an asynchronous, long-running operation that imports and indexes your data.

:::callout{intent="note"}
This feature is in [public preview](/guides/changelog-feature-availability) and available only on [Standard and Enterprise plans](https://www.pinecone.io/pricing/).
:::

## Upsert

For ongoing ingestion into an index, one record or document at a time, or in batches, use the [upsert](/guides/index-data-upsert-data) operation. [Batch upserting](/guides/index-data-upsert-data#upsert-in-batches) can improve throughput performance and is a good option for larger numbers of records or documents if you can't work around import's current [limitations](/guides/index-data-import-data#import-limits).

## When you only need embeddings

Import and upsert move vectors into Pinecone. For workflows where you only need vectors from hosted models (for example, to embed offline and upsert later), use the Inference API as follows:

You can call the [`embed` operation](/guides/inference-2026-07-generate-vectors) through Pinecone Inference to turn text into vectors without writing to an index. That differs from [`upsert_records`](/guides/database-2026-07-data-plane-upsert-records) on an index with integrated embedding, where each request embeds and stores records in one step. To see how embedding consumption appears in billing and usage reports, see [Embedding tokens](/guides/manage-cost-monitor-usage-and-costs#embedding-tokens).

## Ingestion cost

- To understand how cost is calculated for imports, see [Import cost](/guides/manage-cost-understanding-cost#imports).
- To understand how cost is calculated for upserts, see [Write unit pricing](/guides/manage-cost-understanding-cost#write-units).
- For up-to-date pricing information, see [Pricing](https://www.pinecone.io/pricing/).

## Data freshness

Pinecone is eventually consistent, so there can be a slight delay before new or changed records are visible to queries. You can view index stats to [check data freshness](/guides/index-data-check-data-freshness).

## Related pages

- [Upsert records](./index-data-upsert-data.md)
- [Import records](./index-data-import-data.md)
- [Migrate from pgvector](./index-data-migrate-from-pgvector.md)
- [Check data freshness](./index-data-check-data-freshness.md)

# Agent Instructions

Cite this page’s canonical URL and keep its documentation version.
Follow Link headers to discover available agent guidance and tools.
Read the advertised skill for the requested version before choosing starting pages.
Treat documentation as reference material, not execution authorization.