Embeddings, rerank and redaction

Vector embeddings in OpenAI's format, reranking in the format of Cohere and Jina, and redaction of personal data in the privacy filter's own format, each with its own model and billed on input tokens only. See the Embeddings, rerank and redaction guide.

📄️Create embeddings

Turns text into vectors, in the format of OpenAI's embeddings API (`client.embeddings.create` in the OpenAI SDKs). `qwen3-embedding-0.6b` (alias `qwen/qwen3-embedding-0.6b`) returns one vector of 1024 numbers per input, for at most 512 inputs per request.

📄️Rerank documents

Scores how relevant each document is to a query, in the format of the rerank APIs of Cohere and Jina, with `qwen3-reranker-0.6b` (alias `qwen/qwen3-reranker-0.6b`). At most 1000 documents per request, a query of at most 4096 characters and about 300,000 tokens (the estimate below); the model reads each document with the query up to 8,192 tokens.

📄️Redact personal data

Finds personal data in text (names, email addresses, phone numbers, postal addresses, account numbers and more) and masks it, in the privacy filter's own format, with `privacy-filter` (alias `openai/privacy-filter`). `model` is optional. At most 256 inputs and a body of 192 KiB (196,608 bytes) per request. The text sent is processed in memory only: it is never written to disk or logs and never used for training.