# XERJ introduces Reader-1, a document-answering model priced at $0.01 per 1M input tokens

> Original title: This new model is a big deal:

- Source: Santiago
- Published: 2026-11-12T11:35:31.000Z
- Bad Influence: https://badinfluence.news/items/tpfdohlhirmpyqf1idq49947r
- Original: https://x.com/svpino/status/2120842924351164868

## Summary

XERJ introduces Reader-1, a neurosymbolic model trained to return the exact source passages that answer a question, with direct traceability to the document. Svpino says the model costs $0.01 per 1M input tokens, with free output. XERJ says Reader-1 is 20-90x faster and 10-1,000x cheaper than alternatives, and that every answer is a replayable program.

## Post

This new model is a big deal:

It was trained to return the exact passages from the source document that answer a question.

Think about applications that work with contracts, invoices, emails, or other documents. You always want to answer questions with direct traceability back to the source.

$0.01 per 1M input tokens with free output. Awesome price for processing documents at scale!

## Quoted post @d0znpp

> I've built a new AI model that is not allowed to generate text. Instead, it produces a verifiable program that answers your prompt using the original reference.
> 
> XERJ Reader-1 is a neurosymbolic model for working with data. It points to the exact words in your document, writes a small program over them, and exact code computes the answer:
> 
> • 20-90x faster
> • 10-1,000x cheaper (output tokens free)
> • every answer is a program you can replay
> 
> The shortest path to automating data work.

https://x.com/d0znpp/status/2120834698335109140