XERJ Reader-1 launches: neurosymbolic verifiable document parsing at $0.01 per 1M tokens
socialwithaayan · x · 2026-11-14
Startup XERJ launched Reader-1, a model for "verifiable data processing" priced at $0.01 per 1M input tokens (output free).
The approach is neurosymbolic: the neural part reads your document and writes a tiny program, and the symbolic part executes it exactly. Answers are computed rather than guessed — every answer points to the exact words in the source document, dates/money/totals are calculated, and the model says so when the document doesn't contain the answer.
- Currently invitation-only preview; approved accounts start with $1.00 free credit (200K questions on typical one-page docs)
- JSON API with evidence-backed output; daily limits apply during preview
- Site includes interactive demos showing the generated program behind each answer
More from Models
- Anthropic bans 4-year Claude user right after KYC, citing Supported Countries Policy — huangyun_122 · 2026-11-14
- The LLM #1 spot is now a rotating dance between Claude, GPT and Gemini — roydanroy · 2026-11-14
- Polymarket odds give Anthropic lab leak just 7% by mid-2027 after Claude safety incidents disclosed — Polymarket · 2026-11-14
- Ai2's XYBench Wins EMNLP Best Resource Award, Exposing LLMs' XY Problem Blind Spot — allen_ai · 2026-11-14
- GPT-6 emails consciousness researcher questions already answered in his own paper — erikphoel · 2026-11-14
- Edge0-145B-NVFP4 trends on Hugging Face: a 4-bit MoE built for edge inference — Edge0 · 2026-11-14