The Washington Post runs Ask The Post AI on independent inference with 1.79B tokens a month

togethercompute · x · 2026-07-25

The Washington Post’s AI search product runs on independent model inference

The Washington Post says its Ask The Post AI product, launched in November 2024, uses Together AI’s inference platform to answer readers’ questions from the paper’s deeply sourced journalism.

Why it switched

The Post wanted independent model inference instead of being locked into proprietary APIs.
It needed enterprise-grade serving for thousands of daily queries with sub-10-second latency.
Self-hosting was seen as too operationally heavy, while hyperscalers and proprietary providers left too little control over cost and model choice.

What the deployment looks like

Dedicated endpoints for custom GPU infrastructure
Open-model hosting for Llama and Mistral
Hybrid deployment with both dedicated and serverless inference
Direct engineering support from Together AI on configuration and optimization

Reported results

1.79 billion input tokens per month
2-second consistent response times
Fixed monthly pricing instead of variable per-token costs
Better user engagement through answer-expansion and source-click behavior

Original post →

The Washington Post runs Ask The Post AI on independent inference with 1.79B tokens a month

More from Companies & People