SOMA Claims 39.9% Cheaper Input via Context Compression on the Same Prompt
const_reborn · x · 2026-08-17
The SOMA team tested their SOMARIZER context compressor on a 2D HTML/CSS animation prompt (against ChatGPT 5.5 Pro): the original ran 8,680 tokens / 31,364 characters, an estimated $0.5729 input cost at $10/MTok.
After compression at a 0.60 ratio, it dropped to 5,221 tokens / 17,590 characters and $0.3447 — 43.9% fewer characters and 39.9% lower input cost. They claim compression removes not just noise but redundant and contradictory instructions, leaving a tighter spec for the model. Note: vendor-run benchmark, independently unverified.
More from Apps
- AI scans daily web actions to find double bookings, SEO issues, and mistakes — gabriel1 · 2026-08-18
- Deploying a Hermes agent on a dedicated phone to automate content tracking — Teknium · 2026-08-18
- OpenAI stops custom GPT creation for personal accounts, plans conversion to Skills — btibor91 · 2026-08-18
- PhoneNumber-OSINT: Tool to gather country and region info from phone numbers — tom_doerr · 2026-08-18
- WisprFlow Voice Input Achieves 85% Zero-Edit Rate — eurie_kim · 2026-08-18
- MUZIM: Local-first AI file agent for semantic search — FellMentKE · 2026-08-18