LegalOn halves Codex costs while maintaining development speed
- ID
- 33452
- Status
- summarized
- Published
- 08 Oct 2026, 8:00 PM
- Fetched
- 09 Oct 2026, 7:40 AM
- Provider
- OpenAI News
- Category
- ai-labs
- Original URL
- https://openai.com/index/legalon-halves-codex-costs
- Source URL
- https://openai.com/news/rss.xml
Summary
- Score
- 5.0
- Created
- 09 Oct 2026, 7:40 AM
- Tags
- Audience
- developersvibe_codersai_agent_usersai_ml_learnerssaas_founders
What happened
OpenAI published a customer story on LegalOn Technologies, which cut estimated daily Codex costs by 65% and reduced costs 20% in mature business areas while keeping development speed. The company had started with unlimited access to GPT-5.5 in Fast mode, then built model-selection guidelines through an internal AI-powered Development CoE, routing tasks across GPT-6 (Astra, Luna) and GPT-6.1 Sol by complexity and development stage, plus administrator-set monthly usage limits per department and individual.
Why it matters
The concrete pattern worth copying is not 'use AI' but tiered routing plus hard budget caps: start on a lightweight model and escalate only as task complexity rises, with per-department and per-person monthly limits that a CoE monitors and adjusts. If your team currently gives everyone unmetered access to a top-tier coding model, this is a published example of a 65% daily-cost cut that reportedly did not slow delivery, which you can use as a benchmark when arguing for or against admin-level spend controls in your own tooling.
Discussion angle
What model-routing rules would you actually write down for your team, and would per-engineer monthly caps be acceptable to developers you work with, or would they just push usage to personal accounts?