New playbook: when your own AI model pays. Read
Replit (software, ~300 employees) reported this on 26 Aug 2026 in company self-report (source). It belongs to the models and routing layer.
Intelligent Model Routing that matches each step of an agent task to the best-suited model, balancing quality, speed and cost; users start in Free Mode and are notified when work escalates.
Same output quality at 65% lower cost than the previous version of Max Mode, in Replit's testing.
The number covers replit's internal testing of its coding agent.
“…the same output quality at 65% lower cost,” Replit said.
One gateway picks the AI model for each task and records what it costs.
Up to 90%
lower AI cost, AT&T says
An internal AI Gateway that, turn by turn, weighs speed, cost and expected quality and routes each prompt to the most cost-effective model, switching models mid-session, plus a library of post-trained open telco models (OTel 2.0) that run on-prem or in cloud (source).
<8%
of closed-model cost per transaction
A blended model portfolio (in-house compact models, open-source models post-trained on Pinterest data in its own secure cloud, closed models only in 'very limited cases') behind a centralized routing layer that sends routine work to lighter models; being extended to internal engineering and sales tools in H2 2026 (source).
52%
lower cost per agent session since the June peak
A cost equation and weekly metric stack for its agentic 'software factory' (70%+ of PRs agent-attributed), with benchmark-driven Pareto model selection (incl. open-weight models), cheaper default subagent models, Medium reasoning effort default, 400K-token compaction cap and prompt-cache strategy (source).