New playbook: when your own AI model pays. Read
Uber (mobility and delivery) reported this on 27 Aug 2026 in company self-report (source). It belongs to the models and routing layer.
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.
Cost per session down 52% from its June 2026 peak, with the model held constant. Uber's uReview benchmark showed switching models improved F1 while sharply cutting cost per review.
The number covers internal developer AI usage at Uber; model held constant.
“…cost per session is down 52% from its June peak,” Uber said.
One gateway picks the AI model for each task and records what it costs.
Read the guide to models and routing.
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).
30%+
lower average task cost from smart routing, internal coding work
An internal control layer between developers and models: moving defaults to newer cheaper models in one place, task-aware routing across models and harnesses, per-developer spend reports, and progressive friction (warning, approval, downshift to cheaper model) in place of hard caps (source).