New playbook: when your own AI model pays. Read
Descript (video software, 125+ employees) reported this on 15 Sep 2026 in vendor case with a named customer (source). It belongs to the models and routing layer.
Moved its Underlord editing agent from three direct provider integrations to OpenRouter as the production inference layer, with per-model provider priority, data-retention-policy filtering and 3-4 automated fallbacks per model.
1 to 13 models in production (Aug 2026); time to evaluate a new model cut from a week or more to 1-2 hours.
The number covers model operations speed; cost is not reported.
“…we could add 10 more for basically very little work,” Descript 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).