The use case: how Aviva Credito deploys TrueFoundry
Aviva, a Mexico-based lender, routes all its LLM traffic across Azure and Google Cloud through TrueFoundry's AI Gateway for centralized observability, cost tracking, model switching and fallbacks. It also uses TrueFoundry's deployment platform so AI/ML engineers can ship and update production services without Kubernetes specialists.
More reported results
Figures published in TrueFoundry’s case study. They are not independently measured by usedby.
10M+ production LLM requests routed through a single control plane
<1% effective failure rate, with granular breakdown by error type and provider
5B+ input tokens, 210M+ output tokens tracked centrally across Azure and GCP
In the customer’s words
TrueFoundry’s AI Gateway gave us a single place to manage how we use LLMs across Azure and GCP. We can detect cost and latency issues quickly, trace them to specific services, and switch models without touching application code.Other companies using TrueFoundry
Customers across industries, with public evidence.
Adopt AIConfirmed
Aviso AIConfirmed
EchoStarConfirmed
ExamRoom.AIConfirmed
FloQastConfirmed
Games24x7ConfirmedGo straight to the source
Based on TrueFoundry’s published case study. We check the public evidence; the results are reported by the vendor.
truefoundry.com- Source published
- Jan 27, 2026
- Last checked
- Nov 7, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: <20 minutesChecked
Printed word for word on the page, near the name of Aviva Credito.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Aviva Credito.
- The publication dateChecked
Read from the page’s own metadata, never guessed.
- Aviva Credito uses TrueFoundryChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
By centralizing all LLM traffic through TrueFoundry’s AI Gateway, Aviva gained end-to-end visibility and control across a rapidly scaling, multi-cloud AI stack.
