# How Wadhwani AI uses TrueFoundry

**~55%**: “Reduce the cloud cost incurred by ~55% with the same level of reliability and performance.”

As published on [truefoundry.com](https://www.truefoundry.com/case-studies/replacing-managed-ml-service-for-wadhwaniai). Captured by usedby on 2026-10-09.

- Company: [Wadhwani AI](https://www.usedby.ai/companies/wadhwani-ai.md)
- Tool: [TrueFoundry](https://www.usedby.ai/tools/truefoundry.md)
- Industry: [Non-profit & NGO](https://www.usedby.ai/companies/industry/non-profit-ngo.md)
- Teams: Data Scientists, Machine Learning Engineers

## What the story says

Wadhwani AI, a non-profit, runs its Vachan Samiksha oral reading fluency model, which needs GPUs for inference, on TrueFoundry deployed on its own Kubernetes infrastructure instead of its cloud provider's managed ML service. The team uses it for deployment, queue-based GPU autoscaling, scheduled scaling and spot instances to serve pilots in schools.

Summary written by usedby from the source page, in English. The figures are those of TrueFoundry and Wadhwani AI, not ours.

> Scale the application to handle 10X Requests per second compared to the managed ML Service. Reduce the cloud cost incurred by ~55% with the same level of reliability and performance.

- **10X**: “Scale the application to handle 10X Requests per second compared to the managed ML Service.”
- **~80%**: “Reduce the latency of requests by ~80% when the pods are scaling horizontally.”
- **78%**: “We realized that TrueFoundry could scale up 78% faster than managed ML service, which gave the user much faster responses.”
- **40%**: “The end-to-end time taken to respond to the query was 40% less with TrueFoundry.”

> For me the biggest differentiator working with TrueFoundry was the ease of usage and the quick response and support provided by the team. I was able to setup and migrate our entire code base in less than 1 day which was amazing. During the pilot and whenever we had any doubts or request the TrueFoundry team was available immediately to solve our doubts and support us. Besides these factors we are getting a massive cost reduction which is super helpful for the project.
>
> Jatin Agrawal, Machine Learning Scientist

Source: [truefoundry.com](https://www.truefoundry.com/case-studies/replacing-managed-ml-service-for-wadhwaniai), captured 2026-10-09.

## What usedby checked

We compared the story with its live page on 2026-10-09.

- Checked: the figure ~55% is printed word for word on the page, near the name of Wadhwani AI.
- Checked: the passage quoted above is copied word for word from the page, near the name of Wadhwani AI.
- Checked: Wadhwani AI uses TrueFoundry. Confirmed line. Latest check across sources: 2026-10-09.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/wadhwani-ai-truefoundry · How we check: https://www.usedby.ai/methodology