The use case: how Writer deploys Baseten
Writer serves its custom 70-billion-parameter domain-specific Palmyra LLMs for healthcare and finance on Baseten's inference platform. Baseten's model performance engineers built TensorRT-LLM engines for each model to improve serving speed and cost.
More reported results
Figures published in Baseten’s case study. They are not independently measured by usedby.
23% lower time to first token
35% lower cost per million tokens
In the customer’s words
Inference for custom-built LLMs could be a major headache. Thanks to Baseten, we’re getting cost-effective high-performance model serving without any extra burden on our internal engineering teams. Instead, we get to focus our expertise on creating the best possible domain-specific LLMs for our customers.Other AI tools used by Writer
Other public relationships recorded on usedby.
Explore Writer’s AI stackBaseten users in Marketing Tech
Companies in the same sector, with public evidence.
See all Baseten customersGo straight to the source
Based on Baseten’s published case study. We check the public evidence; the results are reported by the vendor.
baseten.co- Last checked
- Nov 11, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 60%Checked
Printed word for word on the page, near the name of Writer.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Writer.
- The numbers in our summaryChecked
Each one is printed on the page.
- Writer uses BasetenChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
With TensorRT-LLM engines deployed on Baseten, Writer surpassed its performance requirements ahead of launching the new models.









