Skip to main content
usedby
BasetenusedbyParallel Web Systems

How Parallel Web Systems uses Baseten

ConfirmedVendor case study · Checked Nov 11, 2026
View captured proof

The use case: how Parallel Web Systems deploys Baseten

Parallel runs the multi-turn agentic pipelines behind its Web Tool APIs on Baseten, starting with pay-per-token Model APIs and moving to dedicated deployments of an open-source model. It also uses Baseten to fine-tune smaller models, deploy them, and shadow-test them against production traffic.

More reported results

Figures published in Baseten’s case study. They are not independently measured by usedby.

50%

Baseten’s proprietary runtime cut latency by 50% and increased throughput by 3x through KV cache-aware routing and speculative decoding.

~100x

Within a few months of their initial deployment, Parallel scaled traffic with Baseten ~100x.

2x

2x latency improvement with Baseten speculative decoding and KV cache-aware routing

In the customer’s words

Our workloads can be very spiky. We need to be able to manage the peaks, but we also don't want to pay for the valleys. Pay-per-token with Model APIs enabled us to easily make the transition to open-source until our scale merited dedicated deployments optimized for throughput and flexible autoscaling.
Matt Lee, Engineering Lead, Parallel Web Systems — Source

Other AI tools used by Parallel Web Systems

Other public relationships recorded on usedby.

HexObserved
Explore Parallel Web Systems’s AI stack

Baseten users in Artificial Intelligence

Companies in the same sector, with public evidence.

EliseAIConfirmedGammaConfirmedHebbiaConfirmedOxen AIConfirmedPoolsideConfirmedRimeConfirmed
See all Baseten customers

More stories

Go 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
baseten.coCaptured Baseten case study about Parallel Web SystemsOpen source capture
What the story claims, and what we checked

What we compared with the page.

  • The figure: 3xChecked

    Printed word for word on the page, near the name of Parallel Web Systems.

  • The passage quoted aboveChecked

    Copied word for word from the page, near the name of Parallel Web Systems.

  • Parallel Web Systems uses BasetenChecked

    Confirmed line.

  • The result itselfNot checked

    We quote it; we did not measure it.

Baseten’s throughput and latency optimizations delivered 3x savings versus the equivalent closed-source model. Eliminating redundant processing made it economically viable to run the kind of long, multi-turn agent workflows that deliver meaningfully better results than a single-shot query.
From the page. baseten.co