Skip to main content
usedby
Together AIusedbyDeep Cogito

How Deep Cogito uses Together AI

ConfirmedVendor case study · Checked Nov 10, 2026
View captured proof

The use case: how Deep Cogito deploys Together AI

Deep Cogito, an AI research lab, uses Together AI's GPU clusters to train its open-weight Cogito reasoning models and dedicated inference endpoints to serve them in production. Together also builds the serving pipeline for hybrid reasoning and produces quantized variants of the models after training.

More reported results

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

500ms

Together delivers under 500ms time to first token at over 1,000 requests per minute, with 99.9% uptime.

1 million

These releases drove significant adoption, contributing to over 1 million downloads across Hugging Face and Ollama.

In the customer’s words

Before Together, we were struggling with adapting to the compute environment for training large open models. Once we found Together, we were able to offload most of it to them and focus on model training and benchmarking, which is our core secret sauce.
Dhruv Malrana, Co-founder, Deep Cogito — Source

Together AI users in Artificial Intelligence

Companies in the same sector, with public evidence.

Arcee AIConfirmedCartesiaConfirmedDecagonConfirmedDippy AIConfirmedHedraConfirmedLegionEdgeConfirmed
See all Together AI customers

More stories

Go straight to the source

Based on Together AI’s published case study. We check the public evidence; the results are reported by the vendor.

together.ai
Last checked
Nov 10, 2026
together.aiCaptured Together AI case study about Deep CogitoOpen source capture
What the story claims, and what we checked

What we compared with the page.

  • The figure: <500msChecked

    The figure is on the page; its label is our wording.

  • The passage quoted aboveChecked

    Copied word for word from the page, near the name of Deep Cogito.

  • Deep Cogito uses Together AIChecked

    Confirmed line.

  • The result itselfNot checked

    We quote it; we did not measure it.

After each training run, Together’s team shipped FP8, FP4, and INT4 quantized variants of the Cogito models in under two weeks, without meaningful quality degradation.
From the page. together.ai