# How Arcee AI uses Together AI

**95%**: “Time to First Token (TTFT): Improved by up to 95%”

As published on [together.ai](https://www.together.ai/customers/arcee-ai). Captured by usedby on 2026-10-09.

- Company: [Arcee AI](https://www.usedby.ai/companies/arcee-ai.md)
- Tool: [Together AI](https://www.usedby.ai/tools/together-ai.md)
- Industry: [Artificial Intelligence](https://www.usedby.ai/companies/industry/artificial-intelligence.md)

## What the story says

Arcee AI moved the inference for its specialized small language models from AWS-managed Kubernetes (EKS) to Together Dedicated Endpoints, a fully managed GPU deployment. The models power its Arcee Conductor routing and Arcee Orchestra workflow products.

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

> Time to First Token (TTFT): Improved by up to 95%, reducing latency of some models from 485ms on AWS to just 29ms on Together Dedicated Endpoints, exceeding expectations.

- **41+**: “Throughput (QPS): Achieved 41+ queries per second at 32 concurrent requests, surpassing Arcee AI's requirements.”

> The migration was a very simple process. We put our models in a private Hugging Face repository, the Together AI team pulled them down and handed us the API, and we just plugged that into our app. That’s what we wanted–a fully managed experience. Everything has been great: full availability, no downtime.
>
> Mark McQuade, CEO

Source: [together.ai](https://www.together.ai/customers/arcee-ai), captured 2026-10-09.

## What usedby checked

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

- Checked: the figure 95% is printed word for word on the page, near the name of Arcee AI.
- Checked: the passage quoted above is copied word for word from the page, near the name of Arcee AI.
- Checked: Arcee AI uses Together AI. 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/arcee-ai-together-ai · How we check: https://www.usedby.ai/methodology