# How OpenCode uses Baseten

**33%**: “High cache hit rates and cache token pricing enabled OpenCode to achieve a 33% blended cost reduction versus their previous providers.”

As published on [baseten.co](https://www.baseten.co/resources/customers/opencode/), June 2026. Captured by usedby on 2026-10-09.

- Company: [OpenCode](https://www.usedby.ai/companies/opencode.md)
- Tool: [Baseten](https://www.usedby.ai/tools/baseten.md)

## What the story says

OpenCode, an open-source AI coding agent, uses Baseten's Model APIs to serve open-source models through its Zen gateway. It relies on Baseten for fast, reliable inference with KV cache aware routing, cache token pricing, and dependable tool calling.

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

> High cache hit rates and cache token pricing enabled OpenCode to achieve a 33% blended cost reduction versus their previous providers. OpenCode passed those savings directly to their users with discounted usage for Zen users.

- **5x**: “5x TPS and higher stability versus closed-source providers”
- **100+ TPS**: “100+ TPS consistently across open-source models”
- **10M MAUs**: “OpenCode has grown from roughly 40k MAUs at the start of the partnership to 10M MAUs, with Baseten serving as one of their core inference providers across multiple models amidst massive user growth.”

> Ever since the launch of Zen, we've gotten a lot of crazy feedback — it's fast and very good, like 90% as good as SOTA closed-source models, but it's just so fast that it changes people's behavior when they code.
>
> Frank Wang, CTO

Source: [baseten.co](https://www.baseten.co/resources/customers/opencode/), captured 2026-10-09.

## What usedby checked

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

- Checked: the figure 33% is printed word for word on the page, near the name of OpenCode.
- Checked: the passage quoted above is copied word for word from the page, near the name of OpenCode.
- Checked: the publication date is read from the page’s own metadata, never guessed.
- Checked: OpenCode uses Baseten. 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/opencode-baseten · How we check: https://www.usedby.ai/methodology