# How MiniMax uses Zilliz

**3-5x**: “processing speed improved by 2x while costs dropped by 3-5x”

As published on [zilliz.com](https://zilliz.com/customers/minimax). Captured by usedby on 2026-10-17.

- Company: [MiniMax](https://www.usedby.ai/companies/minimax.md)
- Tool: [Zilliz](https://www.usedby.ai/tools/zilliz.md)
- Industry: [Artificial Intelligence](https://www.usedby.ai/companies/industry/artificial-intelligence.md)

## What the story says

MiniMax uses Zilliz Cloud as a vector database to power real-time content recommendations for its Talkie consumer app, replacing a Redis-based setup. It also uses a MinHash + LSH engine within Zilliz Cloud to deduplicate large-scale LLM training data.

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

> Compared to their previous MapReduce systems, processing speed improved by 2x while costs dropped by 3-5x, making billion-document deduplication economically viable for routine operations.

- **5,000**: “even during traffic surges above 5,000 queries per second”
- **30 milliseconds**: “under 30 milliseconds”

## What usedby checked

We compared the story with its live page on 2026-10-17.

- Checked: the figure 3-5x is printed word for word on the page, near the name of MiniMax.
- Checked: the passage quoted above is copied word for word from the page, near the name of MiniMax.
- Checked: MiniMax uses Zilliz. Confirmed line. Latest check across sources: 2026-10-17.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/minimax-zilliz · How we check: https://www.usedby.ai/methodology