# Xiaomi: MiMo-V2.6-Flash

Provider: xiaomi  
Category: llm  
Model ID: `xiaomi/mimo-v2.6-flash`

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...

## Specs

- Context length: 1048576 tokens
- Max output: 131072 tokens
- Modalities: text, image, video, audio
- Released: 2026-09-21

## Pricing

- Input: $0.14 per million tokens
- Output: $0.28 per million tokens

## Providers

- **xiaomi** — ctx 1048576, input $0.14/M, output $0.28/M

## Verdict

MiMo-V2.6-Flash is Xiaomi's multimodal model with an exceptionally large 1M token context window and aggressive pricing at $0.14/$0.28 per Mtok — roughly half the cost of comparable multimodal options. It handles text, image, video, and audio in a single API call, making it practical for mixed-media workflows where cost matters more than bleeding-edge accuracy. Without public benchmarks, you're trading proven performance data for price and convenience. Best for teams running high-volume multimodal tasks on tight budgets who can tolerate some uncertainty around quality.

---
Last verified: 2026-10-19T02:30:34.239Z  
Canonical URL: https://switchy.build/directory/models/mimo-v2-6-flash