# MiMo-V2.6 Flash

Model tracker · checked 2026-10-27 · https://dbggr.dev/models/mimo-v2-6-flash/

Open-weight 309B MoE model (15B active) for agentic coding and tool use; multimodal input

MiMo-V2.6 Flash is a fast open-weight model from Xiaomi, released 21 September 2026. At DeepInfra it costs $0.14 per million input tokens and $0.28 per million output tokens, with a 1M-token context window. All 2 providers that serve it charge the same.

- Made by: Xiaomi (MiMo)
- Released: 2026-09-21
- Status: Generally available
- Tier: Fast
- Weights: Open
- Memory to run: About 208 GB (MXFP4)
- Context window: 1,048,576 tokens
- Input: text, image, video, audio
- API id: XiaomiMiMo/MiMo-V2.6-Flash
- Docs: https://deepinfra.com/XiaomiMiMo/MiMo-V2.6-Flash

## MiMo-V2.6 Flash price at 2 providers

US dollars per million tokens. Blended is 3 input tokens for every output token, one number to compare on. The cheapest blended price is highlighted.

| Provider | Input | Output | Cached input | Blended | Batch | Checked |
|---|---|---|---|---|---|---|
| DeepInfra | $0.14 | $0.28 | $0.003 | $0.175 | – | [2026-10-27](https://deepinfra.com/pricing) |
| Novita AI | $0.14 | $0.28 | $0.003 | $0.175 | – | [2026-10-27](https://novita.ai/pricing) |

- DeepInfra: DeepInfra currently shows 35% off, with no end date: $0.091 in, $0.182 out, $0.0018 cached. Served in FP8.
- Novita AI: Served in FP8.

## Can you run MiMo-V2.6 Flash yourself?

Yes. Xiaomi publishes the weights on Hugging Face as [XiaomiMiMo/MiMo-V2.6-Flash-MOPD](https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-MOPD), under MIT: 309B (MoE, 15B active) parameters, 173 GB in MXFP4.

Running it takes about 208 GB of GPU memory: a server with several data-centre GPUs (eight 80 GB GPUs hold 640 GB). That's the weight files plus 20% for working memory with short inputs; long contexts need more, and fitting in memory doesn't make it fast.

## Models like MiMo-V2.6 Flash

| Model | Input | Output | Context | Weights |
|---|---|---|---|---|
| MiMo-V2.6 Flash | $0.14 | $0.28 | 1M | Open |
| [Seed 2.0 Mini](https://dbggr.dev/models/seed-2-0-mini/) | $0.10 | $0.40 | 262K | Closed |
| [NVIDIA Nemotron 3 Super](https://dbggr.dev/models/nvidia-nemotron-3-super/) | $0.085 | $0.40 | 262K | Open |
| [Mercury 3](https://dbggr.dev/models/mercury-3/) | $0.10 | $0.35 | 1M | Closed |
| [Llama 3.3 70B](https://dbggr.dev/models/llama-3-3-70b/) | $0.10 | $0.32 | 131K | Open |
| [Claude Haiku 5.5](https://dbggr.dev/models/claude-haiku-5-5/) | $0.10 | $0.50 | 1M | Closed |

## FAQ

### How much does MiMo-V2.6 Flash cost?

MiMo-V2.6 Flash costs $0.14 per million input tokens and $0.28 per million output tokens at DeepInfra, and $0.003 per million cached input tokens. Prices are list prices in US dollars, last checked 27 October 2026.

### What is MiMo-V2.6 Flash's context window?

MiMo-V2.6 Flash takes up to 1,048,576 tokens in one request.

### Is MiMo-V2.6 Flash open weight?

Yes. Xiaomi publishes the weights, so you can run MiMo-V2.6 Flash yourself or at any host that serves it.

### Can I run MiMo-V2.6 Flash locally?

MiMo-V2.6 Flash's weights are 173 GB in MXFP4, so it needs about 208 GB of GPU memory: a server with several data-centre GPUs (eight 80 GB GPUs hold 640 GB).

### Where can I use MiMo-V2.6 Flash?

MiMo-V2.6 Flash is available from DeepInfra and Novita AI. At DeepInfra, call it as `XiaomiMiMo/MiMo-V2.6-Flash`.