> ## Documentation Index
> Fetch the complete documentation index at: https://www.narev.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# MiMo-V2.6-Flash-RL

> Tok/s vs cost of self-hosting XiaomiMiMo/MiMo-V2.6-Flash-RL on H200:8.

```bash theme={null}
iwant launch mimo-v2.6-flash
```

These commands record the benchmark run. Check [current launch options](https://www.narev.ai/docs/iwant/usage.md) before launching.

Compare GPU configurations and cloud costs for this model. Solid curves use measured results. Dashed curves apply another cloud's hourly price to the same GPU configuration and throughput.

## Hardware cost comparison

The table shows the lowest cost per million output tokens on each curve, at its highest measured throughput. Your cost increases when utilization falls. Estimated offers use the cheapest listed on-demand region for each cloud and GPU configuration.

| Provider | GPUs | Basis | USD per 1M output tokens at peak |
| - | - | - | - |
| GCP | 8× H200 | Measured | 2.495 |
| AWS | 8× H200 | Estimated | 2.594 |
| Azure | 8× H200 | Estimated | 3.475 |
| GCP | 8× H200 | Estimated | 3.556 |

Estimates assume identical throughput for the same GPU configuration across clouds. Listed prices do not guarantee capacity. Measured pricing modes and regions are shown only where recorded by the source; estimates use on-demand pricing.

## Benchmark runs

| Recipe | Hardware | Run started (source time) |
| - | - | - |
| mimo-v2.6-flash\@v2 | GCP a3-ultragpu-8g H200:8 asia-south1-b Spot | 2026-09-25 13:43:26.000 |

## Hosted API context

The API reports a median completion price of 0.265 USD per million tokens across 2 offers. Input charges and workload comparability are unverified, so this is not a savings claim or a plotted baseline.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.