Model
Model
xiaomi
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...
| Provider | Quantization | Input / M tokens | Output / M tokens |
|---|---|---|---|
| Relacerelace/mxfp4 | mxfp4 | $0.10 | $0.24 |
| Darkbloomdarkbloom/fp4 | fp4 | $0.10 | $0.28 |
| Makoramakora/fp8 | fp8 | $0.13 | $0.28 |
| DeepInfradeepinfra/fp8 | fp8 | $0.133 | $0.266 |
| GMICloudgmicloud/bf16 | bf16 | $0.14 | $0.28 |
| Novitanovita/fp8 | fp8 | $0.14 | $0.28 |
| Xiaomixiaomi/fp8 | fp8 | $0.14 | $0.28 |
| Io Netio-net/fp8 | fp8 | $0.15 | $0.29 |
| Venicevenice/fp8 | fp8 | $0.175 | $0.35 |
Prices are what the Provider charges, synced 2026-10-21. Amber adds its platform fee to each Trial’s total; see pricing.
Amber has no curated Model Configuration for this Model yet. Create a custom one in your Workspace to evaluate it.