MiMo-V2.6-Flash

xiaomi/mimo-v2.6-flash

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

MiMo-V2.6-Flash

reasoning open weights tools

Xiaomi 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...

Input $/1M: $0.14
Output $/1M: $0.28
Context: 1.0M
Max output: 131K
Released: Sep 21, 2026
Modalities: textimagevideoaudio

Cached input reads $0.003 per 1M · weights on Hugging Face as XiaomiMiMo/MiMo-V2.6-Flash-RL

On this deployment

Nothing on this deployment answers as this model yet. Connect your own provider under Model providers, or add a target to your catalogue - the router picks it up without retraining.

Not available here yet

Signed in, add the model under Model providers; self-hosting, add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs MiMo-V2.6-Flash
targets:
  - id: mimo-v2-6-flash
    kind: llm
    name: MiMo-V2.6-Flash
    metadata:
      model: xiaomi/mimo-v2.6-flash          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 1048576
    cost:
      usd_per_1k_tokens: 0.000210

Price among Xiaomi models

Input list price per million tokens; MiMo-V2.6-Flash is the cheapest of 5 listed.

1
MiMo-V2.6-Flash
$0.14
2
MiMo-V2.5
$0.14
3
MiMo-V2.6-Pro
$0.43
4
MiMo-V2.5-Pro
$0.43
5
MiMo-V2.6-Pro-UltraSpeed
$4.35

More from Xiaomi

Other models by the same vendor in the catalogue.