name = "MiMo V2.5"
description = "MiMo omni model for text, image, video, audio, and agents"
family = "mimo-v2.5"
release_date = "2026-04-22"
last_updated = "2026-04-22"
attachment = true
reasoning = true
reasoning_options = []
temperature = true
tool_call = true
knowledge = "2024-12"
open_weights = true

[interleaved]
field = "reasoning_content"

[cost]
input = 0.14
output = 0.28
cache_read = 0.0028

[limit]
context = 1_000_000
output = 128_000

[modalities]
input = ["text", "image", "audio", "video"]
output = ["text"]