name = "MiniMax-M3"
description = "MiniMax multimodal model for long-context coding, perception, and agent planning"
family = "minimax"
release_date = "2026-06-01"
last_updated = "2026-06-25"
attachment = true
reasoning = true
temperature = true
tool_call = true
open_weights = true

[[reasoning_options]]
type = "toggle"

[cost]
input = 0.30
output = 1.20
cache_read = 0.06

[[cost.tiers]]
tier = { size = 512_000 }
input = 0.60
output = 2.40
cache_read = 0.12

[limit]
context = 1_000_000
output = 128_000

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