name = "Kimi K2.5"
description = "Kimi multimodal agent model for visual understanding, coding, and planning"
family = "kimi-k2"
release_date = "2026-01"
last_updated = "2026-01"
attachment = false
reasoning = true
reasoning_options = []
structured_output = true
temperature = true
tool_call = true
knowledge = "2025-01"
open_weights = true

[cost]
input = 0.60
output = 3.00

[limit]
context = 262_144
output = 32_768

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