Kimi K3
moonshotai/kimi-k3
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
Capabilities
ReasoningYes
Tool callingYes
Structured outputYes
TemperatureFixed
AttachmentYes
Open weightsYes
Limits
Context1,048,576 tokens
Max inputN/A
Max output131,072 tokens
Details
Familykimi-k3
Knowledge cutoffN/A
Release date2026-07-16
Last updated2026-07-16
Modalities
Inputtext, image, video
Outputtext
Community Rating
—
No ratings yet
Sign in to rate
Pricing
Cost per 1M tokens
InputN/A
OutputN/A