Kimi K2.6
moonshotai/kimi-k2.6
Multimodal Kimi workhorse for agent loops, coding tasks, and visual context
Capabilities
ReasoningYes
Tool callingYes
Structured outputYes
TemperatureSupported
AttachmentYes
Open weightsYes
Limits
Context262,144 tokens
Max inputN/A
Max output262,144 tokens
Details
Familykimi-k2
Knowledge cutoff2025-01
Release date2026-04-21
Last updated2026-04-21
Modalities
Inputtext, image, video
Outputtext
Benchmarks
SWE-Bench Verified
80.2
resolved
Artificial Analysis Coding Agent Index
50.5
average pass@1
SWE-Atlas Codebase QnA
59.8
pass@1
SWE-Bench Pro
27.3
pass@1
Terminal-Bench
64.3
pass@1
Community Rating
—
No ratings yet
Sign in to rate
Pricing
Cost per 1M tokens
InputN/A
OutputN/A