Kimi K2 Thinking
moonshotai/kimi-k2-thinking
Thinking Kimi model for slower research passes, planning, and hard technical questions
Capabilities
ReasoningYes
Tool callingYes
Structured outputNo
TemperatureSupported
AttachmentNo
Open weightsYes
Limits
Context262,144 tokens
Max inputN/A
Max output262,144 tokens
Details
Familykimi-thinking
Knowledge cutoff2024-08
Release date2025-11-06
Last updated2025-11-06
Modalities
Inputtext
Outputtext
Benchmarks
SWE-Bench Verified
71.3
resolved
Community Rating
—
No ratings yet
Sign in to rate
Pricing
Cost per 1M tokens
InputN/A
OutputN/A