Kenari
Kimi K3
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
kimi-k3Context
1M
Max output
131.1K
Input $/M
Free
Output $/M
Free
Cache read $/M
—
Cache write $/M
—
Against the catalogue
Context window1M
Larger than 95% of the 5,751 models listed
Input priceFree
Cheaper than 91% of priced models
Capabilities
Reasoningsupported
Tool callingsupported
Structured outputsupported
Attachmentssupported
Temperaturenot supported
Open weightssupported
Interleaved thinkingnot supported
Modalities
Input
TextImageVideo
Output
Text
Reasoning controls
effortlow, high, maxPricing detail
| Rate | Base $/M |
|---|---|
| Input | Free |
| Output | Free |