Compare AI models: Kimi K2 Thinking vs Kimi K3
- Kimi K2 ThinkingMoonshotHollow points use fallbacks · hover for details
- Kimi K3MoonshotHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
| Model | Reasoning | Coding | Cost efficiency | Context window | Multimodal | Tool use |
|---|---|---|---|---|---|---|
| Kimi K2 Thinking | 50/100 — Reasoning supported; no comparable benchmark | 25/100 | 46/100 | 64/100 | 0/100 | 50/100 — Tool calling supported; no comparable benchmark |
| Kimi K3 | 100/100 | 100/100 | 11/100 | 93/100 | 50/100 | 50/100 — Tool calling supported; no comparable benchmark |
Overview
Author
Context length
262K
1M
Reasoning
True
True
Input modalities
Text
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$0.55/ 1M
$3.00/ 1M
Output
$2.25/ 1M
$15/ 1M
Cached input
$0.28/ 1M
$0.30/ 1M
MomentumLast 2 mo
Unique users
0
333K
Completed sessions
5
792,300
Token share
0%
0.07%
Tokens
00%
728B-49%
No trend data
AUG 19OCT 13
RetentionWeek 1
Returning users
Pending
42%31K user-weeks