Compare AI models: Kimi K2.5 vs Kimi K3
- Kimi K2.5MoonshotHollow 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 K2.5 | 50/100 — Reasoning supported; no comparable benchmark | 20/100 | 44/100 | 62/100 | 50/100 | 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, Image, Video
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$0.45/ 1M
$3.00/ 1M
Output
$2.80/ 1M
$15/ 1M
Cached input
Unknown
$0.30/ 1M
MomentumLast 2 mo
Unique users
20K
347K
Completed sessions
14,654
785,862
Token share
0%
0.08%
Tokens
9B-82%
753B-46%
AUG 18OCT 12
AUG 18OCT 12
RetentionWeek 1
Returning users
77.1%214 user-weeks
42%31K user-weeks