CompareAI models
- DeepSeek V4 FlashDeepSeek
- Kimi K2.5Moonshot
ReasoningCodingCost efficiencyContext windowMultimodalTool use
| Model | Reasoning | Coding | Cost efficiency | Context window | Multimodal | Tool use |
|---|---|---|---|---|---|---|
| DeepSeek V4 Flash | 100/100 | 74/100 | 72/100 | 81/100 | 0/100 | No data |
| Kimi K2.5 | 100/100 | 20/100 | 44/100 | 62/100 | 50/100 | No data |
Overview
Author
Context length
1M
262K
Reasoning
True
True
Input modalities
Text
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$0.15/ 1M
$0.60/ 1M
Output
$0.60/ 1M
$3.00/ 1M
Cached input
$0.003/ 1M
$0.10/ 1M
MomentumLast 2 mo
Unique users
4.4M
46K
Completed sessions
34,142,042
13,447
Token share
44.6%
0%
Tokens
298T+139%
28B-80%
JUL 25SEP 18
JUL 25SEP 18
RetentionWeek 1
Returning users
68.3%483K user-weeks
69.5%763 user-weeks
Related comparisons. Other model pairs to check.