DeepSeek-V4-Flash-0731vsKimi K2 Thinking

DeepSeek-V4-Flash-0731
Kimi K2 Thinking
Specifications
Parameters
1T
Context window
256k
API pricing
Input price
$0.22
Output price
$0.66
Cached input price
$0.007
Cheapest input
$0.04OpenInference$0.60Google
Cheapest output
$0.10OpenInference$2.50Google
Benchmarks
SWE-Bench Verified
79%71.3%
Benchmarks
BullshitBench v2
39%
Terminal-Bench 2.1
82.7%
Toolathlon-Verified
70.3%
BrowseComp
73.2%
CyberGym
76.7%
Humanity's Last Exam · with tools
34.8%
AutomationBench
25.1%
Overview
CompanyDeepSeekMoonshot AI
Release dateJul 31 2026Nov 6 2025
AccessProprietaryOpen Weight

Other comparisons

DeepSeek-V4-Flash-0731vsClaude Fable 5.1Kimi K2 ThinkingvsClaude Fable 5.1DeepSeek-V4-Flash-0731vsGPT-6 AstraKimi K2 ThinkingvsGPT-6 AstraDeepSeek-V4-Flash-0731vsGemini 3.8 FlashKimi K2 ThinkingvsGemini 3.8 FlashDeepSeek-V4-Flash-0731vsMuse Spark 1.3Kimi K2 ThinkingvsMuse Spark 1.3DeepSeek-V4-Flash-0731vsGrok 4.6Kimi K2 ThinkingvsGrok 4.6DeepSeek-V4-Flash-0731vsMistral Medium 3.5Kimi K2 ThinkingvsMistral Medium 3.5

Frequently asked questions

DeepSeek-V4-Flash-0731 leads Kimi K2 Thinking on 1 of the 1 benchmark they both report (SWE-Bench Verified). Only DeepSeek-V4-Flash-0731 has a verified first-party API price: $0.22 per million input tokens and $0.66 per million output tokens. No pay-as-you-go API rate is tracked for Kimi K2 Thinking. Kimi K2 Thinking shipped 267 days before DeepSeek-V4-Flash-0731, so benchmark comparisons should account for the intervening progress.

DeepSeek-V4-Flash-0731 is proprietary, while Kimi K2 Thinking is open weight.

On SWE-Bench Verified, DeepSeek-V4-Flash-0731 leads at 79% vs Kimi K2 Thinking at 71.3%.