Expired50% confidenceFactExact time
In June, the developer used both the DeepSeek Flash model (approximately 130 million tokens) and the Pro model (approximately 10 million tokens).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
DeepSeek + Resonix: A Low-Cost AI Coding Solution — 150 Million Tokens for Just $1.10
bilibili晚烟安安6/21/2026
Related Claims
UnverifiedDeepSeek offers both Flash and Pro model versions accessible via API73% similarUnverifiedThe author's summarized experience in selecting AI models is: use DeepSeek Flash for single-module tasks, and use DeepSeek Pro (paid version) for tasks involving two or three or more modules.71% similarUnverifiedDeepSeek同一天还发布了一个1.6万亿参数的Pro版70% similarUnverifiedDeepSeek Flash performs poorly when handling complex UE C++ code (such as MVVM architecture implementation and irregular inventory network replication interactions), requiring a switch to the Pro version.67% similarUnverifiedThe total cost of developing a Mini Program demo using DeepCode combined with DeepSeek V4 Flash is less than one yuan.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/42885API
curl https://kongchang.com/api/v1/knowledge/claims/42885MCP
get_claim(id=42885)