@TheGeorgePu: I'm trying out DeepSeek V4 Pro, and really like it. Super underrated model. As good as Opus 4.8 from the few tests I ra…
Summary
User @TheGeorgePu praises DeepSeek V4 Pro, calling it underrated and comparing it favorably to Opus 4.8 based on initial tests.
View Cached Full Text
Cached at: 06/17/26, 04:01 PM
I’m trying out DeepSeek V4 Pro, and really like it.
Super underrated model.
As good as Opus 4.8 from the few tests I ran.
Similar Articles
We Tested DeepSeek V4 Pro and Flash Against Claude Opus 4.7 and Kimi K2.6 (11 minute read)
DeepSeek released V4 Pro and V4 Flash under MIT license on April 24, 2026. In benchmarks against Claude Opus 4.7 and Kimi K2.6, V4 Pro scored 77/100 at $2.25, placing between Opus 4.7 (91) and Kimi K2.6 (68), while V4 Flash scored 60/100 at $0.02, the cheapest in the comparison, with a 75% discount on V4 Pro through May 31.
DeepSeek-V4-Flash-0731 now far surpassing the DeepSeek-V4-Pro-Preview in benchmarks
DeepSeek's new V4-Flash-0731 model is now far outperforming the V4-Pro-Preview in benchmarks, marking a significant improvement in the model family.
DeepSeek V4 Pro 0813 quietly released
DeepSeek has quietly released V4 Pro (0813), with API documentation showing support for the Responses API format and integration with Codex, enabling use of deepseek-v4-flash/pro models.
@Av1dlive: holy shit this is a f**king gold mine I replaced opus 5 with deepseek v4-flash, it's basically free and someone figured…
A viral tweet shares a 3-step setup for running DeepSeek V4-flash subagents as a self-improving loop inside Codex, calling it a cost-effective replacement for Opus 5.
@andrewchen: honestly pretty incredible DSV4 Flash 0731 versus Opus 4.6:
Andrew Chen shares excitement about testing DeepSeek V4 Flash 0731 on dual NVIDIA DGX Sparks, comparing it to Opus 4.6.