DeepSeek V4 Pro

“it would always start off promising, just to quickly get sidetracked, start hallucinating problems in the code”

“DeepSeek-V4-Pro plus a small dedicated STT beat an end-to-end frontier voice model on cost-per-minute by ~10x”

“V4-pro in particular seems very capable, but will just dramatically completely misunderstand user intent”

“DeepSeek v4 Pro is a far more capable model and still cheaper than anything that it competes with”

“For tasks like pondering on something, reviewing code, etc. I use Pro, just because it feels like the right model for that.”

“I can't trust it to write it's own plans from a spec, but if I give it a detailed execution plan written by Opus, it's fast and cheap”

“Their privacy policy doesn't forbid them from just straight up publishing your raw prompts as training data.”

“requires enabling "Allow paid endpoints that train on request data" in the OpenRouter privacy settings”

“As it is now, they could double or triple prices and it still would be a better value to use DS.”

“except for Hy3 , DeepSeek v4 Pro , and MiMo v2.5 Pro (whose API rates are cheap and/or discounted already)”

“Deepseek is far and away the most cost effective, fast, and quite good for 90% of implementation work.”

“DeepSeek V4 Pro is really affordable per-token but regularly kept making mistakes in the tasks I gave it”

“GPT 5.6 was picking up on quality and functional issues from DeepSeek and having it resolve them cleanly”

“greatest example of abundance of cheap infinite intelligence will be not glm5.2 but DeepSeek V4 Pro max”

“DeepSeek has consistently been among the best performers and its extreme caching performance makes it cheaper than just about anything”

“I have been heavily using DeepSeek V4 Pro at Max for a month now and I would say it is 100x cheaper.”

“The quality of what you can get from DeepSeek V4 Pro for $10 is light years ahead of what you could get for $20 a year ago.”

“on questions that it couldn't figure out, it only stated that it didn't know around 6% of the time”

“it's pretty obvious from the amount of times I've had to fix or revert a change that broke something that it's no opus”

“I really do feel like DeepSeek V4 Pro is often better than current Sonnet is, in the general case.”

“Results for kimi and deepseek are pretty much indistinguishable from opus for coding if opus writes the plan”

“Kimi and deepseek are pretty much indistinguishable from opus for coding if opus writes the plan.”

“Openweight models turned a corner around kimi 2.6, deepseek v4 pro/flash, hy3 and mimo 2.5 pro.”

“I switched to DeepSeek v4 Pro with OpenCode and am on track for a few hundred dollars of spend this month.”

“Pay for more expensive APIs like deepseek v4 pro, gemini 3.5 flash, etc. This option is not too expensive.”

“DeepSeek V4 Pro is so cheap, especially given their caching effectiveness and cached input pricing”

“Its just as capable, and makes the same kinds of dumb mistakes and the other two have been making since March. For the price, I'm more than happy with it.”

“We have lots of open-weight models like DeepSeek V4 Pro that are very close to SOTA and we know the cost of running them.”

“it's costing the same or less than the typical coding subscription, due to the discount and the power of context caching”

“DeepSeek's architecture is significantly more cost effective than anything from Google, OpenAI, or Anthropic.”

“I have extreme trouble with prompt compliance with V4 Pro in a way that I've never had with Sonnet.”

“It's good and cheap, but don't talk about politics to it or it might trigger some sort of censorship rule.”

“the model is REALLY good. I try Claude at work and Deepseek personally and this is the only model that works without trying to actively bankcrypt me.”

“It's quality of work is not bad at all, it is fairly fast and given the fraction of the cost compared to Claude, I can keep going which makes it a very compelling option.”

“the cache-hit rate is extremely high, and the cache invalidation window is much longer than every other provider's”

“DeepSeek V4 Pro is way more effective at batching multiple tasks together since the KV cache is so much lighter”

“This actually works quite well for DeepSeek V4 series which has comparatively tiny KV-cache sizes”

“I just spent a whole day using it for some pretty hefty refactors, many rounds of back-and-forths, thousands of lines of code changes”

“solid at implementation when given a specification, but falls a good bit short of Opus 4.7 max thinking when planning out larger changes”

“DeepSeek V4-Pro Max shines in competitive coding benchmarks. However, it trails both Opus models on software engineering.”