DeepSeek costs OpenCode Go user $1.14/day; dual DGX breaks even in 24 years

agreed. when using local models, they did send your prompts to openai with 30 day retention to make the titles, silently.

their recent changes to the privacy policy broke their promise of zero data retention. specifically, they offered chatgpt luna under a zero data retention privacy policy. luna was later shown to be 30 days retention.

their privacy policy has never guaranteed your prompts will not be logged and when asked they have failed to revise it.

when challenged about sending data to openrouter without listing it as a 3rd party processor they offered a dismissive response. the same with running prompts through cloudflare. seems trivial, but signifies general disinterest in security.

by default if you run the harness outside your config file by accident, it will automatically run silently with a free model that sends your prompts and local data to an endpoint with training enabled. on top of that it used to dump all the prompts sent to free models into an s3 bucket, the feature was literally called 'datadumper' in the source.

Yeah, the combo of hidden telemetry and other shenanigans along with general code bloat and other tradeoffs among the handful of available OSS harness options are what convinced us it was worth writing a new harness from scratch.

Reading this issue was enough for me to never ever consider OpenCode: https://github.com/anomalyco/opencode/issues/6355

Probably less of an issue but I always disliked with their paid plan/credits that they made I nonobvious that some of the Chinese models train off of your usage. It may have changed now but they would show all these great models you could use, somewhere have a bullet that everything is private adobe have an asterisk next to a handful of those models (including their own). I am sure some cost sensitive folks are ok with that but I disliked how there was not an easy way to tell and it was opt in automatically if you used those models.

The RCE vulnerability drama made me never touch it, in any case.

It's not even possible to delete one's account!

I guess that's why they called OpenCode

I like OpenCode folks, but their marketing to ride DeepSeek's v4 moment is a pit they're digging themselves deep into.

For instance, this "marketing" claim that it'll take 24y to break even if a user uses 100m tokens/day (~$1.14 in DeepSeek v4 Flash usage) ignores the fact that OpenCode Go has 5h & weekly throttles. If you're running automated jobs [0], those throttles make it utterly useless. Besides, I think the local GPU setup in question could serve 10+ "users" at the same time, bringing down the break even by 22y (10x).

[0] For comparision, we routinely do 200m to 500m tokens on 3 to 8 automated code reviews per day with DeepSeek v4 Flash on max.

Privacy, no need to pay for tokens, offline usage, endless possibilities - you do not have to pay for tokens (subscribtion payment), so you can do more. The big issue is that local models are not "ready yet" compared to frontier and paid services. It is hard to run decent model without decent hardware. And to be honest even if you can buy hq hardware and spend a lot of money then it is not the same quality.

Also privacy and offline capabilities.

You can do this but you still need a harness. I like open code because I can use literally any model through it and can connect directly to the provider (although I use open router)

If you’re doing real work you will hit limits quickly on anthropic and codex paid tiers

The 3090s also don't have enough VRAM to run larger models too. It really comes down to how you like to develop (synchronously with lots of steering vs async agentic)

Since the announcement of DeepSeek price hike, I have been using MiniMax M3 and I am really surprised by the quality this model spits out. Subjectively speaking, the bullshit MM3M produces is waaay less than DS0731. Could it be a result of less hallucinations than DS0731? https://artificialanalysis.ai/evaluations/omniscience#aa-omn...

Maybe hallucination is good for prototyping and creative work, but maintaining and debugging code might be better done by a boring model?

Don’t forgot a number of models they have offered to you will train on your data

I've been using Qwen3.6 models locally for a couple of weeks. Both the A3B moe and the dense variant. The moe works well in Librechat combined with my local search/Web retrieval system. All components use open source projects such as SearXNG, Crawl4AI, MetaMCP, Jina rerank, but all needed quite a bit of coding to work nicely together.

I get 140 tok/s on short prompts on an rtx3090 on the qwen3.6 moe which makes is easily 4x the speed of Chatgpt or Claude doing Web research.

But it is a much simpler model. It is only good for simple queries, usually I search for cheapest product in stock in my country available online and stuff like that.

I use the dense model for planning and such, but on its own it is much inferior to for example opus. It needs careful pipelines that check facts and such and in such harness it can be used for mamy tasks.

also worth remembering API price includes power, just dividing price of the hardware by usage doesn't

Why are you hoarding the 3090s T.T They've jumped from $700 to almost double on eBay.

The value prop really depends on what you're doing.

If you're just vibe coding with giant frontier models, yes, the value will be worse. Especially now, where GPU prices have spiked another 20% last month.

For some tasks where owning the setup and full kv cache matters, the payoff calculation is ridiculously in favor of running your own deployment.

For instance for some batch classifications jobs where the prefix cache hit rate will be >95%.

The calculus also changes if you just use AI as a light tool while coding and don't need the giant models; qwen3 27B runs at 80TPS on a 5090 properly deployed.

Why not rent those out on vast.ai and make a little money each month?

Why do you have ten or so 3090s sitting in boxes?

I mean obviously it's worth it just so you can flex on HN. But curious whether there was any other reason? Retired scalper?

Do you really keep ten cards in boxes just to brag on Hacker News? Geez, our industry has gotten pathetic.

> You rent your ISP line. Why isn't renting GPU compute seen the same way?

Is it mostly seen the same way. What is unacceptable is removing the freedom (which you mentioned) of people who prefer to run models locally.

Just as people have the right to tinker at home with DIY and electronics, fully knowing they won't compete with the latest ASML machine, people are free to use open-weight models at home.

BTW Minimax H3 running local can generate amazing short vids quite fast: about 50 seconds to generate a 7 seconds vids on a 4090 (depending on the settings). I've got a friend who spams my Telegram daily with such (no censorship and NSFW btw) vids.

I don't run local but I'll defend the rights of people who want the freedom to do so and I won't look down at them from my high-horse talking about "electricity" and "productivity".