So I created https://getaivo.dev, one can use model in the coding agent directly. Just `aivo claude -m deepseek-v4-pro`
aaurelions 4 hours ago [-]
It seems like any project that makes fun of Claude is bound to reach the top spot on Hacker News. Even if it’s just a project consisting of four lines of code.
This is what I’ve been using for non-confidential projects for about a week now (soon after v4 came out). I honestly can’t tell the difference, but I’m not doing anything crazy with it either.
Worth noting that I don’t think DeepSeek‘s API lets you opt out of training. Once this is up on other providers though… (OpenRouter is just proxying to DeepSeek atm)
btbuildem 2 hours ago [-]
This in essence is what allows one to use any model with CC -- including local.
faangguyindia 34 minutes ago [-]
those who use deepseek v4, what level of output you get? Codex 5.3 or GPT 5.4?
is flash version on level of gpt 5.4 mini
nadermx 4 hours ago [-]
The AI wars have begun
stingraycharles 2 hours ago [-]
This has been possible since the beginning.
vitaflo 4 hours ago [-]
I'm not exactly sure what the point of this is. Deepseek already has instructions to use its API with many CLI's including Claude Code directly:
There probably isn't a point. Someone didn't understand something, didn't research it, so they 1 shotted their first thought and sent it to the front page of HN and all of their socials. It's the future bruh
croes 3 hours ago [-]
From vibe coders for vibe coders
2ndorderthought 3 hours ago [-]
I don't always copy paste vibe coded project readme mds into Claude code and ask them to rewrite it but when I do... actually that's all I do now because my goal in life is to make wealthy overvalued companies wealthier.
kordlessagain 1 hours ago [-]
Problem?
ttoinou 4 hours ago [-]
I thought the tool format wasnt exactly the same ? So plugging any IA into claude code requires a conversion of format
selcuka 3 hours ago [-]
DeepSeek has a dedicated Anthropic-compatible endpoint [1].
Many of them expose “anthropic-compatible” APIs for this very purpose.
faangguyindia 33 minutes ago [-]
qwen also offers openai compatible endpoint.
crooked-v 4 hours ago [-]
I'm curious how well it actually works. I tried Deepseek with Hermes and Opencode and it seemed extremely bad about using some of the basic tools given, like the Hermes holographic memory tools, even with system prompt instructions strongly pointing them out.
justech 4 hours ago [-]
If you're looking for Claude Code alternatives, I would first suggest looking into pi.dev or opencode for your harness. And then for models, you can choose from OpenCode Go (IMO most cost effect at this moment), OpenRouter, or direct from DeepSeek. Better if you go the Kimi route IMO and just buy a subscription from kimi.com
agreed. OpenCode is a strong base, and with a couple modifications it can become a very effective harness. my sideproject mouse.dev I’ve been combining parts from OpenCode, Claude Code, and Hermes to build a cloud agent architecture that works well from mobile.
CharlesW 3 hours ago [-]
> OpenCode is a strong base, and with a couple modifications it can become a very effective harness.
I personally didn't find it to be competitve with Claude Code as a harness. Can I ask how you modified it to perform better?
Aeroi 3 hours ago [-]
I haven’t run formal evals but i improved the experience for my own needs and it feels noticeably better with these modifications.
-Claude-style subagents
-an MCP layer for higher-level tools
-Cursor-style control plane modes like Ask, Plan, Debug, and Build.
The MCP layer lets the harness use things like GitHub file/code read, PR creation, web search/fetch, structured user questions, plan-mode switching, user skills, and subagents.
So the improvement is mostly from better ui/ux orchestration and tool access. There's some things from hermes that are interesting as well.
Most of my focus has been on applying this stack to sandboxed cloud agents so you can properly code and work from mobile devices.
I can't definitively say that the stack is better or worse than Claude code, more just tuned for my use case I guess.
bakugo 3 hours ago [-]
> I would first suggest looking into pi.dev
Looked into this one. Thought it was suspicious that it only had 7 open issues on github. Turns out they have a bot that auto-closes every single issue just because.
I honestly have no words.
__cayenne__ 34 minutes ago [-]
The maintainer, Mario, sometimes declares the repo is on an “issue holiday” where issues are auto closed. This particular holiday is because there is a big refactor coming up. In non holiday periods issues can be reported as normal.
> Maintainers review auto-closed issues daily and reopen worthwhile ones. Issues that do not meet the quality bar below will not be reopened or receive a reply.
Seems like not an unreasonable way to deal with the problem of large numbers of low quality issues being submitted.
The idea is for it to he extremely minimal which strikes me as a very opinionated stance, and not opinions I agree with.
justinhj 29 minutes ago [-]
It's a very interesting project. Many popular open source projects are inundated with poor quality issues and prs, hence the defences they are starting to erect.
aaurelions 4 hours ago [-]
Another very cost-effective option is Ollama Cloud. In a month of use, I only hit the 5-hour limit once, when I ran 8 agents simultaneously for 2 hours.
kopirgan 15 minutes ago [-]
On which tier?
4 hours ago [-]
postatic 4 hours ago [-]
definitely worth it - have both ollama cloud, opencode and hermes running to test them all out, working great so far.
dbeley 5 minutes ago [-]
Honestly with the likes of Opencode / pi / hermes I don't really find the "Claude Code agent loop" part particularly interesting.
The edge Anthropic has on others lies on its models performance. CLI tooling (and obviously pricing) is definitely not better than others.
999900000999 18 minutes ago [-]
I just spent half my day getting CUDA and LLAMA to work with my 5070TI.
I was able to use it in agent mode with Roo, I stopped after having it write out a plan, but I'll continue when I have more time.
Deepseek feels less likely to do a straight up rug pull since you can self host with enough money, but I'm still more excited about local solutions.
Usually I just need grunt work done. I'm not solving difficult problems.
langitbiru 17 minutes ago [-]
I'm wondering why DeepSeek didn't create an AI coding agent like Kimi Code.
_345 5 hours ago [-]
If you're okay with sonnet level performance, this sounds like a straight upgrade. But I find that sonnet messes up too much, that it ends up not being worth cost optimizing down to using it or another sonnet-level model. Glad to have this as an option though
maxdo 41 minutes ago [-]
This is the problem: you need the best model, not just a good one, for:
- Good architecture, which requires reading specs, code, etc. reads like: lots of tokens in/out
- Bug fixing — same, plus logs, e.g. datadog
Once you've found the path, patches are trivial and the savings are tiny unless you're doing refactoring/cleanup.
testing gets more and more complicated. Take a look at opencode go, and you see this:
>Includes GLM-5.1, GLM-5, Kimi K2.5, Kimi K2.6, MiMo-V2-Pro, MiMo-V2-Omni, MiMo->V2.5-Pro, MiMo-V2.5, Qwen3.5 Plus, Qwen3.6 Plus, MiniMax M2.5, MiniMax M2.7, >DeepSeek V4 Pro, and DeepSeek V4 Flash
and now on your own with bugs, all of these models can produce at scale. Am i missing anything in this picture. What is the real use of cheaper models?
2ndorderthought 4 hours ago [-]
A lot of people are having good experiences doing things like using opus for designing and using locally hosted qwen3.6 for implementation.
I could see a serious cost reduction story by using opus for design and deepseek for implementation.
Personally I would avoid anthropic entirely. But I get why people don't.
girvo 4 hours ago [-]
Like me: that’s what I do. Either Opus 4.7 or GLM 5.1 for planning, write it out to a markdown file, then farm it out to Qwen 3.6 27B on my DGX Spark-alike using Pi. Works amusingly well all things considered.
brianjking 1 hours ago [-]
How are you interacting with GLM 5.1? Via the Claude Code harness? I really wish they'd release a fully multimodal model already.
2ndorderthought 4 hours ago [-]
How is glm 5.1? I have t tried it yet but have been meaning too
girvo 3 hours ago [-]
It's surprisingly good. Beats MiniMax 2.7 and Qwen 3.5 Plus in my testing (I haven't tested 3.6 plus though), quite handily. It's far better than Sonnet, and often equivalent to Opus for the web development and OCaml tasks I'm using it for. It definitely isn't Opus 4.7, but its far good enough to earn it's keep and is substantially cheaper.
sshine 2 hours ago [-]
I agree with this. And also: it uses more thinking time to reach this. So while you get a lot of tokens on their plan, the peak 3x token usage multiplier + the extra thinking means you run into the rate limit anyways.
girvo 2 hours ago [-]
True, though the $20 equivalent used for planning only I don’t hit those limits often, vs Claude where the Pro can literally hit limits with a single prompt haha
aftbit 4 hours ago [-]
What hardware are you using to power this?
girvo 3 hours ago [-]
> DGX Spark-alike
Probably wasn't clear enough if you don't know what that is already, apologies
It's an Asus Ascent GX10, which is a little mini PC with 128GB of LPDDR5X as shared memory for an Nvidia GB10 "Blackwell" (kind of, it's a long story) GPU and a MediaTek ARM CPU
sterlind 49 minutes ago [-]
pulls up chair
could you tell me the long story?
edit: or wait, is it quasi-Blackwell the way all DGX Sparks are quasi-Blackwell? like the actual silicon is different but it's sorta Blackwell-shaped?
girvo 32 minutes ago [-]
Yeah exactly. Shader model 121 is different to SM 120 (consumer Blackwell) and is different again to data centre Blackwell SM100.
The promise of this chip was “write your code locally, then deploy to the same architecture in the data centre!”
Which is nonsense, because the GB10 is better described as “Hopper with Blackwell characteristics” IMO.
Still great hardware, especially for the price and learning. But we are only just starting to get the kernels written to take advantage of it, and mma.sync is sad compared to tcgen05
aftbit 3 hours ago [-]
Ah yeah I saw that, I was just curious which particular mini-PC you were using. I was considering picking up one of the various AI Max 395 boxes before the RAMpocalypse but didn't take the plunge. Thanks for the response!
girvo 2 hours ago [-]
I heavily considered one of the AMD Strix Halo boxes, but part of the reason I wanted this was to learn CUDA :)
chrsw 4 hours ago [-]
I keep re-learning this lesson: I chug along with a lesser model then throw a problem at it that's too complex. Then I try different models until I give up and bring in Opus 4.6 to clean up.
energy123 29 minutes ago [-]
It's not even that much cheaper, GPT 5.5 is about 2x more expensive per task when you adjust for less token usage, according to Artificial Analysis. Not worth it unless you're in it for an ideological reason.
brianwawok 4 hours ago [-]
And I keep using Opus to like, make git commits. Really just need a smart router that is actually smart, vs having to micromanage model
sterlind 44 minutes ago [-]
the problem is managing the contexts. your session might fit in Opus, but will that smaller model you dispatch the git commit to fit? even so, will it eat too much on prefill? do you keep compactions around for this, or RAG before dispatch or something? how do you button back up the response?
all doable but all vaguely squishy and nuanced problems operationally. kinda like harness design in general.
willio58 3 hours ago [-]
I don’t find this with sonnet at all. As long as I have a solid Claude.md and periodically review the output and enforce good code practices via basic CI gates I’ve rarely ever found myself having to switch to opus
2ndorderthought 3 hours ago [-]
You might be surprised then at how good cheaper models solve your problems
4 hours ago [-]
nclin_ 1 hours ago [-]
Is claude code the best coding harness? Anyone running evals on that?
ahmadyan 1 hours ago [-]
In my anecdotal experience, it is not. Same model, opus, works better in 3P harnesses such as Factory Droid or Amp.
Claude code, on the other hand, is the most subsidized one, both for consumers (through max subscription) and for enterprises (token discounts). It is also heavily optimized for cost, specially token caching and reduced thinking, at the expense of quality.
dopeepsreaddocs 2 hours ago [-]
Did... Did you just ask an AI to one-shot something that normally amounts to no more than setting two env variables?
alexdns 4 hours ago [-]
obviously vibe coded ( co authored ) + the prices dont even match
2ndorderthought 4 hours ago [-]
It's going to be real hard to find headlines that weren't vibe coded from here on out unfortunately.
SchemaLoad 4 hours ago [-]
Unless I actually know the author I assume everything here is vibeslop and full of mistakes.
Maybe I need to switch to some news publication that actually does real research and writing still. Because public forums like this have been completely destroyed by LLMs.
cyanydeez 4 hours ago [-]
welp, pack it it in boys, it was nice conceptualizing all you as real humans on the internet. I guess I'll just have to go touch grass if I want to feel parasocial.
dragontamer 4 hours ago [-]
I mean, we have the tech and community to actually build in person meetups and sign CRT certificates, right?
If we touch grass in person and swap certificate requests, we can actually rebuild a trust network.
This is a pretty old problem with regards to clubs / secret societies and whatnot. And with certificates / PKI, our modern security tools have solved all the technical problems.
2ndorderthought 4 hours ago [-]
I wish I could be invited to a secret club of guaranteed humans. Someone hand me a certificate next time you see me! Also don't stab me kthxbye
cyanydeez 4 hours ago [-]
Unfortunately, a lot of whats happening in the tech world seems to be from some super serious AI cults, so not sure goin offline like this is any better.
2ndorderthought 3 hours ago [-]
Yea but we could have fun. Play some dnd. Drink tea or whiskey. Eat pizza pie. Light saber battle. Buy a megaphone and hang out at a street corner telling passerbys they are perfectly acceptable and worthy of kindness and love
inciampati 3 hours ago [-]
poorly vibe coded. machines can check details easily, use them.
vagab0nd 3 hours ago [-]
This has become a problem for me. I like trying new things. But I also know that in about a week, there's going to be a better/cheaper setup. And a week after that. And ideally I'd like to get some coding done when I'm not tinkering with the tools.
So I think I'll stay with CC for now.
kordlessagain 1 hours ago [-]
CC has the ability to use Ollama as well, which includes the ability for Ollama to proxy to Ollama's cloud models. It's brilliant, and works with a single Ollama command that doesn't mess with CC at all (so you can run them at the same time).
ANTHROPIC_BASE_URL="https://openrouter.ai/api" ANTHROPIC_AUTH_TOKEN="$OPENROUTER_API_KEY" ANTHROPIC_DEFAULT_SONNET_MODEL="deepseek/deepseek-v4-flash" CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 claude
1 hours ago [-]
3 hours ago [-]
3 hours ago [-]
gnat 5 hours ago [-]
This repo's README explains how it works and you can do it yourself. claude looks for environment variables that say which API endpoint to talk to, which key to pass, which model name to use for haiku/sonnet/opus-level workloads, etc.
dukeofdoom 34 minutes ago [-]
Is there some way to make claude/codex beep when it finishes a task.
Lihh27 4 hours ago [-]
the wrapper is basically env var glue. You’re still betting the whole loop on Anthropic's closed client.
game_the0ry 4 hours ago [-]
Cost engineering [1] will be the next hot topic for AI.
[1] A fancier way of saying "reducing cost."
fHr 2 hours ago [-]
layer on layer on layer to refactor bunch of lines xD
5 hours ago [-]
3 hours ago [-]
esafak 5 hours ago [-]
Why wouldn't you use something open source like OpenCode, which already support DSv4 and has more features than CC?
CharlesW 3 hours ago [-]
Coding harnesses make a big difference, and OpenCode is notably less effective than Claude Code (1) in my experience, (2) with the models I've tried it on. (I've not yet tried it with DSv4.)
dlx 4 hours ago [-]
As someone who does use other models with CC, I am curious about opencode, what extra features does it have that you find essential?
esafak 4 hours ago [-]
I like being able to add a wide array of models, define perms for agents and subagents, turn MCPs on and off at will, and be able to fix bugs I find in it.
dlx 4 hours ago [-]
fair enough...any drawbacks that you've found?
esafak 4 hours ago [-]
Its UI isn't as slick, and it has bugs, but so does CC and you can submit a PR to have them fixed in OC.
ttoinou 4 hours ago [-]
More features than CC ?
Also opencode tracks you by default. Its not safe. Every first prompt you send is routed through their servers, logged and they can use your data however they want
sedawkgrep 4 hours ago [-]
I thought this was debunked awhile ago. ?
esafak 4 hours ago [-]
I could not find any evidence of prompt logging. The code is open; can you point me to it?
2ndorderthought 4 hours ago [-]
Oh shoot now the next CC upgrade will blow your subscription for doing this
morpheos137 4 hours ago [-]
anthropic messed up big time harness works with any muh commodity LLM, meanwhile VCs were duped on the myth of FOOM AGI, probably not a cooincidence Anthropic is enmeshed with the scifi fan fic forum known as lesswrong. The world wants useful tools. The bay area bubble in contrast thrives on Mythos.
hgyyy 3 hours ago [-]
I think OAI and Anthropic will be ok for a year or two. But after that If they still continue to earn revenues from selling tokens to firms/software engineers they will be in serious trouble.
The American firms are not demonstrating escape velocity and as long as china offers something somewhat comparable and offers it at a very low price to compensate for any difference in quality, they will not be generating enough in cash flows to finance reinvestment. I highly doubt they’ll be able to continue raising external financing for numerous periods from here on out - they gotta start showing strong financials and that they are running away from the open source models.
LeFantome 2 hours ago [-]
The performance gap will likely close as Chinese hardware improves. This is happening very rapidly.
Already DeepSeek v4 is being hosted on Huawei Ascend 950. What do you think those cost relative to NVIDIA gear?
morpheos137 2 hours ago [-]
I wouldnt put it past the US gov to ban foreign models. they tried to ban tiktok. what is being demosrrated here is silicon valley can not withstand a competitive market.
LeFantome 2 hours ago [-]
Good luck banning Open Source models.
Not only that but other countries are very unlikely to follow suit, so it is just a straight-up productivity tax on the US.
morpheos137 2 hours ago [-]
Yeah see the Nvidia china us gov self own. The assumption seems to be 1.4 billion people in a middle income country are dependent on 300 million for tech.
bwfan123 1 hours ago [-]
> anthropic messed up big time harness works with any muh commodity LLM
that surprised me too. The intelligence is at the client, and by making that open, anthropic has commoditized the coding agent.
kk_mors 28 minutes ago [-]
[dead]
alattaran 5 hours ago [-]
[flagged]
volume_tech 3 hours ago [-]
[flagged]
deadbabe 3 hours ago [-]
I had a call with our CTO and we are pivoting away from Claude Code to DeepClaude because the cost savings are too substantial to ignore.
Rendered at 03:33:48 GMT+0000 (Coordinated Universal Time) with Vercel.
This is what I’ve been using for non-confidential projects for about a week now (soon after v4 came out). I honestly can’t tell the difference, but I’m not doing anything crazy with it either.
Worth noting that I don’t think DeepSeek‘s API lets you opt out of training. Once this is up on other providers though… (OpenRouter is just proxying to DeepSeek atm)
is flash version on level of gpt 5.4 mini
https://api-docs.deepseek.com/quick_start/agent_integrations...
[1] https://api-docs.deepseek.com/guides/anthropic_api
I personally didn't find it to be competitve with Claude Code as a harness. Can I ask how you modified it to perform better?
-Claude-style subagents -an MCP layer for higher-level tools -Cursor-style control plane modes like Ask, Plan, Debug, and Build.
The MCP layer lets the harness use things like GitHub file/code read, PR creation, web search/fetch, structured user questions, plan-mode switching, user skills, and subagents.
So the improvement is mostly from better ui/ux orchestration and tool access. There's some things from hermes that are interesting as well.
Most of my focus has been on applying this stack to sandboxed cloud agents so you can properly code and work from mobile devices.
I can't definitively say that the stack is better or worse than Claude code, more just tuned for my use case I guess.
Looked into this one. Thought it was suspicious that it only had 7 open issues on github. Turns out they have a bot that auto-closes every single issue just because.
I honestly have no words.
> Maintainers review auto-closed issues daily and reopen worthwhile ones. Issues that do not meet the quality bar below will not be reopened or receive a reply.
Seems like not an unreasonable way to deal with the problem of large numbers of low quality issues being submitted.
https://github.com/badlogic/pi-mono/blob/main/CONTRIBUTING.m...
The edge Anthropic has on others lies on its models performance. CLI tooling (and obviously pricing) is definitely not better than others.
I was able to use it in agent mode with Roo, I stopped after having it write out a plan, but I'll continue when I have more time.
Deepseek feels less likely to do a straight up rug pull since you can self host with enough money, but I'm still more excited about local solutions.
Usually I just need grunt work done. I'm not solving difficult problems.
Once you've found the path, patches are trivial and the savings are tiny unless you're doing refactoring/cleanup.
testing gets more and more complicated. Take a look at opencode go, and you see this:
>Includes GLM-5.1, GLM-5, Kimi K2.5, Kimi K2.6, MiMo-V2-Pro, MiMo-V2-Omni, MiMo->V2.5-Pro, MiMo-V2.5, Qwen3.5 Plus, Qwen3.6 Plus, MiniMax M2.5, MiniMax M2.7, >DeepSeek V4 Pro, and DeepSeek V4 Flash
and now on your own with bugs, all of these models can produce at scale. Am i missing anything in this picture. What is the real use of cheaper models?
I could see a serious cost reduction story by using opus for design and deepseek for implementation.
Personally I would avoid anthropic entirely. But I get why people don't.
Probably wasn't clear enough if you don't know what that is already, apologies
It's an Asus Ascent GX10, which is a little mini PC with 128GB of LPDDR5X as shared memory for an Nvidia GB10 "Blackwell" (kind of, it's a long story) GPU and a MediaTek ARM CPU
could you tell me the long story?
edit: or wait, is it quasi-Blackwell the way all DGX Sparks are quasi-Blackwell? like the actual silicon is different but it's sorta Blackwell-shaped?
The promise of this chip was “write your code locally, then deploy to the same architecture in the data centre!”
Which is nonsense, because the GB10 is better described as “Hopper with Blackwell characteristics” IMO.
Still great hardware, especially for the price and learning. But we are only just starting to get the kernels written to take advantage of it, and mma.sync is sad compared to tcgen05
all doable but all vaguely squishy and nuanced problems operationally. kinda like harness design in general.
Claude code, on the other hand, is the most subsidized one, both for consumers (through max subscription) and for enterprises (token discounts). It is also heavily optimized for cost, specially token caching and reduced thinking, at the expense of quality.
Maybe I need to switch to some news publication that actually does real research and writing still. Because public forums like this have been completely destroyed by LLMs.
If we touch grass in person and swap certificate requests, we can actually rebuild a trust network.
This is a pretty old problem with regards to clubs / secret societies and whatnot. And with certificates / PKI, our modern security tools have solved all the technical problems.
So I think I'll stay with CC for now.
If you are interested, I've built an agentic terminal that helps manage these types of things better: https://deepbluedynamics.com/hyperia
https://api-docs.deepseek.com/quick_start/agent_integrations...
[1] A fancier way of saying "reducing cost."
Also opencode tracks you by default. Its not safe. Every first prompt you send is routed through their servers, logged and they can use your data however they want
The American firms are not demonstrating escape velocity and as long as china offers something somewhat comparable and offers it at a very low price to compensate for any difference in quality, they will not be generating enough in cash flows to finance reinvestment. I highly doubt they’ll be able to continue raising external financing for numerous periods from here on out - they gotta start showing strong financials and that they are running away from the open source models.
Already DeepSeek v4 is being hosted on Huawei Ascend 950. What do you think those cost relative to NVIDIA gear?
Not only that but other countries are very unlikely to follow suit, so it is just a straight-up productivity tax on the US.
that surprised me too. The intelligence is at the client, and by making that open, anthropic has commoditized the coding agent.