I did cut loose Deepseek v4 on a decent sized Typescript codebase and asked it to only focus on a single endpoint and go in depth on it layer by layer (API, DTOs, service, database models) and form a complete picture of types involved and introduced and ensure no adhoc types are being introduced.

It developed a very brief but very to the point summary of types being introduced and which of them were refunded etc.

Then I asked it to simplify it all.

It obviously went through lots of files in both prompts but total cost? Just $0.09 for the Pro version.

On Claude Opus I think (from past experience before price hikes) these two prompts alone would have burned somewhere between $9 to $13 easily with not much benefit.

Note - I didn't use Open router rather used the Deepseek API directly because Open router itself was being rate limited by Deep seek.

I have a gut feeling that these models can do just as well, has someone run a reasonable size task — >=1-2 days of designing and planning — and see it work well with these models?

* For me what worked well was the grill me skill(or its variation) at the design stage, the hygiene I followed here was have it ask one question at a time, resolving dependencies at the design stage and reading the hashed out plan closely. The use of a couple of other MCP tools like a documentation server like deepwiki and arxiv for grounding. Other tricks I use are having high signal tests and having claude either be able to read logs and code at the same time or embedding it in the execution(e.g. as a debugger, repl or devtools)

For DS4 Pro there's a discount going on for the official API, which sometimes gets overlooked and mixed up in discussions. Simon uses the full price in the comparison, so that's not an issue here.

The other issue is that DS4 Pro and K2.6 often use way more reasoning tokens than the frontier models. In my testing there are certain pathological cases where a request can cost the same as with a frontier model because they use so much more tokens. To be fair I'm using DS and kimi via 3rd party providers, so they might have issues with their setups.

But if you look at the Artificial Analysis pages of the models you'll see that DSv4 Pro uses 190M tokens and K2.6 170M tokens for their intelligence benchmark, while GPT 5.5 (high) only used 45M.[0][1][2]

I recommend looking at the "Intelligence vs. Cost to Run Artificial Analysis Intelligence Index" ("Intelligence vs Cost" in the UI). The open source models are still cheaper to run, but not by as much as you'd think just looking at the token prices.

[0] https://artificialanalysis.ai/models/deepseek-v4-pro [1] https://artificialanalysis.ai/models/kimi-k2-6 [2] https://artificialanalysis.ai/models/gpt-5-5-high

"Can you tell me who was on series 8 of Taskmaster, and what's the general opinion about the series? No spoilers!"

It told me amongst other things that Paul Sinha was diagnosed with Parkinsons, as well as who the winner was.

Then I said, "But I said no spoilers!"

And it apologised for telling me Paul Sinha was diagnosed with Parkinsons.

To be clear, i'm not doing state of the art stuff. I mostly used it for frontend development since i'm not great at that and just need a decent looking prototype.

But for my purposes it's a perfectly good model, and the price is decent.

I can't wait for open model small enough for me to run locally come out though. I hate having to rely on someone elses machines (and getting all my data exfiltrated that way)

For me, this is a real alternative after I cancel my github copilot towards the end of the month..

Those tokens are heavily subsidized, but DeepSeek's API pricing is looking really good. For example, with an agentic coding setup (roughly 85% input, 15% output and around 90% cache reads) I'd get around 150M tokens per month for the same 100 USD. Even at more output tokens and worse cache performance, it'd still most likely be upwards of 100M.

Two caveats: - when inferring through Openrouter, we've had a lot of issues with very slow speeds (TPS) and an occasional instability. I just checked and it's still 10-30 TPS on all available providers, which is not a lot for a model that likes to think as much as DeepSeek does.

- the official DeepSeek API makes no guarantees of data privacy even for paying users.

Both points could be moot with using it through Azure AI foundry (the latter is, afaik); I have yet to test that.

In any case, happy to see more open-weights models that are somewhat competitive with SOTA models!

We had to really understand why it outperformed DeepSeek V4 Pro (although even on unreliable model cards, Flash was very close to Pro). Pro is slower and smarter in one-shot reasoning problems, but less effective with tools and therefore less performant in long horizon agentic tasks (especially with custom tools it was not trained on).

Benchmarks at https://gertlabs.com/rankings

I'm gonna stick to GLM5.1 for now.

e.g. Have V4 call out to Opus when it's uncertain, but otherwise handle execution.

The results with Sonnet/Haiku in the blog post seemed promising, so I'm curious how it would go with these latest open models.

[0] https://claude.com/blog/the-advisor-strategy

(3) The deepseek-v4-pro model is currently offered at a 75% discount, extended until 2026/05/31 15:59 UTC.

Was this taken into account when reviewing the model?

Keep the pelican but isn’t it time to add something else more novel that all current and past models struggle with?

Even without the currently discounted pricing, the value is incredible.

It takes about twice as long to finish code reviews given an identical context compared to opus 4.7/gpt 5.5 but at 1/10 the cost of less, there's just no comparison.

https://twitter.com/aljosa/status/2049176528638902555

https://www.youtube.com/watch?v=todMmp6AGCE

ChatGPT has really degraded in my eyes, and I find Grok and Deepseek more helpful most of the time.

Of course, ChatGPT is better sometimes.

These models are just better than others at different cases, thus the reason to experiment.

I tried to build something simple and while it got the job done the thinking displayed did not fill me with confidence. It was pages and pages of "actually no", "hang on", "wait that makes no sense". It was like the model was having a breakdown.

Bear in mind open code was also new to me so I could be just seeing thinking where I usually don't

GPT-5 Nano should really be in the list too. It is $0.05 input and $0.40 output - and half that if you use the Flex tier.

Last week I upgraded an old batch process from GPT-4.1 Nano, and GPT-5 Nano worked just as well as GPT-5.4 Nano but at a much lower cost.

As always OpenAIs naming is really bad, GPT-5.4 Nano is a different model, its not a straight upgrade from GPT-5 Nano.

In my tests[0], V4 Flash actually does slightly better and for a lot cheaper than V4 Pro, mostly because it reasons twice as much.

[0]: https://aibenchy.com/compare/deepseek-deepseek-v4-flash-high...

I've used K2.6, GLM5.1, and DSV4 all a good amount. They're all very impressive, but DSV4 has taken the cake.

Open AI has GPT-5.5 Pro which only difference, I think, is in the price. Billing is from open router but the breakdown is roughly

    - GPT 5.5 Pro: Super expensive it makes no sense (cost is around $2)
    - Gemini/Opus: $0.2/$0.1. Opus is cheaper as it consumed less tokens
    - DeepSeek/GLM: $0.019/$0.021 10-5 times cheaper than Gemini and Opus

DeepSeek is a great model, and Cecli is all about efficiency. It works great for my purposes - agentic programming on a budget.

[1] https://www.reuters.com/world/china/openai-accuses-deepseek-...

[2] https://x.com/AnthropicAI/status/2025997928242811253