So I took Deepseek V4.1 Flash for a spin maybe 2 weeks ago now (before Luna 6 and Sol 6 were announced), and I racked up $100+ in about 2-3 days. It was pretty great, but it uses way more tokens (TPS is fast, but it's way more tokens per turn) than Sol 5.6 which I found to be about it's equivalent at the time (on medium or high, with DS on max). My cache rate was around 98-99%.

It would definitely cost me more per month than a x20 ChatGPT or Claude plan, probably around $400+ was my estimate at the time. This was with Fireworks (ZDR) which has since increased their prices (and got slower!).

That being said, very impressed with the model, and looking forward to what comes next. As the frontier models become less subsidized, the open models will become more appealing.

P.S. There are subscription plans for open models, but I've found most of them to be extremely slow, have model throttling (only so much of model X), and also very sketchy about training and data retention. No thanks! If you want to share your data, just use Muse Spark contributor. Seems impossible to beat that on price per task if you don't mind feeding your data to the Meta machine (spoiler: I won't).

It’s easy to hit your quota. “Speed up the compilation time of this C++ codebase. Feel free to use several subagents to search through the files in parallel.” That’ll cost you about $200 for a codebase of ~1,000 files.

Subagents are like trading derivatives. You can lose as much as you want.

There's a difference between "write this function for me" coding agents and "build this prototype from end-to-end". If you're doing the former, deepseek is fine. If you're doing the latter, it's not gonna work, and that's where the extra intelligence is most valuable.

I spent the weekend trying Deepseek 4 Pro on a Linux porting project and it led me down a complete rabbit hole where Linux wouldn't even boot by the end of the weekend. Waste of $120. Switched back to GPT 6 on Monday and Linux is booting again and I'm making progress.

The only thing I've found Deepseek and Kimi good for are security tasks that GPT refuses to do.

This is a summary of what Deepseek did and got wrong:

Lost the proven baseline: changed kernel source, configuration, compiler, RAM geometry, MMC width, and peripherals together. Matching an upstream commit did not preserve local boot fixes, making failures difficult to isolate. Misidentified an image: a file labelled “r18-known-good” actually contained the r23 parent bootloader. Filename-based reasoning replaced verification of the artifact’s identity and provenance. Shipped inconsistent boot contracts: flash-16b’s loader read too few kernel blocks. Fresh2 changed the device tree without updating the loader’s expected length and CRC, creating deterministic rejection before normal Linux handoff. Patched binaries without maintaining reproducible source: loader constants diverged from source, a separately compiled cache-flush length remained stale, and assembly used an oversized stage-two slot. Their causal contribution to hangs was not established. Overstated diagnosis: claimed failures were definitively in U-Boot, blamed compiler or IPU changes without controlled isolation, converted noisy observations into confirmed hangs, and neglected persistent journals as an alternative explanation. Mistook compilation for integration: framebuffer registration was incomplete, timing success handling was inverted, BT.656 selection was unreachable, encoder overrides were missing, and audio lacked software clock configuration. Misread hardware evidence: asserted interrupt-free PMIC operation, assigned RF to the wrong SPI controller, confused regulator identifiers with register addresses, and described repeated encoder writes as unique registers. Overclaimed results: treated kernel/probe indications as userspace success, presented earlier discoveries as new progress, and omitted failed flashing attempts from the final narrative.

I've been trying to use DeepSeek V4.1 Flash more and been very impressed. My current (very rough) rule of thumb is that an Artificial Analysis score of ~40 is the crossover point for "good enough" for most of the things I need to do with coding agents.

The intelligence difference between models like DS4.1 and Sol/Opus is NOT negligible.

What do you do? I’m 200 bucks deepseek flash in about 2 months and it’s increasing

I use it as main Hermes model that orchestrates codex/droid harnesses with subscriptions for heavy dev work

I do have ChatGPT as main assistant that sets direction and delegation of projects to Hermes

At my increasing usage, kind of 200 usd subscriptions makes sense and max out on Luna max

I've been using Claude Code at work and OpenCode for side projects for a few months. Every OpenCode model I've tried always felt subpar compared to Claude, but good enough. But it changed with DeepSeek 4.1 Flash, I've been using it for the past few days and I've come to forget I was not using Claude, it's a really good model and it's basically free for my usage (I used it almost all the weekend and spent ~$5)

I think the only answer to this is you're just not using agents enough, because even with the very cheap pricing, it's still easy to rack up a large bill.

A lot of people having different pricing experience. I think it’s important to understand that caching can differ, than if the agents spend waiting on code, or consume a lot of content. It depends on how you structure you codebase and how explorable it is, how much effort you set and probably some other issues.

For raw productivity most of what works is best and switching will cost you getting on use parity with other models, as you need to learn what they good at, potentially how the tool works and how to prompt it best.

For tasks that you implement in code, you should have benchmarks and evals.

That said for me was Luna a huge leap and 500+ of cost savings a month

I've spent $200+ on deepseek and this is for making a multiplayer FPS game. Trust me there are use-cases.

And no it did not deliver. A lot of it was re-done by Astra

The speed of deepseek is insane to experience after using claude code with opus for so long. Not only is the tps roughly 3x faster, but the round trip times are magnitudes faster.

A bit tired of spending $200 out-of-pocket for openai. What do you use as harness? (for me the harness if half of the benefit... controlling my PC, working from phone, etc.)

$200/month is for Navier-Stoker grade problem.

You clearly haven’t used opus or astra or only had simple tasks. Such a difference maker

Where do you do your inference?

Are you just using it directly from them?

Kind of ambiguous without saying token amounts and cost.

Opus 5.5.is crazy good. I ask it to do things and it just writes the code to do it.

I just ran a huge text/image extraction grudgematch against all the current inexpensive models except gpt-5.5/5.6/6 (due to some issues with openrouter and bugs in my code) and DS4 ranked very poorly. Accuracy winner was Gemini 3.8 flash with minimax M3 and qwen 3.8 placing, and the chinese models beat the incumbent (Gemini 2.5 Flash) on cost whilst keeping like 95% of the accuracy.

I haven't used deepseek for anything else but the above results make me question its overall capability. Meanwhile qwen3.8 has continued to impress.

API pricing?

It's trivial to hit that kind of quota if you're trying to execute on major projects. Especially as you start having dozens or hundreds of subagents investigating, prototyping, and working on different things.