151–160 of 493 posts
Currently burning money quickly on official deepseek api. They are also increasing pricing starting today. V4 Flash 0731 still feels like the most outstanding model of the past few months and probably to come.
What's the new pricing? The prices on OpenRouter still look the same.
but openrouter says they don't expect the price to change other than through the deepseek api, other people hosting the same model will keep charging the same price.
https://api-docs.deepseek.com/quick_start/pricing/ Competitive with opus 4.8 but weaker than sol or fable. About 20x cheaper.
If that wasn't impressive enough, it's actually ~60x cheaper if you take into account the typical cache-read/input/output split in agentic coding, and the deep discount for cache reads offered by DeepSeek. Opencode has some public data on the typical split [1]: For DeepSeek V4 Pro the typical split is 750 in, 290 out, 82k cached. Cost per request for V4 Pro: $0.000875 per request. Equivalent Opus cost (w/o taking int…
ignore the numbers except the classic and keep in mind that classic is based on pi with the only change limiting tool output to 10kb
https://harness.eveid.com/lazy-harness-cost-simulation
* I built this for getting an initial estimate between different checkpoint/ compaction methods for the harness.
Nice bicycle chain, the little basket with a fish didn't show up in the right place: https://tools.simonwillison.net/markdown-svg-renderer#url=ht...
I think I saw a better overall composition out of Flash 0731 Effort on this one?
Wow, the low, medium, and high pelicans came out in surprisingly different styles: https://tools.simonwillison.net/markdown-svg-renderer#url=ht...
Benchmarks: | Benchmark | DS-V4-Pro | DS-V4-Flash | DS-V4-Pro | DS-V4-Flash | GLM-5.2 | Kimi-K3 | Opus-4.8 | Fable 5 | | | 0813 | 0731 | Preview | Preview | | | | (w/ fallback) | |--------------------------|-----------|-------------|-----------|-------------|-----------|-----------|-----------|---------------| | HLE (wo/w tools) | 42.7/60.0 | 37.8/51.5 | 37.7/48.2 | 34.8/45.1 | 40.5/54.7 | 43.5/56.0 | 49.8/57.9 | 53.…
To me it feels like the difference between "RL performance" and the pretraining / base "knowledge".
Yes you can RL terminal bench to the moon but does the model hold up on out of distribution tasks?
Kind of like trying to navigate a dark room with a laser light, vs a flashlight. Laser is going to go a lot farther much more efficiently but only if you are already pointing it at the right place.
Tested both DS v4 pro 0813 and Grok 4.6 (all from openrouter) on Codex cli. Worked on a same new feature development on my project. Deepseek 4 pro: Worked for 12m 02s - cost $0.12 - has bug. Grok 4.6: Worked for 3m 18s - cost $ 1.41 - no bug.
I thought it was impossible to downvote posts?
Just tested through openrouter.. gave exactly same task.. the task was to scan existing repo, and generate a single docker-compose file to deploy behind a caddy server, where certain port ranges are already used, the service demands widlcard certificates to be provisioned from outside, and postgre needs to be built-in one... Tested this model, and gpt-5.6-terra-high. Results: this one had few issues. terra: none. The…
Just tested through openrouter.. gave exactly same task.. the task was to scan existing repo, and generate a single docker-compose file to deploy behind a caddy server, where certain port ranges are already used, the service demands widlcard certificates to be provisioned from outside, and postgre needs to be built-in one... Tested this model, and gpt-5.6-terra-high. Results: this one had few issues. terra: none. The…
Earlier quoted context omitted.
[flagged]
There are still sane people here, we just don't talk about "rocket man" because it enrages the particular subgroup on display here and usually goes no where actually productive (and has like a 50% of getting flagged to death anyways). I'm not pro Elon by any means, but the standard HN profile of him is pretty bat shit crazy.