DeepSeek V4 Pro vs GPT 6.1 Sol
Compare models
DeepSeek V4 Pro is more worth it — 62% vs 41%
How we score worth-it? →Latest DeepSeek — V4.1 with a Flash variant
- Deepseek blazes through work - at quite good quality - and you don't find yourself waiting for your agents to finish... Being able to see the CoT and not being randomly blocked for cyber review.— hn
- Feels better to me in the sense that it doesn't try to be too clever. When I ask it to do things it actually generates code that a developer would write. That still lets me build software in layers like I do mentally. And it keeps you in control of where abstractions are.— hn
- DS flash has been so consistently good I've kinda settled on it for 90% of my work... I genuinely feel as tho if no new models ever get made I'd be fine with just using DS forever.— hn
- I second this, I love DS and am not looking back. For Elixir, not a lot of models are good, but DS just blazes through it.— hn
- I ported some of my childhood Finnish shareware games for Linux and Rust with DeepSeek V4.1 Flash. It took about six hours of spelunking and finally I was pretty happy with the results! I did it twice. Tokens for both of the games were around 3 euros.— hn
- DeepSeek v4.1 Flash hallucinates like crazy.— hn
- Deepseek-v4-pro is 1.6T params, the cut-down version is 284B params, and I wouldn't trust them to do something on their own.— hn
- There's no reason one would choose Deepseek V4 Pro 0813 (max) even though it's in the 'most attractive quadrant', because GLM-5.3-Flash is both cheaper and scores better.— hn
- My biggest annoyance is that DeepSeek does seem to be considerably rate-limited of late — the agent takes 10-20 minutes to do stuff that takes much less time via OpenRouter.— hn
- Same project, same prompt — DeepSeek V4 Pro produced blank output. DS wasted 29.49 yuan in total — a real waste. Without turning on Opus it really can't compete.— v2ex ↗
“Flash hits 300 tokens/sec on real tasks — feels instant”
“Heavy agent use ran only ¥20/day — great value”
“Some devs hit bad lag on the hosted API and gave up on it”
Bills run high on agent tasks
- GPT 6.1 Sol is already the new Terra IMO. Same pricing as old Terra and competitive performance with even Astra on strictly coding-oriented tasks.— hn
- If I were to grade those models from 1-10 (10 = top tier), I'd give deepseek a solid 6.5 and 6.1 sol a 7.5-8.0 maybe.— hn
- GPT 6.1 Sol is an excellent model. It has some weaknesses (frontend design) but also strengths (computer use / control, great for automated E2E QA).— hn
- GPT 6.1 Sol can now beat games 100% vision-only — Pokémon is no longer a difficult challenge, and it beat Final Fantasy VII vision-only surprisingly quickly.— hn
- I genuinely prefer OpenAI models for coding. GPT models are generally better at following the system prompt, tool use, and skill use.— hn
- This wasn't my experience. GPT 6.1 Sol is ~6-7x more expensive for similar intelligence.— hn
- Agent reliability regression: incorrect goal interpretation, prolonged execution, and failure to self-correct.— github
- GPT-6.1 Sol at xhigh regresses in instruction following and task completion.— github
- GPT-6.1 Sol sessions lose coherence, slow down and repeatedly restart the same plan.— github
- Opus 5.5 is an order of magnitude better at design and design nuances than GPT 6.1 Sol, surprisingly.— hn
“The actual value king from OpenAI. Does 90% of what Astra does for way less.”
“Agent tasks are where it shines — cheap enough to run all day without watching the meter.”
“It's not the sharpest on hard reasoning, but for everyday work it's plenty.”
FAQ
Is DeepSeek V4 Pro or GPT 6.1 Sol more worth it?
DeepSeek V4 Pro is more worth it, with a 62% worth-it score vs 41% for GPT 6.1 Sol.
How much does DeepSeek V4 Pro cost vs GPT 6.1 Sol?
DeepSeek V4 Pro: $0.66/$1.98 per 1M (off-peak) · GPT 6.1 Sol: $2/$10 per 1M tokens.
What do users say about DeepSeek V4 Pro vs GPT 6.1 Sol?
DeepSeek V4 Pro: Flash hits 300 tokens/sec on real tasks — feels instant. GPT 6.1 Sol: The actual value king from OpenAI. Does 90% of what Astra does for way less..