14 engineers on Hacker News describe using Mistral first-hand: 6 endorse it, 3 regret it, 2 are mixed.
“But Mistrals models are certainly "good enough". Good enough is good, too.”
endorse · personal · 0.7 yr · berkes · 2026-10-29 · source ↗ · wrong label?“Mistral has been great for us as a provider for our EU-based company. We use Mistral Large 4 ... through their API”
endorse · production · d2kx · 2026-10-29 · source ↗ · wrong label?“I've been using it for my personal project and it's still too expensive and very slow when thinking.”
regret · personal · almindor · 2026-10-29 · source ↗ · wrong label?“Price/speed/quality ratio was the best I could find. ... it is really good. I've replaced a lot of my browser-based-chat-ui-llm-usage with mistral”
endorse · personal · barrell · 2026-10-20 · source ↗ · wrong label?“Some days it's quite fast, some days it's so slow I interrupt it because I thought it was hanging.”
mixed · personal · sspiff · 2026-10-19 · source ↗ · wrong label?“I've been using Mistral 4 as well, but from OMP with a Vibe subscription. ... It's slow as hell”
regret · personal · nozzlegear · 2026-10-19 · source ↗ · wrong label?“after being disappointed that the Pro tier was opt-in to training on prompts by default we switched up to the Team tier”
regret · production · teekert · 2026-09-02 · source ↗ · wrong label?“btw we're getting pretty good results with mistral!”
endorse · production · downsplat · 2025-12-11 · source ↗ · wrong label?“They are incredibly fast and cost-effective for specific, repetitive tasks.”
endorse · production · PaulShin · 2025-06-09 · source ↗ · wrong label?“Direct model upgrade led to significant quality degradation”
mixed · production · Jet_Xu · 2024-11-28 · source ↗ · wrong label?“I've been using Mistral 7B on my M1 and I thought it was tolerable but turned out I wasnt utilizing Metal and now its amazing”
endorse · personal · yieldcrv · 2023-12-19 · source ↗ · wrong label?“I've only tested the three US labs and Mistral.”
neutral · personal · urbsgpw · 2026-07-21 · source ↗ · wrong label?“Mistral 7B has a context window of 32k. I use it in production for medical summarization tasks”
neutral · production · pilotneko · 2024-12-31 · source ↗ · wrong label?“over our previous use of Mistral/Claude/OpenAI”
neutral · production · ivorbuk · 2024-09-24 · source ↗ · wrong label?