Загрузка видео...
Не удалось загрузить видео
Ranking inference providers six ways
69,088 просмотров • 6 дней назад •via X (Twitter)
Комментарии: 23

Thanks for the shoutout, @AdamHoltererer Great to see PrimaLabs in S-tier for accuracy. We’re also now #1 for Kimi K3.1 Pro cost per task on Artificial Analysis. Excited to keep pushing on performance and value. AA benchmark:

Check out @telnyx inference 💚

i’m sad that humans don’t live in a 6-dimensional space. this is very hard to visualize all at once.

Fantastic animation. Love to see @parasail_io in the top tier across the board.

Love it @AdamHoltererer ! pumped we’re in the top tier

awesome! is this from artificial analysis data?

Yup, cited in the footnote

at @nebiustf we've been getting day 0 launch for most of the recent ones, so was surprisd that's why wanted to validate. I'll check the data!

Thanks for the analysis @AdamHoltererer It takes extreme hardware-software co-design and distributed systems engineering to be top notch on price/perf and price/quality frontiers. We have been laser focused on this @digitalocean and this will only continue to improve! cc @paddix @jenukal

Love this animation.

Great visuals but what really matters is agentx/inferencex bench from @dylan522p and the @SemiAnalysis_ team. You can’t index on any one dimension. Throughput over interactivity is the only true metric for performance

Crusoe and TogetherAI should be an S tier on all metrics.

Great to see @lithos_ai at the top 🚀

i see you @parasail_io 👀 👏

Check us out @telnyx

What did you not like about GMI Cloud? How can it move to A-S ?

digging the way you broke down by segment. thx for sharing.

Hi 😎

How about stack depth as a criteria? New stacks being added every month - e.g sandbox deployment, post-training data marketplace? Also name “inference providers” now obsolete given depth of stack. My name - MCMaaS - Model Creator and Manager as a Service. Based on full stack criteria, @baseten clear leader

👀

Add @Doubleword_ as well next time!!

for Model served, AWS is in D Tier, I always thought AWS gave more options when it came to serving open source models, but maybe I am wrong and there are better options 🥹

TIL Databricks is an inference provider lol


