Загрузка видео...

Не удалось загрузить видео

На главную

Ranking inference providers six ways

69,088 просмотров • 6 дней назад •via X (Twitter)

Комментарии: 23

Фото профиля PrimaLabs
PrimaLabs5 дней назад

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:

Фото профиля Travis
Travis5 дней назад

Check out @telnyx inference 💚

Фото профиля Zhu Liang
Zhu Liang6 дней назад

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

Фото профиля Ben Geller
Ben Geller5 дней назад

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

Фото профиля Mike Henry
Mike Henry5 дней назад

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

Фото профиля 1LittleCoder💻
1LittleCoder💻6 дней назад

awesome! is this from artificial analysis data?

Фото профиля Adam Holter
Adam Holter6 дней назад

Yup, cited in the footnote

Фото профиля 1LittleCoder💻
1LittleCoder💻6 дней назад

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!

Фото профиля Piyush Srivastava
Piyush Srivastava5 дней назад

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

Фото профиля Kol Tregaskes
Kol Tregaskes6 дней назад

Love this animation.

Фото профиля Salman Paracha
Salman Paracha5 дней назад

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

Фото профиля Mortis II
Mortis II5 дней назад

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

Фото профиля Dimitrios Skarlatos
Dimitrios Skarlatos5 дней назад

Great to see @lithos_ai at the top 🚀

Фото профиля Ali Youngblood
Ali Youngblood5 дней назад

i see you @parasail_io 👀 👏

Фото профиля Gunveet Arora
Gunveet Arora5 дней назад

Check us out @telnyx

Фото профиля parth.
parth.5 дней назад

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

Фото профиля Adam McDaniel
Adam McDaniel5 дней назад

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

Фото профиля prasanna
prasanna5 дней назад

Hi 😎

Фото профиля Lawrence W. Abrams
Lawrence W. Abrams5 дней назад

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

Фото профиля harry
harry5 дней назад

👀

Фото профиля Meryem Arik
Meryem Arik5 дней назад

Add @Doubleword_ as well next time!!

Фото профиля Adit Modi
Adit Modi6 дней назад

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 🥹

Фото профиля Pyro
Pyro6 дней назад

TIL Databricks is an inference provider lol

Похожие видео

Introducing Liquid Inference by Architect, a new LLM model router where inference providers compete dynamically to offer lowest-cost tokens. Providers onboard in minutes, not weeks. Buyers have full price visibility and receive 20% of referred fees in free inference. More info: Liquid Inference can be used in place of any OpenAI or Anthropic API-compatible backend. Behind it, our team has leveraged our experience trading and building financial exchanges to create real-time two-sided price discovery for inference. Benefits for buyers and providers: INFERENCE BUYERS • Fully compatible with agentic coding tools: Claude Code, Codex, OpenCode, Cursor, Pi, Cline, and many more. Full multi-modal support. • Hundreds of open- and closed-weight models. Create routing rule presets or use our Auto routing algorithms. • Providers compete dynamically on price for every prompt, offering the lowest marginal cost. • Sign up for free with email, first 500 users get $20 of free inference. • Receive 20% of referred fees as free inference, 10% for second-level referrals. INFERENCE PROVIDERS • Onboard through the Liquid Inference app. We verify new providers in minutes, not weeks. • All prompts are OpenAI API standard. Simple REST/Websocket API to register models and quotes. • Update quotes dynamically based on your own costs. Monetize GPU capacity only when you want. • Standardize payouts via Stripe, full itemized records of all jobs performed.

Brett Harrison

39,450 просмотров • 1 месяц назад