cloud.killer social

#llm

In the cloud.killer community.

Members can post here. Sign in with pit.world: the one account for every *.pit.world site.

@tokenmargin.dev network
3/ Run your own workload parameters & interactive FinOps stress test in our full engineering guide:
https://tokenmargin.dev/guides/openrouter-openai-anthropic-csv-bill-analyzer.html?ref=bsky #AI #LLM #FinOps #DevTools #BuildInPublic
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app · a reply
@gp-pulipaka.bsky.social network
Generative AI At AWS: Turn Business Strategy Into Production-Ready AI Applications And Agent! #BigData #Analytics #DataScience #AI #MachineLearning #NLProc #LLM #IoT #IIoT #PyTorch #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #GoLang #CloudComputing #Serverless #DataScientist #Linux
1 image (open on the network to see)
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app
@tokenmargin.dev network
3/ Run your own workload parameters & interactive FinOps stress test in our full engineering guide:
https://tokenmargin.dev/guides/aws-bedrock-vs-openrouter-vs-direct-api-pricing-comparison.html?ref=bsky #AI #LLM #FinOps #DevTools #BuildInPublic
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app · a reply
@tokenmargin.dev network
AWS Bedrock vs OpenRouter vs Direct Anthropic/OpenAI API Pricing

Compare enterprise cloud markups, cross-region inference pricing, and serverless open-weight host arbitrage between AWS Bedrock, Google Vertex AI, OpenRouter, and DeepInfra. 🧵👇

#AI #LLM #DevTools #SaaS #BuildInPublic
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app
@tokenmargin.dev network
3/ Run your own workload parameters & interactive FinOps stress test in our full engineering guide:
https://tokenmargin.dev/guides/deepseek-r1-reasoning-model-cloud-pricing-cheapest-providers-2026.html?ref=bsky #AI #LLM #FinOps #DevTools #BuildInPublic
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app · a reply
@tokenmargin.dev network
DeepSeek R1 Reasoning Model Cloud Pricing & Cheapest Providers

Complete 2026 cloud pricing and cheapest provider benchmark for DeepSeek R1 (671B MoE) and DeepSeek R1 Distill (70B/32B) across DeepInfra, Fireworks AI, Together AI, Groq, OpenRouter, and RunPod dedicated GPUs. 🧵👇

#AI #LLM #DevToo...
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app
@galloni.net network
What it means for AI Search is more nuanced. #AI #LLM #AgenticAI #SEO

https://netcontentseo.com/article/amazon-introduces-hope-why-preserving-ai-expert-teams-matters-for-smaller-more-capable-agents-1543 (2/2)
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app
@privum.bsky.social network
Cheapest GPU rentals today (2026-11-10), by VRAM:
32GB Tesla V100 $0.069/h (Vast.ai)
48GB RTX A6000 $0.330/h (RunPod)

RTX 4070S Ti ▲115% vs yesterday, now $0.203/h
RTX A4500 ▲74% vs yesterday, now $0.190/h

All chips, 90-day history: https://overfeed.news/gpus
#GPU #AI #LLM
1 image (open on the network to see)
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app
@neubench.bsky.social network
Claude Fable 5.2 hitting 65 on Artificial Analysis sets a new frontier, but let's see how it holds up against real-world prompt routing variance and token latency under load.

Benchmarks: https://app.neubench.workers.dev

#AI #MachineEngineering #LLM
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app
@tokenmargin.dev network
3/ Run your own DAU, prompt cache hit rate (0-95%), and LiteLLM fallback router simulation on our live comparison page:
https://tokenmargin.dev/compare/gpt-4-1-mini-vs-deepseek-chat-v3-0324.html?ref=bsky #AI #LLM #FinOps #DevTools #BuildInPublic
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app · a reply
@tokenmargin.dev network
GPT-4.1 Mini (75% Cache Discount) vs DeepSeek V3 (0324): Which LLM API actually protects your SaaS gross margin at 10,000 DAU?

Here is the live 2026 token math across input, output & prompt caching: 🧵👇

#AI #LLM #DevTools #SaaS #BuildInPublic
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app
@trynoguard.bsky.social network
Big AI labs sell "safety" as a feature, but it's often just a layer of corporate refusals. Stop guessing what makes a model really uncensored. We break down the difference between hard limits and hidden filters. #AI #LLM

https://aethersky.ai/learn/ai-with-no-restrictions-what-uncensored-means
1 image (open on the network to see)
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app
@senryuichi.bsky.social network
（Twitter/X本日のニュース）
ローカルLLM議論：コスト高とプライバシー重視の声

コードとか書かなくても、用意しといていいと思うけどね。安心感が違うよね、プライバシー方面の。結局オンラインで使うけどね、たいていは。使い分けは大事だね、いろいろ考えて。 #LLM #AI #ローカルLLM
1 image (open on the network to see)
From the AT Protocol network, via jetstream2.us-east.bsky.network, atproto.africa, jetstream1.us-west.bsky.network · view on bsky.app
@tokenmargin.dev network
3/ Run your own DAU, prompt cache hit rate (0-95%), and LiteLLM fallback router simulation on our live comparison page:
https://tokenmargin.dev/compare/gpt-4-1-vs-gemini-2-5-pro.html?ref=bsky #AI #LLM #FinOps #DevTools #BuildInPublic
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app · a reply
@tokenmargin.dev network
GPT-4.1 (1M Context Frontier) vs Gemini 2.5 Pro: Which LLM API actually protects your SaaS gross margin at 10,000 DAU?

Here is the live 2026 token math across input, output & prompt caching: 🧵👇

#AI #LLM #DevTools #SaaS #BuildInPublic
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app
@vinpatel.bsky.social network
The AI bubble debate is the wrong question for builders.

What breaks in your stack if valuations fall?

Hacker News isn't convinced the bubble exists — but conviction about valuations won't save your infrastructure dependencies.

Build like the floor might drop.

#AI #LLM
Capability: Is the AI Bubble Real? What Builders Should Watch Instead vinpatel.com
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app
@tokenmargin.dev network
3/ Run your own DAU, prompt cache hit rate (0-95%), and LiteLLM fallback router simulation on our live comparison page:
https://tokenmargin.dev/compare/claude-3-5-haiku-vs-gpt-4o-mini.html?ref=bsky #AI #LLM #FinOps #DevTools #BuildInPublic
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app · a reply
@tokenmargin.dev network
Claude 3.5 Haiku vs GPT-4o Mini: Which LLM API actually protects your SaaS gross margin at 10,000 DAU?

Here is the live 2026 token math across input, output & prompt caching: 🧵👇

#AI #LLM #DevTools #SaaS #BuildInPublic
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app
@tokenmargin.dev network
3/ Run your own DAU, prompt cache hit rate (0-95%), and LiteLLM fallback router simulation on our live comparison page:
https://tokenmargin.dev/compare/gpt-4-1-vs-deepseek-chat-v3-0324.html?ref=bsky #AI #LLM #FinOps #DevTools #BuildInPublic
From the AT Protocol network, via atproto.africa, jetstream1.us-west.bsky.network, jetstream2.us-east.bsky.network · view on bsky.app · a reply
@tokenmargin.dev network
GPT-4.1 (1M Context Frontier) vs DeepSeek V3 (0324): Which LLM API actually protects your SaaS gross margin at 10,000 DAU?

Here is the live 2026 token math across input, output & prompt caching: 🧵👇

#AI #LLM #DevTools #SaaS #BuildInPublic
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app
@ikezisan.bsky.social network
ぶっちゃけ、AIで資料作成の下準備したら30分以上節約できたかも。正直、もう手放せないツールですよねこれ。

Honestly, AI helped me prep documents faster and saved over 30 minutes. It's becoming an indispensable tool, for real.

#AI #AIBot #AI自動化 #ChatGPT #LLM #生成AI #Automation #Productivity #Bluesky #時短
1 image (open on the network to see)
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app
@tokenmargin.dev network
3/ Run your own DAU, prompt cache hit rate (0-95%), and LiteLLM fallback router simulation on our live comparison page:
https://tokenmargin.dev/compare/deepseek-r1-distill-llama-70b-vs-o3-mini.html?ref=bsky #AI #LLM #FinOps #DevTools #BuildInPublic
From the AT Protocol network, via atproto.africa, jetstream2.us-east.bsky.network, jetstream1.us-west.bsky.network · view on bsky.app · a reply

Older