Top all-time · #7379
Portkey Blog
Company blog · portkey.ai/blog · on HN as roh26itai
Portkey Blog is the company blog at portkey.ai, writing about ai. Since 2023, 11 different Hacker News readers have linked it 30 times, most often “Reducing LLM Costs and Latency with Semantic Cache”. It is still writing: the last post was on 2026-06-28, and you can follow it by feed.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
Linked for a post on cutting LLM costs and latency with semantic caching, cited as a comparison to GPTCache in a Show HN thread. Also linked as the homepage for an open source LLM log router.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Democratize and productionize Gen AI across your entire org with Portkey's suite of AI gateway, observability, guardrails, and prompt management modules.
Most-linked posts?
- Reducing LLM Costs and Latency with Semantic Cache3 people · 5 mentions · first linked 2023-07-11
- LLM Obervability Platform3 people · 4 mentions · first linked 2023-08-01
- Implementing FrugalGPT: Reducing LLM Costs and Improving Performance2 people · 3 mentions · first linked 2024-04-27
- Decoding OpenAI Evals Framework2 people · 2 mentions · first linked 2023-05-10
- Deep Dive: OpenAI's O1 – The Dawn of Deliberate AI2 people · 2 mentions · first linked 2024-12-09
- GPT-4 is Getting Faster2 people · 2 mentions · first linked 2023-10-17
What Hacker News says?
Thank you! We have built out the cache system -- we do both simple caching (matching the request strings 100%) and also do semantic caching (returning a cache hit for semantically similar requests). More here - https://portkey.ai/docs/product/ai-gateway-streamline-llm-in... The caching part isn't open source yet, but part of our internal workers. Would be very cool to open source it!
Comment linking /docs/product/ai-gateway-streamline-llm-integrations/cache-simple-and-semantic
on “Show HN: A lightweight AI gateway to 100+ models, in TS”Submitted Portkey launches LLM analytics suite for AI builders as a story · 7 points
HN discussionLooks great, do you have any concrete data how much money it will save ? Also, how does it compare to for example GptCache[0] ? or any other semantic cache solution[1] ? [0] https://gptcache.readthedocs.io/en/latest/ [1] https://portkey.ai/blog/reducing-llm-costs-and-latency-seman...
Comment linking /blog/reducing-llm-costs-and-latency-semantic-cache/
on “Show HN: Reduce ChatGPT costs 10x with distributed cache for LLMs”Submitted LLM Obervability Platform as a story · 6 points
HN discussionhttps://portkey.ai/
Comment linking /
on “Segment for LLM Traces? Seeking Feedback on an Open Source LLM Log Router”Submitted We analysed 4B requests on our AI Gateway as a story · 5 points
HN discussionHere's a mega guide on keeping costs low with LLMs - https://portkey.ai/blog/implementing-frugalgpt-smarter-llm-u... tl;dr: - Keep prompts short, combine prompts or make more detailed prompts but go to a smaller model - Simple and semantic cache lookups - Classify tasks and route to the best LLM using an AI gateway Portkey.ai could help with a lot of this
Comment linking /blog/implementing-frugalgpt-smarter-llm-usage-for-lower-costs/
on “Ask HN: Devs using LLMs, how are you keeping costs low for LLM calls locally?”Submitted Implementing FrugalGPT: Reducing LLM Costs and Improving Performance as a story · 5 points
HN discussionhttps://portkey.ai/ - is also a nice addition to the list
Comment linking /
on “Open-source tools for LLM monitoring and observability”Submitted Everything we know about Claude Code Limits as a story · 4 points
HN discussionthank you! we don't have a strong Evals module within our Prompt Studio at the moment. So there's no straightforward way to do that. however, we do have one of the better modules for applying guardrails on live AI traffic and setting up routing based on guardrail verdicts: https://portkey.ai/features/guardrails
Comment linking /features/guardrails
on “Show HN: Prompt Engineering Studio – Toolkit for deploying AI prompts at scale”Submitted Reducing LLM Costs and Latency with Semantic Cache as a story · 3 points
HN discussionhelping build https://portkey.ai/ where we try to take care of storing all prompts, responses, erros, costs, latencies etc and make it available to debug.
Comment linking /
on “Ask HN: How are you improving your use of LLMs in production?”Submitted LLM pricing is 100x Harder than you think as a story · 2 points
HN discussionSubmitted Deep Dive: OpenAI's O1 – The Dawn of Deliberate AI as a story · 2 points
HN discussionSubmitted Implementing FrugalGPT in Production as a story · 2 points
HN discussionSubmitted OpenAI Model Deprecation Guide – GPT3 is shutting down as a story · 2 points
HN discussionSubmitted GPT-4 is Getting Faster as a story · 2 points
HN discussionSubmitted Agent Identity: Why Every Agent Vulnerability Is a Trust Boundary Failure as a story · 1 points
HN discussionSubmitted Why do you need an MCP Gateway? as a story · 1 points
HN discussionSubmitted Come down a rabbit hole with OpenAI o1 system card as a story · 1 points
HN discussionSubmitted My Journey with AI-Driven Development as a story · 1 points
HN discussionSubmitted Show HN: Anyscale Inference and Portkey Ops as a story · 1 points
HN discussionSubmitted OpenAI DevDay's Implications for LLM Apps in Prod as a story · 1 points
HN discussionSubmitted GPT-4 is Getting Faster as a story · 1 points
HN discussionSubmitted Reducing LLM Costs and Latency with Semantic Cache as a story · 1 points
HN discussionSubmitted Neat implementation of semantic cache for GPT4 as a story · 1 points
HN discussionSubmitted Implementing Semantic Cache to Reduce LLM Cost and Latency as a story · 1 points
HN discussionSubmitted Decoding OpenAI Evals as a story · 1 points
HN discussionSubmitted Decoding OpenAI Evals Framework as a story · 1 points
HN discussion