Skip to main content

6 posts tagged with "LLM"

Articles about large language models

View all tags

The Self-Hosted LLM Gateway Pattern: How Mantis and LiteLLM Turn Model Routing Into a $10 Container
·Dora Noda·13 min

The Self-Hosted LLM Gateway Pattern: How Mantis and LiteLLM Turn Model Routing Into a $10 Container

Self-hosted gateways like Mantis and LiteLLM run model routing, fallback, and cost tracking as a $10 container beside your apps — at 100M tokens the 5.5% managed fee costs 3x more and still routes your prompts through a third party.

self-hosting
PaaS
LLM
AI
+1
Hetzner Is Building an LLM Inference API: What €889/Month of GPU and a Free Experimental Endpoint Do to the Self-Hosted AI Math
·Dora Noda·16 min

Hetzner Is Building an LLM Inference API: What €889/Month of GPU and a Free Experimental Endpoint Do to the Self-Hosted AI Math

Hetzner is testing an OpenAI-compatible inference API alongside its €889/month RTX PRO 6000 GEX131 — what the experiment changes for self-hosted AI rent-vs-own math, EU sovereignty, and running inference as a regular tenant workload.

AI
LLM
self-hosting
infrastructure
+1
OpenCost 1.121 Brings Inference Cost Tracking to Kubernetes: Metering GPU Token Workloads Like Any Other Tenant
·Dora Noda·10 min

OpenCost 1.121 Brings Inference Cost Tracking to Kubernetes: Metering GPU Token Workloads Like Any Other Tenant

OpenCost 1.121 adds per-inference cost metering to Kubernetes, so self-hosters can finally measure dollars per million tokens per tenant. We decompose owned vs leased vs rented GPU vs API costs, find the utilization crossover, and wire vLLM token metrics into a multi-tenant showback report.

Kubernetes
cost-optimization
self-hosting
LLM
+1
Your AI Agent's Debug Loop Costs Grow Quadratically, Not Linearly — Here's the Math
·Dora Noda·8 min

Your AI Agent's Debug Loop Costs Grow Quadratically, Not Linearly — Here's the Math

A 50-step AI agent debug loop bills 26x more than the tool calls it actually made — because every LLM call resends the entire conversation history. Here's the math, the real dollar cost for a deploy-from-chat MCP server, and the fix that actually bounds it.

AI
LLM
PaaS
self-hosting
+1
How LLMs Are Redefining Conversation and Where We Go Next
·Lark Birdy·9 min

How LLMs Are Redefining Conversation and Where We Go Next

Large Language Models (LLMs) like ChatGPT, Gemini, and Claude are transforming industries by powering chat-based tools that enhance education, customer support, productivity, mental health, and e-commerce. Explore the current landscape, identify gaps, and discover opportunities in the evolving world of conversational AI.

AI
LLM
Chatbots
tech-innovation
+1
Negative Feedback on LLM-Powered Storytelling & Roleplay Apps
·Lark Birdy·32 min

Negative Feedback on LLM-Powered Storytelling & Roleplay Apps

Large language model-driven storytelling and roleplay apps like AI Dungeon, Replika, NovelAI, and Character.AI face criticism for technical limitations, ethical concerns, and user experience issues. This article provides a comprehensive overview of common negative feedback, highlighting challenges in narrative coherence, content moderation, and long-term engagement.

AI
LLM
storytelling
roleplay
+2