AI Made Tools
The engineering platform for building, deploying, securing, and operating AI applications.
Build beyond the prototype
AI engineering, end to end
Start with the system layer you need to decide or improve.
🧠 AI Models
Chinese and Western models, ranked and compared.
DeepSeek API Authentication Fix: API Key and Billing Issues
Fix DeepSeek API authentication errors. Covers API key setup, billing issues, and account …
DeepSeek API Rate Limit Fix: Managing Request Quotas
Fix DeepSeek rate limit errors. Covers API quotas, retry strategies, and cost optimization…
Ornith 1.5 35B-A3B: Specs, Benchmarks and How to Run It Locally
Ornith 1.5 is a 35B MoE coding and agent model with about 3B active parameters, 262K conte…
GPT-6 Astra Explained: API Pricing, Context, Computer Use & Availability
GPT-6 Astra has 1.05M context, 128K output, built-in agent tools and $10/$50 API pricing. …
GPT-6 Astra vs GPT-5.6 Sol: Pricing, Tools and the Right OpenAI Model
Compare GPT-6 Astra and GPT-5.6 Sol on price, context, agent tools, reasoning and availabi…
AI Dev Weekly #24: Gemini 3.8 Flash Goes GA, Fable 5.1 Cuts Agent Cache Costs, Agent Plugins 1.0 Ships
Week of Aug 28-Sep 3: Gemini 3.8 Flash reaches production, Claude Fable 5.1 changes agent …
🤖 Coding Agents & AI IDEs
Claude Code, Cursor, Aider, Codex CLI, and more.
GPT-6 Astra Explained: API Pricing, Context, Computer Use & Availability
GPT-6 Astra has 1.05M context, 128K output, built-in agent tools and $10/$50 API pricing. …
GPT-6 Astra vs GPT-5.6 Sol: Pricing, Tools and the Right OpenAI Model
Compare GPT-6 Astra and GPT-5.6 Sol on price, context, agent tools, reasoning and availabi…
Gemini 3.8 Flash Explained: Pricing, Context, Coding and API Changes
Gemini 3.8 Flash is Google's GA model for coding and agents. Compare its 1M context, 64K o…
Gemini 3.8 Flash vs Claude Fable 5.1: Coding, Agents and API Cost
Compare Gemini 3.8 Flash and Claude Fable 5.1 for coding agents, multimodal workflows, con…
Claude Fable 5.1 Explained: Specs, Pricing, Context and Coding
Claude Fable 5.1 has a 1M context window, 128K output, adaptive thinking, and $10/$50 API …
Claude Code Installation Failed Fix: Node.js and npm Issues
Fix Claude Code installation failures. Covers Node.js version, npm permissions, and depend…
💻 Local AI
Ollama, vLLM, and self-hosted model guides.
K2 Horizon Explained: Six Open Models From 0.9B to 375B
K2 Horizon spans six Apache-2.0 models from 0.9B dense to 375B-A23B MoE. Compare sizes, op…
Build a Local AI Regex Generator — Describe It, Get Regex
Stop struggling with regex. Describe what you want in plain English and get working regula…
IBM Granite 4.2 8B Guide: Reasoning, 128K Context and Local Deployment
Granite 4.2 8B is IBM's Apache-2.0 dense reasoning model with 128K context, tool calling, …
Ornith 1.5 35B-A3B: Specs, Benchmarks and How to Run It Locally
Ornith 1.5 is a 35B MoE coding and agent model with about 3B active parameters, 262K conte…
I Used LM Studio for a Week — The Most Popular Local Model Runner
Week 22 of my AI tool series. LM Studio runs AI models locally on your machine. After a we…
Gemini 3.5 Transcribe vs Whisper: Cloud or Local Speech-to-Text?
Compare Gemini 3.5 Transcribe with local Whisper for recorded audio, live voice agents, pr…
💰 APIs & Pricing
Compare API costs and find the cheapest capable model.
GPT-6 Astra Explained: API Pricing, Context, Computer Use & Availability
GPT-6 Astra has 1.05M context, 128K output, built-in agent tools and $10/$50 API pricing. …
GPT-6 Astra vs GPT-5.6 Sol: Pricing, Tools and the Right OpenAI Model
Compare GPT-6 Astra and GPT-5.6 Sol on price, context, agent tools, reasoning and availabi…
AI Dev Weekly #24: Gemini 3.8 Flash Goes GA, Fable 5.1 Cuts Agent Cache Costs, Agent Plugins 1.0 Ships
Week of Aug 28-Sep 3: Gemini 3.8 Flash reaches production, Claude Fable 5.1 changes agent …
Gemini 3.8 Flash Explained: Pricing, Context, Coding and API Changes
Gemini 3.8 Flash is Google's GA model for coding and agents. Compare its 1M context, 64K o…
Gemini 3.8 Flash vs Claude Fable 5.1: Coding, Agents and API Cost
Compare Gemini 3.8 Flash and Claude Fable 5.1 for coding agents, multimodal workflows, con…
Claude Fable 5.1 Explained: Specs, Pricing, Context and Coding
Claude Fable 5.1 has a 1M context window, 128K output, adaptive thinking, and $10/$50 API …
📝 Latest Articles
DeepSeek API Authentication Fix: API Key and Billing Issues (2026)
Fix DeepSeek API authentication errors. Covers API key setup, billing issues, and account problems.…
I Used Langfuse for a Week — Open-Source LLM Observability
Week 23 of my AI tool series. Langfuse is an open-source LLM observability platform. After a week, here's why it matters…
GPT-6 Astra Explained: API Pricing, Context, Computer Use & Availability
GPT-6 Astra has 1.05M context, 128K output, built-in agent tools and $10/$50 API pricing. Here is what is available duri…
GPT-6 Astra vs GPT-5.6 Sol: Pricing, Tools and the Right OpenAI Model
Compare GPT-6 Astra and GPT-5.6 Sol on price, context, agent tools, reasoning and availability to choose the right OpenA…
K2 Horizon Explained: Six Open Models From 0.9B to 375B
K2 Horizon spans six Apache-2.0 models from 0.9B dense to 375B-A23B MoE. Compare sizes, openness, context and deployment…
AI Dev Weekly #24: Gemini 3.8 Flash Goes GA, Fable 5.1 Cuts Agent Cache Costs, Agent Plugins 1.0 Ships
Week of Aug 28-Sep 3: Gemini 3.8 Flash reaches production, Claude Fable 5.1 changes agent economics, Agent Plugins 1.0 s…