Guides & Explainers
In-depth written guides on AI concepts, from beginner to advanced
Large Language ModelsOpen-Weight AI Models Explained: Open Weights vs Open Source
What open-weight AI models are, how open weights differ from open source, the licences they use, which models publish their weights, and the hardware they need.
Mixture of Experts (MoE) Explained: How Sparse AI Models Work
What a mixture-of-experts (MoE) model is: experts, the router, total vs active parameters, where MoE came from, and the trade-offs, with real model examples.
How to Compare AI Models: Elo, Benchmarks, Price and Speed
How to compare AI model performance: what LMArena Elo, benchmarks, price per token, context window and speed each measure, with a live side-by-side example.
Gemini 3.8 Live Explained: Google's Real-Time Voice AI
What Gemini 3.8 Live and Live Extended Thinking are, how live voice AI works, where to use them, 97 languages, and the price per minute of audio.
Gemini 4 Argon Explained: Availability, Price and Specs
Gemini 4 Argon is generally available since 13 October 2026. Its price ($2/$10 per 1M tokens, then $4/$20), 1M context window, where to use it, and FAQs.
GPT-6 Astra Explained: Price, Context Window and Specs
GPT-6 Astra explained: OpenAI's first GPT-6 model at $10/$50 per million tokens, 1.05M context, 128K output, April 2026 cutoff, five effort levels.
Claude Fable 5.1 Explained: Price, Cache and Specs
What Claude Fable 5.1 is: $10/$50 per million tokens like Fable 5, cache reads cut to $0.25, 1M context, 128k output, adaptive thinking and effort levels.
Qwen3.7 Max Explained: Price, Context and Specs
Alibaba's Qwen3.7 Max explained: $2.50/$7.50 per million tokens internationally, $1.65/$4.951 in Beijing, 1M context, 131K output, and Qwen3.8 compared.
Muse Spark 1.2 Explained: Meta's Model, Price and Modes
Meta's Muse Spark 1.2 explained: $1.25/$4.25 per million tokens, or $0.10/$0.20 in Contributor mode, 1M context, text, image, video and audio input.
DeepSeek V4-Pro Explained: Peak and Off-Peak Pricing
DeepSeek V4-Pro explained: $1.32/$3.96 per million tokens at peak, half off-peak, when peak hours are, 1M context, 384K output, MIT open weights.
Grok 4.5 Explained: Price, Specs and How It Compares
xAI's Grok 4.5 explained: $2/$6 per million tokens under 200k prompt tokens, double above, 500k context, reasoning efforts, and Grok 4.6 and 4.7 compared.
Claude Sonnet 5: Release Date, Price and Specs Explained
When Claude Sonnet 5 came out, what it costs ($2/$10 per million tokens), its 1M-token context window, and how it compares with Claude Sonnet 5.5.
Showing 1–12 of 24 guides