Guides & Explainers
In-depth written guides on AI concepts, from beginner to advanced
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.
Claude Opus 4.8 Explained: Price, Specs and Legacy Status
Claude Opus 4.8 is a legacy Anthropic model that is still available: $5/$25 per million tokens, 1M context, 128k output, and how it compares with Opus 5.
Gemini 3.1 Pro Explained: Preview Status, Price and Specs
Gemini 3.1 Pro explained: a Google preview model at $2/$12 per million tokens up to 200k, $4/$18 above, 1M input, 65K output, text, image, video and audio.
GPT-5.6 Sol, Terra and Luna Explained: Pricing and Differences
What GPT-5.6 Sol is, and how Sol ($4/$20), Terra ($2/$12) and Luna ($0.20/$1.20) differ: the shared 1.05M context, pricing rules, and how they relate to GPT-6.
Claude Fable 5 Explained: Price, Specs and Parameters
What Claude Fable 5 is, what it costs ($10/$50 per million tokens), whether Anthropic publishes its parameter count, and how it compares with Fable 5.1 and Opus.
How Much Does Claude Opus Cost? Opus 5 and Every Opus Price
Claude Opus 5.5 costs $4/$20 per million tokens and Opus 5 costs $5/$25. Every Opus model's API price, Claude plan prices, and Opus 5's specs and release date.
DeepSeek V4-Flash Explained: Retired, and What Replaced It
DeepSeek retired V4-Flash on 10 September 2026; its name now routes to V4.1-Flash. Current Flash pricing, peak and off-peak hours, and specs.
Nemotron 3.5 Lightning Explained: NVIDIA's 30B Open Model
NVIDIA's Nemotron 3.5 Lightning: 30B parameters with 3B active, runs on one H100 or A100, up to 1M context, open weights under OpenMDW 1.1.
Qwen3.8-Max Explained: 2.4T Parameters, Price and Open Weights
Qwen3.8-Max explained: 2.4T parameters with 95B active, $2/$6 per million tokens on Qwen Cloud, hosted vs open-weight versions, context and licence.
Grok 4.6 Explained: Two-Tier Pricing and Specs
xAI's Grok 4.6 explained: $2/$6 per million tokens, doubling once a prompt reaches 200k tokens, 500k context, image input, and how it compares with 4.5 and 4.7.
Gemini 3.7 Flash Explained: Deprecated, Now Routed to 3.8 Flash
Google deprecated Gemini 3.7 Flash; API requests now route to Gemini 3.8 Flash. What 3.7 Flash was, its specs and launch price, and what applies now.
The Open-Source Software Behind AIblogly
The open-source software that runs AIblogly, from Next.js and React to Prisma, Postgres and Tailwind CSS, with each project's licence and link.
Showing 25–36 of 45 guides