24 articles
Caching a shared prompt cut our worked example by about 78-80% on four models; batch takes 50% off at most providers but 40% at Moonshot and 20% at xAI. Only Anthropic, Fireworks and xAI say the two stack. The math, the assumptions and the quotes.
Free tiers are where training happens: Google's unpaid quota outside the EEA, Switzerland and the UK, Mistral's Free mode, and some OpenRouter free models. Paid APIs mostly say no. Retention is a separate question, and four providers' own docs disagree with themselves.
Claude Fable 5.1 keeps $10/$50 pricing but cuts cache reads to $0.25/MTok. The three breaking API changes, new betas, and when Opus 5.5 is enough.
GPT Image 2.5 Sunburst and Flare add xhigh and max quality at GPT Image 2 token rates. Model IDs, type-checked code, costs and when to pick each.
OpenAI shuts down whisper-1 and the gpt-4o transcribe models on Feb 26, 2027. Move files to gpt-transcribe ($0.0045/min) and live audio to gpt-live-transcribe.
OpenCode server on Railway: run opencode serve in a container as a password-protected HTTP API with a persistent volume, reachable from any machine or webhook.
Automate video editing with the Descript API: one script takes a raw recording to a cleaned, captioned, published cut without opening the editor.
GitHub Apps can now be installed at the enterprise level, opening enterprise management to third-party integrators, with a security boundary on top permissions.
AI session portability compared across OpenAI, Anthropic, and Gemini: storage defaults, encrypted reasoning, compaction, and what you can move or audit.
GitHub Models is retired as of July 30, 2026 - the playground, inference API and BYOK are gone. The shutdown timeline and where to get model access now.
AI API token relays resell OpenAI, Anthropic, and Google access at up to 97.8% off. How the gray market works and what it means for developers on AI APIs.
Meta Muse Spark 1.1 developer guide: Meta's first paid model API, with 1M-token context, OpenAI-compatible endpoints, pricing and setup for agentic tasks.
Google's Gemini 3.5 Pro arrives with a 2-million-token context window and Deep Think reasoning mode. Here is how to access it, what it costs, and when the massive context actually helps.
Showing 12 of 23 articles
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
Explore 844 topics
Browse All Topics