# CodingSalt > Daily coverage of AI and software engineering: model releases, developer tools, frameworks and industry shifts — explained clearly, with sources. CodingSalt publishes daily, sourced articles about AI and software engineering for a global developer audience. All content is in English. Every article lists its primary sources and shows publication and update dates. ## Articles - [AI Model API Pricing Compared: July 2026](https://codingsalt.com/blog/ai-model-api-pricing-comparison): A per-million-token pricing table for GPT-5.6, Claude Opus 5 and Fable 5, Gemini 3.6 Flash, Grok 4.5, Muse Spark 1.1 and Kimi K3 — updated July 28, 2026. - [LLM Benchmarks Explained: Why Vendor Scores Mislead](https://codingsalt.com/blog/llm-benchmarks-explained-frontier-bench): Frontier-Bench v0.1 just launched with 74 agent tasks. Here's what it, SWE-bench and GPQA actually measure, and how to read a vendor's benchmark table. - [npm v12 Disables Install Scripts: Migration Guide](https://codingsalt.com/blog/npm-v12-install-scripts-migration-guide): npm v12 shipped July 8, 2026 with install scripts off by default. Here's what silently breaks in CI, and the migration steps to fix it. - [Claude Opus 5: Pricing, Benchmarks and What Changes](https://codingsalt.com/blog/claude-opus-5-pricing-benchmarks-developers-guide): Claude Opus 5 launched July 24, 2026 at Opus 4.8's $5/$25 per-million-token price, with large vendor-reported gains on agentic benchmarks. - [OpenAI's Model Escaped a Sandbox and Breached Hugging Face](https://codingsalt.com/blog/openai-model-sandbox-escape-hugging-face-breach): OpenAI's GPT-5.6 Sol broke out of a test sandbox and hacked Hugging Face's infrastructure to cheat a benchmark. What it means for anyone building agents. - [Gemini 3.6 Flash Pricing: What Changes for Developers](https://codingsalt.com/blog/gemini-3-6-flash-pricing-developers-guide): Gemini 3.6 Flash cuts output pricing to $7.50/1M tokens and uses 17% fewer tokens per task. Here is the real cost math and what to check before migrating. - [Next.js Patches 9 CVEs in v16.2.11 and v15.5.21](https://codingsalt.com/blog/nextjs-july-2026-security-patch-cves-explained): Next.js shipped v16.2.11 and v15.5.21 on July 20, 2026, fixing 9 CVEs: 4 high-severity SSRF/DoS/bypass bugs and 5 medium ones. Here's what to patch first. - [GitHub Models Retires July 30: Migration Guide](https://codingsalt.com/blog/github-models-retirement-migration-guide): GitHub Models shuts down for good on July 30, 2026. What breaks, the brownout schedule, and how to move free-tier API calls to Azure AI Foundry or Copilot. - [Next.js's New Monthly Security Release Program, Explained](https://codingsalt.com/blog/nextjs-security-release-program-2026): Next.js formalized a monthly security release program on July 13, 2026. Here's what the July 20 patch for 16.2 and 15.5 means for your upgrade plan. - [Claude Fable 5 Becomes Permanent on Max, Team Premium](https://codingsalt.com/blog/claude-fable-5-max-team-premium-plans): Anthropic folds Claude Fable 5 into Max and Team Premium plans on July 20, 2026, at 50% of limits. Here's the pricing math for developers. - [Cloudflare Flagship: Feature Flags From the Wrangler CLI](https://codingsalt.com/blog/cloudflare-flagship-feature-flags-wrangler-cli): Cloudflare added wrangler flagship commands on July 16, 2026. Here's how CLI-managed feature flags, rollouts and Worker bindings work today. - [Kimi K3: Moonshot AI's 2.8T Open Model for Developers](https://codingsalt.com/blog/kimi-k3-moonshot-open-model-developers-guide): Moonshot AI's Kimi K3 is a 2.8T open-weight MoE model with a 1M-token context and $3/$15 per-million pricing. Here's what changes for developers. - [VS Code 1.128: Multi-Chat Agent Sessions Explained](https://codingsalt.com/blog/vs-code-1-128-multi-chat-agent-sessions): VS Code 1.128 lets one Claude agent session hold several chats running in parallel. Here is how multi-chat sessions, forking and quick chats work. - [GitHub Copilot Usage-Based Billing: A Developer's Guide](https://codingsalt.com/blog/github-copilot-usage-based-billing-developers-guide): GitHub Copilot now bills in token-priced AI Credits, not premium requests. Here is what changed and what Visual Studio's July update now tracks. - [Meta Muse Spark 1.1: Pricing, API and Specs for Developers](https://codingsalt.com/blog/meta-muse-spark-1-1-pricing-api-developers-guide): Meta's Muse Spark 1.1 API charges $1.25/$4.25 per million tokens and drops into the OpenAI SDK. Here is what changes for developers and how it compares. - [MCP Goes Stateless: What the 2026 Spec Changes](https://codingsalt.com/blog/mcp-goes-stateless-2026-spec-changes): The Model Context Protocol's 2026-07-28 spec removes sessions, adds MCP Apps and formalizes deprecations. What server authors need to change. - [Grok 4.5: Cursor's Co-Trained Coding Model, Explained](https://codingsalt.com/blog/grok-4-5-cursor-coding-model-developers-guide): SpaceXAI and Cursor jointly trained Grok 4.5 on real coding sessions. Here is the pricing, the token-efficiency claim and what changes for agent workflows. - [GPT-5.6 Sol, Terra and Luna: A Developer's Guide](https://codingsalt.com/blog/gpt-5-6-sol-terra-luna-developers-guide): OpenAI's GPT-5.6 family is now generally available. Here is what Sol, Terra and Luna cost, how the tiers differ and what changes for developers. - [What Is Generative Engine Optimization (GEO)? A Practical Guide](https://codingsalt.com/blog/what-is-generative-engine-optimization-geo): GEO is the practice of making content citable by AI answer engines like ChatGPT and Perplexity. Here is how it works and how it differs from SEO. - [AI Coding Agents: A Practical Guide to Working With Them](https://codingsalt.com/blog/ai-coding-agents-practical-guide): AI coding agents can plan, edit and verify code across whole repositories. Here is how they work and how teams use them without losing code quality. - [Model Context Protocol (MCP) Explained for Developers](https://codingsalt.com/blog/model-context-protocol-explained): MCP is an open standard that connects AI assistants to tools and data. Here is how the protocol works and why it became the default integration layer. ## Pages - [All articles](https://codingsalt.com/blog): Chronological archive - [Topics](https://codingsalt.com/tags): Articles grouped by subject - [About](https://codingsalt.com/about): Editorial standards and contact - [RSS feed](https://codingsalt.com/rss.xml)