DEVELOPER GUIDE

Claude Models on Google Cloud (Anthropic managed) is the full Claude API behind Google Cloud IAM and billing. Setup, the 2 services, IAM roles and SDK code.

Claude API version 2026-10-21 removes temperature, top_p and top_k, and new major SDKs (TypeScript 1.0, Python 2.0) send it by default. What breaks and how to migrate.

Claude Code Review now has three review levels. How Quick, Standard and Deep trade depth for cost, how to set them per repo, and how to budget before rollout.

Claude Inference hooks left beta for Enterprise on Oct 20. How the prompt and tool call frames work, how to verify signatures, and a TypeScript verdict server.

GPT-Live can now call the Decisions API itself, mid-sentence. How native delegation and transcript triggers work, the session config, and the events to handle.

Claude API inline tools beta: define, reshape or upgrade a tool mid-conversation with one system message and keep the prompt cache. Code included.

The Claude API exports OpenTelemetry traces in beta. Set up SDK spans in TypeScript or Python, add a Console destination for API spans, and count tokens once.

Claude Code 2.1.299 compacts sessions over 200K tokens after about 54 idle minutes. How the cache math works, the setting to turn it off, and when to keep it.

OpenAI prompt-to-voice turns a text description into a saved GPT-Live voice. Creating it is free, the limit is 100 per org, and it only works in GPT-Live.

Anthropic's own runs: a Fable 5.1 advisor added 1.7 points to Opus 5.5 for 2.1x the cost. When the Claude advisor tool pays, and when to raise effort instead.

Claude Haiku 5.5 pricing, the cliff above 100K-token prompts, the tokenizer catch, the migration steps from Haiku 4.5, and when to use it instead of Sonnet.

Claude Sonnet 5.5 costs $2/$10 per million tokens, and cache reads fell to $0.10 on October 7 - half of Opus 5.5 on every line. Pricing math and API changes.

Claude Opus 5.5 costs $4/$20 per million tokens with $0.20 cache reads. SDK examples, Claude Code setup, and when to pick it over Sonnet 5.5 or Haiku 5.5.

Qualcomm is acquiring Modular for about $3.9 billion. What the deal means for developers using MAX, Mojo, and hardware-agnostic AI inference beyond CUDA.

Cursor v3.11 Side Chats guide: open parallel agent conversations with /side or /btw, search past sessions with Conversation Search, and use Cloud Agent Hooks.

Claude Sonnet 5 migration guide: the three breaking API changes from Sonnet 4.6, the new effort parameter, tokenizer impact and when to use each effort level.

Claude Science wraps Claude with scientific tools, local code execution and HPC access. How to get it, what it costs, and how it fits alongside Claude Code.

Cursor Composer 2.5 guide: Cursor's agentic coding model, setup, Standard vs Fast pricing, benchmarks against Opus 4.7 and GPT-5.5, and when to use it.

Claude in Microsoft Foundry on Azure is GA with Azure billing and Entra ID auth. The developer setup: CCU pricing, SDK examples and deployment options.

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.