Practical LLM API guides, model reviews, and integration tutorials.
A step-by-step OpenRouter migration guide for OpenAI-compatible apps: base URL, model-ID mapping, a test request, common errors, and a safe dual-run cutover.
Configure Claude Code with a custom Anthropic-compatible API: env vars, the base-URL gotcha, model selection, and the errors people hit first.
Set up Cursor with a custom OpenAI-compatible API: the override base URL, model IDs, a test request, real per-token pricing, and Cursor's limits.
Configure Cline in VS Code with a custom OpenAI-compatible API: base URL, key, model IDs, tool-use costs, troubleshooting, and real per-token pricing.
Qwen3.8-Omni-Flash combines text, image, audio, and video in a single Agent workflow. This guide covers its capabilities, API integration, and audio/video Agent use cases.
DeepSeek V4.1 Flash is out: a 552B-parameter native multimodal MoE with 8B/16B activation, 1M context, and Agent benchmark gains. Covers API model IDs, pricing tiers, KV cache compression, and the V4 Pro routing switch.
A breakdown of four public WorkBuddy case studies covering cultural media, one-person companies, and WeChat public-account automation with AI agent workflows and Skills.
Qwen3.8-Flash delivers 1M context, multimodal input, and Function Calling via OpenAI-compatible API. Key distinction: qwen3.8-flash for production, Qwen/Qwen3.8-Flash-Next for self-hosting.
DeepSeek's experimental multimodal model adds image understanding to V4 Flash with 1M context, 384K output, and broad API compatibility.