https://buzzai.cc/ Engineering writing on AI gateways, transparent forwarding, prompt caching, multi-model routing, and pricing strategy. From the team that runs https://buzzai.cc. en Fri, 22 May 2026 18:50:00 +0000 Fri, 22 May 2026 09:00:00 +0000 buzzai.cc https://buzzai.cc/og/home.png https://buzzai.cc/ 1200 630 https://buzzai.cc/blog/ai-gateway-comparison-buzz-openrouter-helicone https://buzzai.cc/blog/ai-gateway-comparison-buzz-openrouter-helicone Fri, 22 May 2026 18:30:00 +0000 A decision framework for choosing between BUZZ, OpenRouter, Helicone, and LiteLLM, covering model breadth, pricing, privacy, observability, and self-hosting trade-offs. https://buzzai.cc/blog/claude-tool-use-gateway https://buzzai.cc/blog/claude-tool-use-gateway Fri, 22 May 2026 18:00:00 +0000 How tool_use and tool_result round trips work through a transparent gateway, including streaming + tool combinations, retry boundaries, cost math, and a working agent loop. https://buzzai.cc/blog/anthropic-prompt-caching-playbook https://buzzai.cc/blog/anthropic-prompt-caching-playbook Fri, 22 May 2026 17:30:00 +0000 Cache_control patterns, 5-minute vs 1-hour break-even math, three production code patterns, and the gateway-side guarantee that cache directives pass through unchanged. https://buzzai.cc/blog/openai-sdk-claude-compatibility https://buzzai.cc/blog/openai-sdk-claude-compatibility Fri, 22 May 2026 17:00:00 +0000 The OpenAI-compatible Chat Completions adapter at /v1, what works out of the box, what doesn't translate cleanly, and when to fall back to the native Anthropic SDK. https://buzzai.cc/blog/claude-code-cheaper-with-gateway https://buzzai.cc/blog/claude-code-cheaper-with-gateway Fri, 22 May 2026 09:15:00 +0000 How to route Claude Code through BUZZ to reduce per-session cost without losing extended thinking, tool use, or prompt caching. https://buzzai.cc/blog/one-key-claude-gpt-gemini https://buzzai.cc/blog/one-key-claude-gpt-gemini Fri, 22 May 2026 09:10:00 +0000 The operational cost of N model providers, what a unified gateway gives you, and when not to use one. https://buzzai.cc/blog/zero-retention-llm-gateway https://buzzai.cc/blog/zero-retention-llm-gateway Fri, 22 May 2026 09:05:00 +0000 What zero retention should actually mean, the architecture that makes it possible, why retention is dangerous in production, and how to verify a vendor's claim. https://buzzai.cc/blog/claude-api-gateway-guide https://buzzai.cc/blog/claude-api-gateway-guide Fri, 22 May 2026 09:00:00 +0000 How to use Claude API through a gateway, comparing direct integration with gateway routing on reliability, pricing, transparent forwarding, and operational concerns.