Yomi APIUsing Claude API from China: OpenAI SDK, Claude Code and Cursor setup with troubleshooting
Get a key in three steps, choose from three integrations, troubleshoot 401/429/504 and pay in RMB with WeChat Pay/Alipay.
Are AI API relays safe? Distinguishing official channels from gray-market APIs
Six checks for a five-minute compliance assessment following the security advisory and AI application campaign.
What is an API relay? Architecture, types and compliance boundaries (2026)
Aggregation architecture, three service types, compliance boundaries, unified access, RMB payments and token billing: a 2026 primer.
Choosing an API gateway: a 2026 guide to compliance, price, latency and stability
Compare compliance, pricing, latency, stability and ecosystem with weighted scores and ten decision checks.
AI model API costs compared: GPT, Claude and DeepSeek prices per million tokens (2026)
GPT, Claude and DeepSeek rates per million tokens, billing concepts and model selection. Use Model Explorer for live prices.
One API key for 200+ models: the Yomi API integration guide
Register → create a key → change base_url → switch model. Includes Python/curl examples and popular model references.
OpenRouter alternatives for China: SiliconFlow versus Yomi API (2026)
Compare coverage, payments, latency, routing and billing transparency, with a migration tutorial.
Using OpenAI API from China: GPT SDK, Cursor and troubleshooting
Get a key in three steps, connect GPT through SDK/Cursor, troubleshoot 401/403/429/500 and pay with WeChat Pay/Alipay.
Calling DeepSeek API: pricing, integration and model selection (2026)
Choosing v4-pro or v4-flash, actual rates, three-step SDK integration, costs and FAQ.
SiliconFlow versus API relays: two service models explained (2026)
Open-source inference compute versus aggregated official provider channels: understand the two models and choose.
How to top up an API relay: billing, RMB payments and cost control (2026)
RMB top-ups, token/monthly billing, prices, usage records, five cost controls and invoices explained.
High API relay latency? A guide to low-latency model API access
Three latency stages, five improvements and a P50/P95 script for low-latency global model access.