Blog and Guides
Explore practical LLM API guides, integration notes, and product updates.
Product updates, integration guides, and practical notes for LLM API developers.
Topic directory
Browse every article topic
A server-rendered directory gives every topic a permanent, crawlable path from the main blog.
Browse all topicsStart here
New to the gateway? These pages answer the big questions first
Pricing, setup docs, and the purchase flow — the fastest route from reading about a model to calling it with a working key.
Use the live pricing page for multipliers, token math, and plan fit before comparing routes.
Read the docs before wiring clientsThe docs page is the source of truth for endpoint style, compatibility, and integration examples.
Use Chinese LLM APIs overseasA direct commercial page for Kimi, GLM, Qwen, DeepSeek, StepFun, and China MaaS access through one key.
Connect Claude Code by APIA direct setup page for Claude Code, Codex CLI, coding agents, and compatible model routes.
Start the purchase flowUse the buy page for first-time access, then top up once the key is live.
Compare China MaaS providersWhich Chinese model routes are worth buying: pricing, model coverage, and overseas access paths compared.
Read the Step-3.7 Flash coding guideWhat step-3.7-flash offers for coding agents and multimodal work, and how to run it through one key.
Xiaomi MiMo-V2.6 Pro and Flash: Open-Weight Ranking, Pricing, and CodeMidas
Choose MiMo-V2.6 Pro or Flash with the AA 46-point context, $3.47M Live RL disclosure, CodeMidas method, official cached API prices, and platform multipliers.
Qwen3.8-Omni-Flash Multimodal Model Launch: API and Audio-Video Agent Guide
Qwen3.8-Omni-Flash is a newly released multimodal model for text, image, audio, and video input with a 1M-token context window. This guide covers audio-video agents, long-video understanding, meeting execution, API integration, and Qwen-Live Harness.
DeepSeek V4.1 Flash API Pricing: 552B Guide
DeepSeek V4.1 Flash launched on September 10, 2026. Review its 552B architecture, API pricing, native vision, agent benchmarks, and V4 Pro migration path.
Tencent Hy4 Preview Guide 2026: 770B MoE & 1M Context
Tencent Hy4 preview is released and open sourced. Verify its 770B/49B MoE, 1M context, coding-agent results, TokenHub price, model IDs, and API limits.
GLM-5.3-Flash API Guide 2026: 1M Multimodal & Coding
GLM-5.3-Flash is live with 1M context, native multimodal input, 320B/18B MoE, coding and agent benchmarks, API access, and production guidance.
Qwen3.8-Flash API Pricing & Coding Guide 2026: 1M Multimodal
Qwen3.8-Flash is live. Review 1M context, multimodal input, 125B+51B/6B MoE, QSA, official pricing, Coding Agent access, and model choice.
DeepSeek-V4-Flash-Vision-Exp API Guide 2026
DeepSeek-V4-Flash-Vision-Exp adds image input, a 1M context window, up to 384 image tokens, and Chat, Messages, and Responses API support.
GLM-5.3 API Guide 2026: 1M Context & 8x Pricing
GLM-5.3 is live with a 1M context window and the same 8x rate as GLM-5.2. Review coding benchmarks, API migration, reasoning effort, and agent use.
DeepSeek-V4-Pro-0813 Guide 2026: API, Codex & Price
DeepSeek-V4-Pro-0813 is the current deepseek-v4-pro version. Review its 1M context, official price, Codex and Responses API setup, and gateway rate.