Field notes

Operational notes for Chinese AI API workloads.

Start with the failure or decision in front of you: a context boundary, an unexplained charge, a route change, or a production check.

Run the verified request path Check the current rate card

Read historical facts with their dates.
An older article may describe the route or rate available when it was published. Use the current Models and Pricing pages before a production decision.

Operational notes for Chinese AI API workloads.

Moonshot v1 Auto Route Pins for 128K API Buyers

Official Price Page Drift Capture for Chinese AI API Workbooks

OpenAI-Compatible SDK Contract Gates for Chinese Model Routes

AIWave Pricing JSON vs Live Route Table for API Budgets

VIP Key 10 Percent Discount Receipts for AIWave API Teams

Intelligent Retry Patterns for OpenAI-Compatible AI Gateways

DeepSeek Flash September Price Row Canaries for API Gateways

MiniMax M2 and M3 Route Ledgers for Agent Workloads

Doubao and Qwen Multimodal Route Budgets for Product Teams

Chinese AI Model Pricing Tracker (September 2026)

AIWave Blog Sitelinks for API Evaluators

DeepSeek vs GLM vs Kimi Route Receipts for Production Teams

Chat Completion Stream Receipts for Chinese AI API Trials

ERNIE 5.1 API: Baidu's Models for Production

MiniMax M3 API: Complete Integration Guide

StepFun API: Chinese AI Models for Coding

Doubao API: ByteDance's AI Models Explained

MiMo API: Xiaomi's Long-Context AI Models

Moonshot v1 128K API Context Receipts for Evaluators

Qwen Max and Flash Route Budget Tests for SaaS Agents

DeepSeek V3.2 Fallback Canaries for OpenAI-Compatible Routes

GLM-5.1 Cached-Input Regression Tests for API Migrations

Kimi K3 Repeated-Context Ledgers for Coding Agents

AIWave Docs and Pricing Sitelinks for API Evaluators

Responses API Streaming Gates for Chinese AI Routes

Qwen Tool and Batch Billing Fields for SaaS API Ledgers

Machine-Readable AIWave Evidence for API Search Evaluators

The Complete Guide to Chinese AI APIs

DeepSeek V4 Pro API: A Developer's Guide

Cost Comparison: Direct API vs Reseller vs Gateway

Context Window Exceeded API Runbook Long Context Workloads 2026

Deepseek V4 PRO API Access 1M Context Coding Agents 2026

Openrouter Alternative Long Context Deepseek Routing 2026

Deepseek V4 PRO 10M Token Cost Ledger Tier1 2026

Default VS VIP Billing Groups Aiwave API Requests 2026

Gateway Success Rates Denominators AI API Buyers 2026

DeepSeek Reasoning vs GPT-4o Pricing for Agent Routes

ERNIE API Pricing Procurement Scorecard for SaaS Teams

From Four to Nine: A Practical Gateway for Chinese AI Models

site:aiwave.live CTR Runbook for API Trial Pages

AIWave API Documentation Sitelinks for Tier 1 Buyers

GLM-5.1 API Pricing and GLM-5.3 Migration Controls

Kimi K3 API Context and Search-Cost Controls for Coding Agents

AIWave.live API Evaluation Plan for Brand Searchers

DeepSeek V4 Peak Windows and Cache-Hit Budgeting for US Teams

Qwen API Batch, Thinking, and Tool-Fee Budget Controls

AIWave API Documentation for Production Model Switching

Chinese AI API Gateway Trust Checklist for SaaS Procurement

ERNIE 5.1 API Pricing and Cache-Aware Enterprise Routing

Evaluating DeepSeek API Access for Overseas Teams

GLM and Qwen API Routing: Batch, Cache, and Tool-Cost Controls

Kimi K3 API Cost Controls for Long-Context Coding Agents

AIWave API Documentation for Production Chinese Model Migration

AIWave Pricing: Cache-Aware Forecasting for Chinese AI APIs

ERNIE Speed API Routing for Global SaaS Workloads

Chinese AI API Cost Governance for SaaS Teams

DeepSeek V4 Pro vs Flash Routing for Production Agents

OpenAI-Compatible Chinese AI APIs With GDPR-Aware Deployment

AIWave API Documentation Quickstart for Chinese Model Routing

DeepSeek API Rate Limits and 429 Controls for Agent Gateways

ERNIE API Pricing for SaaS Routing and Cost Ledgers

Account, Route, and Billing Questions for Gateway Evaluation

Cache-Aware Chinese AI API Ledger for DeepSeek, Qwen, Kimi, and GLM

Chinese AI API Pricing and Routing: A Review Checklist

Chinese Model Routing: Account, Rate, and Control Questions

DeepSeek V4 Flash vs V4 Pro: A Developer Comparison

DeepSeek V4 Peak Pricing Budget Locks for SaaS Agents

DeepSeek V4 Pro vs GPT-4o: Real Benchmark Data (2026)

Migrating from OpenAI to AIWave: A Controlled Switch Guide

OpenAI-Compatible Chinese Model Migration Runbook After DeepSeek Price Changes

DeepSeek V4 Peak Pricing: A Cost Impact Analysis for API Teams

DeepSeek V4 Pro vs Flash: When to Use Each After Pricing Changes

Migrating From DeepSeek Direct to a Multi-Provider API After the Price Hike

AIWave API Documentation Quickstart for Production Teams

DeepSeek V4 429 Handling for Production Agent Gateways

ERNIE API Pricing and Fallback Planning for Global SaaS

GLM-5 API Routing for Production Coding Agents

Kimi K3 Cache Budgets for Long-Context Coding Sessions

Qwen3.7 Context-Tier Budgeting for Multimodal Agents