Changelog

Platform updates and API change records

Changelog | OpenAI API

Interpreting GPT-5.4’s Native Computer Use Capability: Major Breakthrough in AI Agent and Efficient Practical Guide for OpenClaw
ByAPIYI - Stable and affordable AI API 2026年 3月 6日

Author's Note: A deep dive into GPT-5.4's native Computer Use capability, its 75.0% OSWorld score surpassing human experts, and how to combine it with the OpenClaw AI Agent framework for efficient automation. GPT-5.4 isn't just another model upgrade—it's OpenAI's first product to natively build computer usage capabilities into a general-purpose model. This means the AI…

Read More Interpreting GPT-5.4’s Native Computer Use Capability: Major Breakthrough in AI Agent and Efficient Practical Guide for OpenClaw
Changelog | LLM API News

Analyzing the 5 Reasons Behind the Release of GPT-5.4: From GPT-5.3 Instant to the AI Triad Rivalry
ByAPIYI - Stable and affordable AI API 2026年 3月 6日

Author's Note: A deep dive into why GPT-5.4 was released just 2 days after GPT-5.3 Instant launched, analyzing the competitive landscape between OpenAI, Anthropic, and Google, and the differentiated positioning of GPT-5.4. On March 3rd, OpenAI released GPT-5.3 Instant. Just 2 days later, on March 5th, GPT-5.4 officially went live. Two heavyweight models from the…

Read More Analyzing the 5 Reasons Behind the Release of GPT-5.4: From GPT-5.3 Instant to the AI Triad Rivalry
Announcements | Changelog

Gemini 3.1 Pro Preview API is now live on APIYI: Analysis of 6 major core upgrades with doubled inference performance
ByAPIYI - Stable and affordable AI API 2026年 2月 20日

Great news—Gemini 3.1 Pro Preview is now live on APIYI and available for API calls. The model name is gemini-3.1-pro-preview, with prompt pricing at $2.00/1M tokens and completion pricing at $12.00/1M tokens—exactly the same as Gemini 3.0 Pro Preview. But don't let the price fool you; the performance is on a whole different level. Gemini…

Read More Gemini 3.1 Pro Preview API is now live on APIYI: Analysis of 6 major core upgrades with doubled inference performance
Changelog | LLM API News

Mastering GLM-5 API Calls: 5-Minute Getting Started Guide for the 744B MoE Open Source Flagship Model
ByAPIYI - Stable and affordable AI API 2026年 2月 15日

Zhipu AI officially released GLM-5 on February 11, 2026. It's currently one of the largest open-source Large Language Models by parameter count. GLM-5 utilizes a 744B MoE (Mixture of Experts) architecture, activating 40B parameters per inference, and has reached the top tier for open-source models in reasoning, coding, and Agent tasks. Core Value: By the…

Read More Mastering GLM-5 API Calls: 5-Minute Getting Started Guide for the 744B MoE Open Source Flagship Model
Changelog | LLM API News

Is Kimi K2.5 open source? A 3-step guide to Kimi K2.5 API integration
ByAPIYI - Stable and affordable AI API 2026年 1月 31日

Author's Note: Kimi K2.5 is now fully open-source. This article explains the open-source license, model download links, and API access methods in detail, and provides a complete code example for quickly calling Kimi K2.5 via APIYI. Has Kimi K2.5 gone open source? That's been the top question for many developers lately. Well, good news: Moonshot…

Read More Is Kimi K2.5 open source? A 3-step guide to Kimi K2.5 API integration