Vision Understanding API Page Updated · Refreshed Models + cURL Examples

The Vision Understanding (Image Recognition) API docs have been updated: refreshed the supported vision models list, replacing the older GPT-4o / Gemini 2.5 Pro / Claude 3.5 Sonnet with current mainstream multimodal models such as Gemini 3.1 Pro Preview, Gemini 3.5 Flash, gpt-5.5, and Claude Opus 4.7 / Sonnet 4.6; added cURL examples (image URL and local Base64); and added guidance to check the latest model list. Synced in both Chinese and English.

2026/6/8 13:03 (UTC+8) · Docs Update 📚 Vision Understanding (Image Recognition) API page updated —— Refreshed the supported vision models list (replacing the older GPT-4o / Gemini 2.5 Pro / Claude 3.5 Sonnet with current mainstream multimodal models such as Gemini 3.1 Pro Preview, Gemini 3.5 Flash, gpt-5.5, and Claude Opus 4.7 / Sonnet 4.6), added cURL examples (image URL and local Base64), and added guidance to check the latest model list (most chat models now support multimodal image input). Synced in both Chinese and English. 👉 Vision Understanding API

← Back to Live · 📚 Monthly Archive