DeepSeek Adds Vision Support; OpenAI Open Sources Codex Platform

卡尔的AI沃茨 · wechat · 2026-08-21

DeepSeek released deepseek-v4-flash-vision-exp, a multimodal model supporting image input (not just OCR) with improved coding capabilities. DeepSeekHarness was updated to support image/text inputs and @files. Pricing matches the flash tier: cached input is ¥0.05–0.1 per million tokens, and output is ¥4.5–9.0.

OpenAI open-sourced Codex components, including CodexCLI, CodexSDK, and Skills repositories. The key app-server allows integrating Codex into third-party apps, supporting streaming events and interaction sync. The author also plans to test the new OxAlpha model on OpenRouter.

Related event: DeepSeek Launches V4-Flash-Vision-Exp, Closing In on Opus 4.8(29 posts)→

Original post →

More from coding & agent

coding & agent channel →