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)→
More from coding & agent
- Open source MCP server implements HTTP 402 micropayment gateway — EstablishmentTough18 · 2026-08-23
- nb.nvim Fixes Cross-Folder Image Link Bug — 4310sy · 2026-08-23
- AI Agent Search Optimization: Path Calculation Drops from 504ms to Near 0ms — DanielLockyer · 2026-08-23
- How To Build An AI Agent: A Complete Workflow Guide — mdancho84 · 2026-08-23
- A practical guide to AI agents for small businesses: lead response in minutes, 40 hours of invoice work down to 6 — juliesweetie93 · 2026-08-23
- GSD Pi: A terminal agent for long-haul autonomous software projects — tom_doerr · 2026-08-23