Filter by tag

#deepseek

16 materials

DeepSeek V4 Flash Vision Exp: Multimodal Model for Agents

DeepSeek releases experimental multimodal model V4-Flash-Vision-Exp for agents, closing in on Opus 4.8 in visual benchmarks.

cpauaAugust 21, 2026 at 06:42 PM1 min314

DeepSeek V4 Pro and V4 Flash are available in the Codex app using the official DeepSeek API key—ideal as a backup when you hit Codex usage limits.

cpauaMay 25, 2026 at 08:16 AM1 min1,108

DeepSeek permanently cuts DeepSeek V4 Pro pricing by 75%. New rates: $0.003625/M cached input, $0.435/M input, $0.87/M output tokens.

cpauaMay 23, 2026 at 06:36 AM1 min466

DeepSeek V4 Flash is now available for free in OpenCode. Learn what it is, how to access it, and why it matters for faster coding workflows.

cpauaMay 15, 2026 at 04:38 PM1 min8,148

CodexSaver routes low-risk tasks from Codex to DeepSeek, keeping costly models for decisions—48% average savings across five tasks with ~6s latency.

cpauaMay 10, 2026 at 11:55 AM1 min1,178

MIMO V2.5 Pro beats DeepSeek V4 Pro with faster output and cleaner visuals, thanks to its multimodal roots. DeepSeek V4 Vision may close the gap.

cpauaMay 3, 2026 at 12:23 PM1 min1,066