🇨🇳 Chinese model
DeepSeek V4 Flash Vision Exp
Text Image Function calling Structured output Reasoning File input
Pricing & specs
Input / 1M tokens $0.14
Output / 1M tokens $0.28
Cache / 1M tokens $0.00
Context window 1M tokens
Max output 384K tokens
Updated 2026-08-21
Docs Official docs ↗
Price source View source ↗
Providers
USD / 1M tokens · input / output
DeepSeek Official $0.14 / $0.28 NanoGPT lowest $0.22 / $0.66 OpenRouter $0.22 / $0.66 OpenCode Go $0.22 / $0.66 Vercel AI Gateway $0.22 / $0.66 Eden AI $0.22 / $0.66 Kilo Gateway $0.22 / $0.66 2 more at higher prices
Similar models · Top 5
Qwen Plus 🇨🇳 1M In $0.12 · Out $0.29 · Cache $0.01 MiMo-V2.5 🇨🇳 262K In $0.15 · Out $0.30 · Cache $0.00 Gemini 2.5 Flash-Lite 🇺🇸 1.0M In $0.10 · Out $0.40 · Cache $0.01 Qwen3 Coder Flash 🇨🇳 1M In $0.14 · Out $0.57 · Cache — Doubao 1.5 Pro 🇨🇳 256K In $0.12 · Out $0.30 · Cache $0.02
Want to go deeper on AI and cloud cost management?
Explore more on AI infrastructure, model API cost and resource optimization at mofcloud.