🇨🇳 Chinese model

DeepSeek V4 Flash

Text Function calling Structured output Reasoning

Pricing & specs

Input / 1M tokens $0.45

Output / 1M tokens $1.34

Cache / 1M tokens $0.01

Context window 1M tokens

Max output 384K tokens

Updated 2026-07-31

Docs Official docs ↗

Price source View source ↗

Pricing notes

价格为厂商官方公开人民币价（单位：元/百万 tokens）。

数据来源：LLM Abacus (llmabacus.com)，CC-BY-4.0。

Providers

USD / 1M tokens · input / output

DeepSeek Official $0.45 / $1.34 Deep Infra lowest $0.09 / $0.18 Pioneer $0.10 / $0.20 GMI Cloud $0.11 / $0.22 Jalapeno Cloud $0.14 / $0.28 Hugging Face $0.14 / $0.28 Nebius Token Factory $0.14 / $0.28

6 more at higher prices

Plans / subscriptions

SCNet Token Plan Included in plan

Similar models · Top 5

GPT-4.1 mini 🇺🇸 1.0M In $0.40 · Out $1.60 · Cache $0.10 MiniMax-M3 🇨🇳 1.0M In $0.31 · Out $1.25 · Cache $0.06 Gemini 3.1 Flash Lite 🇺🇸 1.0M In $0.25 · Out $1.50 · Cache $0.03 Mistral Large 3 🇫🇷 262K In $0.50 · Out $1.50 · Cache — Qwen3 Max 🇨🇳 262K In $0.37 · Out $1.49 · Cache —

Want to go deeper on AI and cloud cost management?

Explore more on AI infrastructure, model API cost and resource optimization at mofcloud.

Go to mofcloud Back to price explorer