Skip to content

noya21th/awesome-deepseek-v4

Repository files navigation

awesome-deepseek-v4 — community multilingual hub for DeepSeek V4

awesome-deepseek-v4

Practical, multilingual resource hub for DeepSeek V4.

License: MIT Unofficial PRs Welcome Languages Hugging Face

🌍 Read in your language

English · 简体中文 · Français · العربية · 日本語 · Deutsch · हिन्दी


Fact sheet

DeepSeek-V4-Pro DeepSeek-V4-Flash
Total parameters 1.6 T MoE 284 B MoE
Activated per token 49 B 13 B
Experts (routed × active) 384 × 6 256 × 6
Context length 1,000,000 tokens 1,000,000 tokens
Training tokens 33 T 32 T
Precision FP4 (experts) + FP8 FP8
API price — input $1.74 / Mtok $0.14 / Mtok
API price — output $3.48 / Mtok $0.28 / Mtok
Weights license MIT — commercial use OK MIT — commercial use OK
Reasoning modes Thinking · Non-Thinking Thinking · Non-Thinking

Full spec: docs/architecture.md · Benchmarks: docs/benchmarks.md · Pricing: docs/pricing.md · Comparison tables: docs/comparison.md.


60-second quickstart

V4 speaks both OpenAI ChatCompletions and Anthropic Messages protocols.

# OpenAI SDK
from openai import OpenAI
client = OpenAI(api_key="sk-...", base_url="https://api.deepseek.com/v1")
resp = client.chat.completions.create(
    model="deepseek-v4-pro",   # or "deepseek-v4-flash"
    messages=[{"role": "user", "content": "Prove √2 is irrational."}],
)
print(resp.choices[0].message.content)
# Anthropic SDK
from anthropic import Anthropic
client = Anthropic(api_key="sk-...", base_url="https://api.deepseek.com/anthropic")
msg = client.messages.create(
    model="deepseek-v4-pro", max_tokens=1024,
    messages=[{"role": "user", "content": "Prove √2 is irrational."}],
)
print(msg.content[0].text)

More: API quickstart · Thinking mode · Tool calling · Raw curl · Local vLLM.


What's in this repo

Getting started

Core reference

  • Benchmarks — headline scores with primary-source citations.
  • Architecture — CSA+HCA attention, mHC, Muon, On-Policy Distillation.
  • Pricing — API, managed hosts, self-hosting TCO.
  • Comparison tables — V4 vs. Claude / GPT / Gemini / Qwen / Llama / Mistral / GLM.

Doing real work

  • Recipes10 copy-paste patterns with cost estimates: whole-repo review, long-doc QA, coding agent, batch pipeline, math tutor, LiteLLM fallback, self-host, Aider, Cline, synthetic data.
  • Prompting guide — temperature, Thinking mode, prompt style.
  • Fine-tuning — LoRA / QLoRA / full fine-tune recipes and hardware.
  • FAQ — the questions everyone asks.

Resources

Examples

OpenAI SDK · Anthropic SDK · Thinking mode · Tool calling · curl.

CLI tools (tools/)

Single-file Python CLIs. pip install openai is the only dependency.

  • v4-cost-calc — compare monthly spend across V4, Claude, GPT, Gemini.
  • v4-migrate-env — scan a codebase for OpenAI/Anthropic config and rewrite to V4.
  • v4-repo-review — pack a repo into V4-Pro and get a structured code review.
  • v4-chat — streaming terminal REPL with /think, /model, /save.

Self-hosting (deploy/)

OpenAI-compatible endpoint on your own hardware.

  • Docker Composedocker compose up and you're serving V4.
  • Kubernetes — production Deployment + Service + ConfigMap.
  • systemd — bare-metal unit file.

Prompt library (prompts/)

Battle-tested system prompts. Each declares its recommended model and mode.


Contributing

PRs welcome — corrections, translations, new benchmark reproductions, new community tools. See CONTRIBUTING.md.

Especially wanted: native-speaker review of Arabic, Hindi, Japanese, German, French pages; benchmark reproductions on your own data; deployment notes for non-Linux, AMD GPUs, Apple Silicon.


License and notices

  • Original content of this repository: MIT.
  • DeepSeek V4 weights and technical report: MIT, © DeepSeek-AI.
  • "DeepSeek" is a trademark of DeepSeek-AI. This project is not affiliated with DeepSeek-AI — see DISCLAIMER.

Maintained by

AI小蓝鲸 — I post about AI and open models in Chinese. Same handle across platforms:

Platform Handle
📕 Xiaohongshu (小红书) AI小蓝鲸
📺 Bilibili (B站) AI小蓝鲸
🎵 Douyin (抖音) AI小蓝鲸
🎬 WeChat Channels (视频号) AI小蓝鲸 (search inside WeChat)

PRs from everywhere are welcome regardless of platform.


Star ⭐ if this saves you time. Open an issue or PR if anything is wrong or missing.

About

Community-maintained multilingual resource hub for DeepSeek V4 — recipes, benchmarks, deployment, and migration guides in 7 languages

Topics

Resources

License

Code of conduct

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages