DeepSeek V4: The Open-Weights Model
That Changed AI Coding Forever
Released April 24, 2026. V4-Pro scores 80.6% SWE-bench at $0.87/M output — that's 28x cheaper than Claude Opus 4.8. Here's everything you need to know.
V4-Pro vs V4-Flash: Which One Should You Use?
DeepSeek shipped two models on the same day. V4-Pro is the frontier model; V4-Flash is the budget speed demon. Both support 1M-token context and 384K max output.
🚀 V4-Pro
- 1.6 trillion total parameters
- 49B active parameters per token
- 80.6% SWE-bench Verified
- Best for: complex coding, multi-file refactoring
- 28.7x cheaper than Claude Opus 4.8
- 34.5x cheaper than GPT-5.5
⚡ V4-Flash
- 284 billion total parameters
- 13B active parameters per token
- 79.0% SWE-bench Verified
- Best for: fast iteration, daily coding tasks
- ~89x cheaper than Claude Opus 4.8
- Replaces legacy deepseek-chat endpoint
Pricing Comparison: DeepSeek V4 vs The Competition
How much does a dollar buy you in output tokens? This is where DeepSeek V4 dominates.
| Model | Output Price (per 1M) | Tokens per $1 | SWE-bench |
|---|---|---|---|
| DeepSeek V4-Flash | $0.28 | 3,571,428 | 79.0% |
| DeepSeek V4-Pro | $0.87 | 1,149,425 | 80.6% |
| DeepSeek Chat (legacy) | $1.10 | 909,090 | 67.8% |
| Gemini 3.1 Pro | $10.50 | 95,238 | 80%+ |
| GPT-5.5 | $30.00 | 33,333 | ~87% |
| Claude Opus 4.8 | $25.00 | 40,000 | 88.6% |
The verdict: A $1 budget gets you 1.15M tokens from V4-Pro vs just 40K from Claude Opus. For most coding tasks, that's an easy tradeoff.
How to Set Up DeepSeek V4
With Claude Code (Terminal)
DeepSeek V4 supports the Anthropic API format natively — just change the base URL:
# 1. Get your API key from platform.deepseek.com
export ANTHROPIC_BASE_URL=https://api.deepseek.com/anthropic
export ANTHROPIC_API_KEY=sk-your-deepseek-key
# 2. Use claude-code normally — it routes through DeepSeek V4
claude-code "refactor the authentication module"
# To switch between Pro and Flash:
export DEEPSEEK_MODEL=deepseek-v4-pro
# or
export DEEPSEEK_MODEL=deepseek-v4-flash
With Cursor IDE
# Settings → Models → Add Custom Model
# API Base URL: https://api.deepseek.com/v1
# Model: deepseek-v4-pro (or deepseek-v4-flash)
# API Key: your DeepSeek API key
With OpenRouter (Recommended for Multi-Model)
# OpenRouter gives you DeepSeek V4 + Claude + GPT in one key
export OPENROUTER_API_KEY=sk-or-your-key
# Model: deepseek/deepseek-v4-pro
# Model: deepseek/deepseek-v4-flash
# Works with Claude Code, Aider, Continue.dev, Cline
Self-Hosting (MIT License)
V4 weights are on Hugging Face under MIT license. V4-Flash (284B/13B active) can run on a single 8xH100 node. V4-Pro (1.6T/49B active) needs multi-node inference. Use vLLM or SGLang for serving.
Benchmark Deep Dive
| Benchmark | V4-Pro | V4-Flash | Claude Opus 4.8 | GPT-5.5 |
|---|---|---|---|---|
| SWE-bench Verified | 80.6% | 79.0% | 88.6% | ~87% |
| Chatbot Arena Elo | ~1450 | 1433 | ~1500+ | ~1490 |
| Coding Arena Elo | — | 1479 | — | — |
| Context Window | 1M | 1M | 200K (1M enterprise) | 128K |
| Max Output | 384K | 384K | 64K | 16K |
| License | MIT (open) | MIT (open) | Proprietary | Proprietary |
💡 Our Take
DeepSeek V4 is the best value proposition in AI coding today. For 90% of coding tasks, V4-Pro delivers results indistinguishable from models costing 28x more. Use Opus or GPT-5.5 for the hardest 10% of tasks. For everything else, V4 is the smart play.
Try DeepSeek V4 Today
Start with $5 free credit on OpenRouter — access DeepSeek V4, Claude, GPT-5, and 200+ models with one API key.
Get Started on OpenRouter →Buy Crypto to Pay for API Credits
Many developers pay for API credits with crypto. Get the lowest fees on Binance.
Sign Up on Binance (Fee Discount) →