Back to Models

DeepSeek V4 Pro

![DeepSeek](https://artificialanalysis.ai/img/logos/deepseek_small.svg)DeepSeek
39/ 57

Intelligence Score

Intelligence

39

#47 of 212 (top 22%)

Speed

34 tok/s

#134 of 141

Price

$2.17

per M tokens

#112 cheapest of 142

Context Window

1M

tokens

Latency: 2ms (#73)

Score Breakdown

Quality Score65%
Speed Score4%
Cost Score81%

Similar Models

Mistral Medium 3.5

![Mistral](https://artificialanalysis.ai/_next/image?url=%2Fimg%2Flogos%2Fmistral_small.png&w=32&q=75)Mistral

39intelligence

Gemma 4 31B

![Google](https://artificialanalysis.ai/img/logos/google_small.svg)Google

39intelligence

Qwen3.5 Omni Plus

![Alibaba](https://artificialanalysis.ai/img/logos/alibaba_small.svg)Alibaba

39intelligence

Grok 4.1 Fast

![xAI](https://artificialanalysis.ai/img/logos/xai.svg)xAI

39intelligence

Qwen3.5 397B A17B

![Alibaba](https://artificialanalysis.ai/img/logos/alibaba_small.svg)Alibaba

40intelligence

Use This Model

Claude Code

claude --model deepseek-v4-pro-non-reasoning

API (cURL)

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{
    "model": "deepseek-v4-pro-non-reasoning",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Vercel AI SDK

import { generateText } from "ai";
import { openrouter } from "@openrouter/ai-sdk-provider";

const { text } = await generateText({
  model: openrouter("deepseek-v4-pro-non-reasoning"),
  prompt: "Hello",
});
Back to Models