Back to Models

DeepSeek V4 Pro (High)

![DeepSeek](https://artificialanalysis.ai/img/logos/deepseek_small.svg)DeepSeek
50/ 57

Intelligence Score

Intelligence

50

#18 of 203 (top 9%)

Speed

38 tok/s

#121 of 131

Price

$2.17

per M tokens

#107 cheapest of 136

Context Window

1M

tokens

Latency: 2ms (#67)

Score Breakdown

Quality Score83%
Speed Score6%
Cost Score81%

Similar Models

Qwen3.6 Plus

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

50intelligence

GLM-5

![Z AI](https://artificialanalysis.ai/img/logos/zai_small.svg)Z AI

50intelligence

MiniMax-M2.7

![MiniMax](https://artificialanalysis.ai/img/logos/minimax_small.svg)MiniMax

50intelligence

GLM-5.1

![Z AI](https://artificialanalysis.ai/img/logos/zai_small.svg)Z AI

51intelligence

GPT-5.5 (low)

![OpenAI](https://artificialanalysis.ai/img/logos/openai_small.svg)OpenAI

51intelligence

Use This Model

Claude Code

claude --model deepseek-v4-pro-high

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-high",
    "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-high"),
  prompt: "Hello",
});
Back to Models