Back to Models

DeepSeek V4 Flash (Max)

![DeepSeek](https://artificialanalysis.ai/img/logos/deepseek_small.svg)DeepSeek
47/ 57

Intelligence Score

Intelligence

47

#25 of 203 (top 12%)

Speed

84 tok/s

#79 of 131

Price

$0.17

per M tokens

#22 cheapest of 136

Context Window

1M

tokens

Latency: 1ms (#34)

Score Breakdown

Quality Score78%
Speed Score12%
Cost Score98%

Similar Models

GLM-5-Turbo

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

47intelligence

Gemini 3 Flash

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

46intelligence

Qwen3.6 27B

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

46intelligence

Grok 4.20 0309 v2

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

49intelligence

MiMo-V2-Pro

![Xiaomi](https://artificialanalysis.ai/img/logos/xiaomi_small.svg)Xiaomi

49intelligence

Use This Model

Claude Code

claude --model deepseek-v4-flash

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