Back to Models

DeepSeek V4 Flash (High)

![DeepSeek](https://artificialanalysis.ai/img/logos/deepseek_small.svg)DeepSeek
45/ 57

Intelligence Score

Intelligence

45

#30 of 203 (top 15%)

Speed

N/A

Not measured

Price

$0.17

per M tokens

#23 cheapest of 136

Context Window

1M

tokens

Latency: N/A

Score Breakdown

Quality Score75%
Speed Score0%
Cost Score98%

Similar Models

Qwen3.5 397B A17B

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

45intelligence

MiMo-V2-Omni-0327

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

45intelligence

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

Claude Sonnet 4.6 (Non-reasoning)

![Anthropic](https://artificialanalysis.ai/img/logos/anthropic_small.svg)Anthropic

44intelligence

Use This Model

Claude Code

claude --model deepseek-v4-flash-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-flash-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-flash-high"),
  prompt: "Hello",
});
Back to Models