Back to models
Model · DeepSeek
DeepSeek

DeepSeek V4.1 Flash

deepseek/deepseek-v4-1-flash
Try in Agents

Natively multimodal V4.1 Flash — 1M context at Flash-tier pricing

visioncaching
Specs
Context
1.0M
Max output
33K
Provider
DeepSeek
Input
$0.300/ 1M tokens
Output
$1.20/ 1M tokens
Cache read
$0.0070/ 1M tokens
Try it
Chat with DeepSeek V4.1 FlashTerramind API
⌘+Enter to run
Code
import { streamText } from "ai";
import { createOpenAICompatible } from "@ai-sdk/openai-compatible";

const terramind = createOpenAICompatible({
  name: "terramind",
  baseURL: "https://terramind.com/api/v1",
  apiKey: process.env.TERRAMIND_API_KEY!,
});

const result = streamText({
  model: terramind("deepseek-v4-1-flash"),
  prompt: "Why is the sky blue?",
});

for await (const chunk of result.textStream) {
  process.stdout.write(chunk);
}

Want to run this in your app? Grab an API key · Full chat reference

More by DeepSeek
ModelContextInOutCapabilities
DeepSeekdeepseek/deepseek-v4-flash1.0M$0.076$0.153
caching
DeepSeekdeepseek/deepseek-v4-flash-vision1M$0.220$0.660
visioncaching
DeepSeekdeepseek/deepseek-v4-pro1.0M$0.660$1.98
reasoningcaching