Model · DeepSeek

DeepSeek V4 Pro

deepseek/deepseek-v4-pro

Try in Agents

DeepSeek V4 flagship with thinking and non-thinking modes and 1M context

reasoningcaching

Specs

Context

1.0M

Max output

384K

Provider

DeepSeek

Input

$0.660/ 1M tokens

Output

$1.98/ 1M tokens

Cache read

$0.066/ 1M tokens

Try it

Chat with DeepSeek V4 ProTerramind 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-pro"),
  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

Model	Context	In	Out	Capabilities
deepseek/deepseek-v4-flash	1.0M	$0.076	$0.153	caching
deepseek/deepseek-v4-flash-vision	1M	$0.220	$0.660	visioncaching
deepseek/deepseek-v4-1-flash	1.0M	$0.300	$1.20	visioncaching