DeepSeek / deepseek-v4-pro

DeepSeek V4 Pro

DeepSeek's larger MoE model for high-quality reasoning, code generation, agents, and technical analysis.

Code assistantLong documentsAutomation & agents

Context

1,000K

tokens

Input

$2.88

/ 1M tokens

Output

$5.76

/ 1M tokens

Quality

Elo 1355

Overview

What this model is good for

DeepSeek's larger MoE model for high-quality reasoning, code generation, agents, and technical analysis.

Model capabilities

Tool calling

Can call tools or functions, so product flows can connect model output to backend actions.

Streaming

Supports streamed responses for chat, assistants, and interfaces that need visible incremental output.

Prompt cache

Supports prompt caching patterns for repeated context and longer production conversations.

Model maker

Model maker and access

This section shows the model maker, SeaLink model ID, protocol, and pricing information.

DeepSeek

Called through SeaLink's unified account, balance, and OpenAI-compatible API.

Protocol

OpenAI-compatible Chat Completions

Base URL: https://test.sealink.io/v1

Pricing

Pricing and cost sense

Prices come from the current model catalog. Simple estimates help users judge whether the model fits production volume.

Input$2.88/ 1M tokens

Output$5.76/ 1M tokens

Light production run

100K input + 25K output

$0.432

Higher-volume run

1M input + 250K output

$4.32

Actual billing follows usage logs and billing records; caching and media pricing depend on the endpoint.

API

Copy into your code

The model page should make it clear which model to copy, which base URL to use, and where to get an API Key.

model

deepseek-v4-pro

base_url

https://test.sealink.io/v1

Auth

Bearer $SEALINK_API_KEY

cURL

curl https://test.sealink.io/v1/chat/completions \
  -H "Authorization: Bearer $SEALINK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-pro",
    "messages": [{"role": "user", "content": "Hello."}]
  }'

Python (OpenAI SDK)

from openai import OpenAI
client = OpenAI(base_url="https://test.sealink.io/v1", api_key="<your-sealink-key>")

resp = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[{"role": "user", "content": "Hello."}],
)
print(resp.choices[0].message.content)

Node.js (OpenAI SDK)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://test.sealink.io/v1",
  apiKey: process.env.SEALINK_API_KEY,
});

const resp = await client.chat.completions.create({
  model: "deepseek-v4-pro",
  messages: [{ role: "user", content: "Hello." }],
});
console.log(resp.choices[0].message.content);