DeepSeek V3.2 API — OpenAI-Compatible Quickstart

Why DeepSeek-V3.2

DeepSeek-V3.2 is optimized for high-volume production: chat, tool calling, code generation, and long-context RAG. It is usually the better default than R1 when you need speed and cost control rather than deep chain-of-thought math.

• OpenAI-compatible chat completions
• Strong coding + instruction following
• Much cheaper than Western frontier models for bulk workloads
• Pairs well with R1 when only hard reasoning steps need a reasoning model

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_KEY",
    base_url="https://api.chinamodelapi.com/v1",
)

resp = client.chat.completions.create(
    model="deepseek-v3",
    messages=[
        {"role": "system", "content": "You are a precise coding assistant."},
        {"role": "user", "content": "Write a Python function to chunk text for RAG."},
    ],
    temperature=0.2,
)
print(resp.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.CHINAMODELAPI_KEY,
  baseURL: "https://api.chinamodelapi.com/v1",
});

const resp = await client.chat.completions.create({
  model: "deepseek-v3",
  messages: [{ role: "user", content: "Summarize this API error for ops." }],
  stream: false,
});
console.log(resp.choices[0].message.content);

V3.2 vs R1 — when to pick which

See also the dedicated DeepSeek R1 API guide.

FAQ

Related Guides