DeepSeek V4 Pro
DeepSeek · Teks · Konteks 1M · output maks 393.2K token
deepseek-v4-pro
Coba
Harga
| MarkasAI | Harga list vendor | |
|---|---|---|
| Input | Rp 10.090 | Rp 11.808 |
| Output | Rp 30.267 | Rp 35.423 |
| Cache | Rp 337 | |
| Tulis cache | Rp 10.090 |
Harga jual MarkasAI dalam Rupiah, dibaca dari katalog yang sama dengan GET /v1/models. Harga dapat berubah dan berlaku untuk permintaan berikutnya.
Spesifikasi
- ID model
deepseek-v4-pro- Provider
- DeepSeek
- Jenis
- Teks
- Endpoint
POST /v1/chat/completions- Jendela konteks
- 1.000.000 token
- Batas output per permintaan
- 393.216 token
Tentang model ini
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
Kutipan dari katalog publik penyedia, dalam bahasa Inggris.
Contoh pemanggilan
curl https://api.markas.ai.id/v1/chat/completions \
-H "Authorization: Bearer $MARKASAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro",
"messages": [{"role": "user", "content": "Apa itu API?"}],
"max_tokens": 300
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://api.markas.ai.id/v1", api_key=os.environ["MARKASAI_API_KEY"])
resp = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "Apa itu API?"}],
max_tokens=300,
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.markas.ai.id/v1", apiKey: process.env.MARKASAI_API_KEY });
const resp = await client.chat.completions.create({
model: "deepseek-v4-pro",
messages: [{ role: "user", content: "Apa itu API?" }],
max_tokens: 300,
});
console.log(resp.choices[0].message.content);Simpan API key di variabel lingkungan MARKASAI_API_KEY. Baca dokumentasi endpoint