DeepSeek V4 Flash 0731

Limited Trial

Fast MoE model with 304B params and low, high, and max reasoning-effort levels; substantially enhanced for agentic coding and tool use, with a 1M token context window.

DeepSeek API Usage

POST /v1/chat/completions

import requests
import json

url = "https://api.akashml.com/v1/chat/completions"

payload = {
    "model": "deepseek-ai/DeepSeek-V4-Flash-0731",
    "messages": [
        {
            "role": "user",
            "content": "Hello, how are you?"
        }
    ],
    "max_tokens": 150,
    "temperature": 0.7
}

headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer YOUR_API_KEY"
}

response = requests.post(url, json=payload, headers=headers)
print(response.json())