DeepSeek-V4 Flash

model="DeepSeek-V4-Flash"

DeepSeek-V4-Flash is DeepSeek's latest open-source MoE model featuring 284B total parameters with only 13B activated during inference, delivering high-speed generation without sacrificing capability. With native support for a 1M-token context window and three switchable reasoning modes — Non-Think, Think High, and Think Max — it offers flexible intelligence scaling from everyday tasks to complex reasoning, all under the MIT License.

Model Capabilities

Accepts (Input)

Text Generation

Generates (Output)

Text Responses

Quick Integration

Python (OpenAI SDK)

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://helyxai.space/v1/chat/completions",
    api_key=os.environ.get("HELYX_API_KEY")
)

response = client.chat.completions.create(
    model="DeepSeek-V4-Flash",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "How do I use this model?"}
    ],
    max_tokens=384000
)

print(response.choices[0].message.content)

Architecture

Context Window

1,049,000 tokens

Max Input

1,049,000

Max Output

384,000

Usage Allowances

Free Plan (Default)

50,000 tokens / day

Automatically resets every 24 hours.

Developer Plan

10,000,000 tokens / day

Market Pricing Equivalency

Input (per 1M) $0.1400

Output (per 1M) $0.2800

Your Cost: $0.00 (Via Free Quota)

Contact Support