DeepSeek: deepseek-flash

Tentang deepseek-flash

DeepSeek V4.1 Flash tersedia melalui model ID ChinaAPI yang sudah ada, deepseek-flash. Dirilis pada 2026-09-10, model gambar-teks native Mixture-of-Experts ini memiliki 552B parameter, dengan 8B aktif saat prefill input dan 16B saat decode output, konteks 1M, serta output hingga 384K. Model mendukung mode reasoning dan non-reasoning, tool calling, output JSON, Responses API, dan akses Anthropic-compatible.

Panduan Singkat

Salin-tempel permintaan API.

curl -X POST https://api.chinaapi.ai/v1/chat/completions \
  -H "Authorization: Bearer $CHINAAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-flash",
    "messages": [
      {"role": "user", "content": "Summarize the main tradeoffs for this API workload."}
    ]
  }'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["CHINAAPI_API_KEY"],
    base_url="https://api.chinaapi.ai/v1",
)

response = client.chat.completions.create(
    model="deepseek-flash",
    messages=[
        {"role": "user", "content": "Summarize the main tradeoffs for this API workload."}
    ],
)
print(response.choices[0].message.content)