DeepSeek: deepseek-v4-flash-vision-exp

Tentang deepseek-v4-flash-vision-exp

DeepSeek V4 Flash Vision (eksperimental) menambahkan pemahaman gambar ke tingkat V4 Flash. Model menerima input campuran teks dan gambar, mengubah gambar menjadi token input tanpa biaya gambar terpisah, serta mendukung mode thinking dan non-thinking, pemanggilan alat, dan output JSON dengan konteks 1M dan output hingga 384K.

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-v4-flash-vision-exp",
    "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-v4-flash-vision-exp",
    messages=[
        {"role": "user", "content": "Summarize the main tradeoffs for this API workload."}
    ],
)
print(response.choices[0].message.content)