DeepSeek: deepseek-v4-flash-vision-exp

About deepseek-v4-flash-vision-exp

DeepSeek V4 Flash Vision (experimental) adds image understanding to the V4 Flash tier. It accepts mixed text and image input, converts images into input tokens with no separate image charge, and supports thinking and non-thinking modes, tool calling, and JSON output with a 1M context window and up to 384K output.

Quickstart

Copy-paste API request.

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)