DeepSeek V4 Flash Vision

deepseek/deepseek-v4-flash-vision-exp

DeepSeek V4 Flash Vision (experimental) is a vision-enabled variant of DeepSeek V4 Flash — a sparse mixture-of-experts model (13B active of 284B total) adding image understanding to its reasoning, coding, and agent workflows.

Pricing

Specifications

Use DeepSeek V4 Flash Vision

Point your existing OpenAI SDK at xKiro and pass deepseek/deepseek-v4-flash-vision-exp as the model. Nothing else in your code changes.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.xkiro.com/v1",
    api_key="YOUR_XKIRO_KEY",
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-flash-vision-exp",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

max_tokens · temperature · top_p · stop · frequency_penalty · presence_penalty · seed · stream · tools · tool_choice · response_format · structured_outputs · reasoning · include_reasoning

Related models

• DeepSeek V3.1Free
• DeepSeek V3.2Free
• DeepSeek V4 FlashFree
• DeepSeek V4 Flash 0731$0.091
• DeepSeek V4 ProFree
• DeepSeek V4 Pro 0813$0.2828