DeepSeek Flash · Peak · 10M tokens

DeepSeek Flash billed at the peak rate, for requests that must run in business hours. The same multimodal workhorse, without the off-peak scheduling constraint.

What you get

• 10M tokens for every unit you buy. Order several units to stack quota.
• A personal access key for deepseek-flash, issued automatically once your order is completed.
• Billing window: Peak. DeepSeek peak hours are 01:00-04:00 and 06:00-10:00 UTC, Monday to Friday excluding Chinese public holidays; every other hour is off-peak.
• No shipping: delivery is digital, under My Account > Order History and by email.

Capabilities

• Multimodal
• Peak hours
• Thinking mode
• Tool calls

Best for

Latency-sensitive agents and real-time multimodal tasks.

Quick start

from openai import OpenAI

client = OpenAI(api_key="YOUR_ACCESS_KEY", base_url="YOUR_BASE_URL")
response = client.chat.completions.create(
    model="deepseek-flash",
    messages=[{"role": "user", "content": "Hello"}],
    extra_body={"thinking": {"type": "enabled"}},
)

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