DeepSeek V4 Flash API

CN DeepSeek | released 2026-04 | knowledge cutoff 2025-08

DeepSeek V4 Flash is the lightweight sibling of V4 Pro, optimized for latency and cost. At roughly a third of Pro’s price, it is ideal for classification, extraction, routing, and other high-throughput tasks where speed matters more than peak reasoning depth.

CodeImageTool UseJSON ModeFast

Pricing (official list, per 1M tokens)

Input

$0.14/M

Output

$0.29/M

Specifications

Context window1000K tokens Max output32.768K tokens Input modalitiesImage StreamingYes APIOpenAI-compatible

How to use DeepSeek V4 Flash

Drop-in OpenAI replacement. Change only the base_url and model.

# Python -pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://meshtok.com/v1",
    api_key="sk-your-MeshTok-key",
)

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

# cURL
curl https://meshtok.com/v1/chat/completions \
  -H "Authorization: Bearer sk-your-MeshTok-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek/deepseek-v4-flash","messages":[{"role":"user","content":"Hello!"}]}'