DeepSeek V4 Pro API

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

DeepSeek V4 Pro is the flagship model from DeepSeek, delivering frontier-class reasoning and coding at a fraction of the cost of Western alternatives. It supports a 128K context window, native tool calling, and structured outputs, making it a strong default choice for agentic and code-generation workloads.

ReasoningCodeImageTool UseJSON ModeFlagship

Pricing (official list, per 1M tokens)

Input

$0.43/M

Output

$0.86/M

Specifications

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

How to use DeepSeek V4 Pro

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-pro",
    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-pro","messages":[{"role":"user","content":"Hello!"}]}'