DeepSeek V4 Pro API

Overview

About this model

DeepSeek V4 Pro, 1M context, supports low/high/max thinking intensity, tool calling, and Responses API. Officially planned from 2026 year 9 month 14 day 12:00 (Beijing time), deepseek-v4-pro requests will be routed to V4.1 Flash, and billed at the V4.1 Flash unit price; before that, billing will still follow the official V4 Pro price.

Capabilities

Capability matrix

Pricing and groups

Routes and pricing

Prices in USD per 1M tokens. Rates follow provider adjustments; live prices in Model Explorer as the reference.

Snapshot: 2026-10-07 23:09. Availability reflects active probes over the past 24 hours; performance reflects actual calls.

API

Integration example

All models share one OpenAI-compatible endpoint. To switch models, change the model field. One key accesses every model.

# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://api.yomiapi.com/v1",
    api_key="sk-your-yomi-key",
)

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

curl https://api.yomiapi.com/v1/chat/completions \
  -H "Authorization: Bearer sk-your-yomi-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-pro",
    "messages": [{"role": "user", "content": "Hello"}]
  }'