deepseek-v4-flash-0731 API pricing & access

deepseek-v4-flash-0731 API access

Compare supported API endpoints and capabilities, then access deepseek-v4-flash-0731 through the unified API gateway.

Supported APIs

OpenAI Chat Completions API

API endpoints

POST /v1/chat/completions

deepseek-v4-flash-0731 API pricing

Base input price

$75 per 1M tokens

Base output price

$75 per 1M tokens

Base prices are shown in USD before group-specific adjustments. Open the live pricing page for current access-group prices.

How to call deepseek-v4-flash-0731

deepseek-v4-flash-0731 is served through ModelsOk's unified gateway. Existing OpenAI or Anthropic SDK code keeps working: point base_url at https://modelsok.com and use your ModelsOk API key.

curl (OpenAI-compatible)

curl https://modelsok.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek-v4-flash-0731", "messages": [{"role": "user", "content": "Hello"}]}'

Python (openai SDK)

from openai import OpenAI

client = OpenAI(base_url="https://modelsok.com/v1", api_key="YOUR_API_KEY")
response = client.chat.completions.create(
    model="deepseek-v4-flash-0731",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Related pages

• deepseek-v4-flash-0731 availability, latency and throughput (last 90 days)
• All DeepSeek model APIs
• Connect deepseek-v4-flash-0731 to Claude Code, Cursor, Cherry Studio and other clients

Frequently asked questions

Do I need to change my code to use deepseek-v4-flash-0731 here?

No. The gateway speaks the OpenAI and Anthropic wire formats. Change base_url to https://modelsok.com and the API key; requests, streaming and tool calls stay the same.

How is deepseek-v4-flash-0731 billed?

Usage is billed per token at the base price shown above ($75 per 1M tokens), deducted from a prepaid balance. Group-specific rates and cached-token discounts are applied on the live pricing page.

Is deepseek-v4-flash-0731 available right now?

The status page publishes real-traffic availability, first-token latency and throughput for every model over the last 90 days, refreshed every minute.