1. 7API
  2. Models
  3. DeepSeek
  4. DeepSeek V4 Pro

DeepSeek V4 Pro API

Model ID: deepseek-v4-pro-0813 · Developer: DeepSeek · Available on 7API: yes, as of 2026-11-20

Call DeepSeek V4 Pro with any OpenAI- or Anthropic-compatible client. Use base URL https://7api.st/v1 (OpenAI) or https://7api.st (Anthropic) and send "model": "deepseek-v4-pro-0813".

Specifications

Model IDdeepseek-v4-pro-0813
Context window1,000,000 tokens
Max output65,536 tokens
InputText
Tool callingYes
StreamingYes
Reasoning effortModel default
API formatsChat Completions, Responses, Anthropic Messages

Pricing

USD per 1M tokens
Input$0.25
Output$0.25
Cached input$0.05

For example, an agent turn with 150,000 cached input tokens, 2,000 new input tokens and 800 output tokens costs about $0.0082 on DeepSeek V4 Pro. Billing is pay per token from a prepaid balance. See Pricing and billing.

Benchmarks

Independent scores for DeepSeek V4 Pro, as published by third parties (retrieved 2026-10-24). 7API serves the same model, so these scores apply to it here.

BenchmarkResult
Artificial Analysis Intelligence Index, max effort36

Example

Python (OpenAI SDK)
from openai import OpenAI

client = OpenAI(base_url="https://7api.st/v1", api_key="YOUR_7API_KEY")
r = client.chat.completions.create(
    model="deepseek-v4-pro-0813",
    messages=[{"role": "user", "content": "Write a haiku about caching."}],
)
print(r.choices[0].message.content)

In Claude Code: /model claude-deepseek-v4-pro-0813. Setup guides: Claude Code, OpenCode, Codex, Cursor.