DeepSeek V4-Pro API

Capabilities

Context window

1M tokens (published model limit)

Output budget

384K tokens (published model limit)

• Coding assistance
• Document analysis
• Tool workflows
• reasoning
• streaming
• function_calling
• caching
• structured_output

API pricing

Model introduction

Text reasoning and coding for multi-step engineering, document analysis, and tool workflows. Send source code, requirements, and logs as text. Preserve assistant tool calls and their matching tool results across turns. Convert visual material to text before including it.

Specifications and limits

This model does not support image input. Thinking is enabled by default; controls depend on the route. Include reasoning within your output budget.

Getting started

Create a BulkToken API key

Create a key in API Keys and save it as BULKTOKEN_API_KEY on your server.

Configure the client

Use https://bulktoken.ai/v1 and model ID deepseek-v4-pro.

Send your first request

Call POST /v1/chat/completions. Start with text input and review actual usage in Usage Logs.

FAQ

Which model ID should I use?

Use deepseek-v4-pro exactly. The model must be published and available to your API key.

How is usage priced?

DeepSeek prices follow the official schedule: peak hours are Monday–Friday, 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. All other hours are off-peak. Peak input, output, and cache-read rates are twice the off-peak rates; both tiers retain the 20% discount.

Code examples

See [the DeepSeek V4-Pro integration guide](/docs/deepseek-v4-pro) for Python, Node.js, and cURL examples. Install openai for the Python example.

Python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["BULKTOKEN_API_KEY"], base_url="https://bulktoken.ai/v1")
stream = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[{"role": "user", "content": "Explain a hash table in one sentence."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

cURL

curl https://bulktoken.ai/v1/chat/completions \
  -H "Authorization: Bearer $BULKTOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek-v4-pro", "messages": [{"role": "user", "content": "Hello!"}], "stream": true}'