How much does the DeepSeek V4 Pro API cost?

On FastMetal, DeepSeek V4 Pro is billed per token in yen: ¥341.32 per 1M input tokens and ¥684.42 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call DeepSeek V4 Pro with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "deepseek-v4-pro" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of DeepSeek V4 Pro?

1,048,576 tokens, shared between the prompt and the response.

How does DeepSeek V4 Pro rank?

#21 on the public arena's Japanese board (ELO 1,462). Ranks move as the leaderboard is updated.

What do I need to try DeepSeek V4 Pro?

Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Back to Models

deepseek/deepseek-v4-pro

DeepSeek V4 Pro

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

4/24/2026

1,048,576 tokens

#21 Text (Japanese)

Input: ¥341.317/M

Output: ¥684.421/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

Output

text

Supported Parameters

frequency_penalty

include_reasoning

logit_bias

logprobs

max_tokens

min_p

presence_penalty

reasoning

reasoning_effort

repetition_penalty

response_format

seed

stop

structured_outputs

temperature

tool_choice

tools

top_k

top_logprobs

top_p

Max Output Tokens

384,000

Reasoning Configuration

Default: Thinking on (effort: high)
Selectable effort levels: xhigh
high
Turning thinking off: Possible (reasoning.enabled: false)

How to control thinking, and what it costs

Code Examples

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

How DeepSeek V4 Pro actually answers

Real responses to our standard prompts, recorded on FastMetal.

Count the number of 'r's in 'strawberry'

Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

The word is "strawberry". Let's count the occurrences of the letter 'r' step by step: 1. Write the word: s t r a w b e r r y 2. Examine each character: - s: not an 'r' - t: not an 'r' - r: is an 'r' → count 1 - a: not an 'r' - w: not an 'r' - b: not an 'r' - e: not an 'r' - r: is an 'r' → count 2 - r: is an 'r' → count 3 - y: not an 'r' 3. Total number of 'r's = 3. Therefore, there are **3** 'r's in "strawberry".

7.3s response1136 output tokens

Debug This Error

I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

The error is occurring because `users` is `undefined` when the component renders, and you're trying to call `.map()` on it. This typically happens when the data hasn't been loaded yet or wasn't passed correctly to the component. ## Here are several ways to fix this: ### 1. **Add a default value with empty array (Simplest fix)** ```javascript function UserList({ users = [] }) { return ( <ul> {users.map(user => <li key={user.id}>{user.name}</li>)} </ul> ); } ``` ### 2. **Add a conditional check** ```javascript function UserList({ users }) { if (!users) { return <div>No users found</div>; } return ( <ul> {users.map(user => <li key={user.id}>{user.name}<…

6.9s response442 output tokens

Code Review

Please review the following Python function and suggest improvements for readability, performance, and best practices: def get_data(url, retries=3): import requests import time for i in range(retries):…

Here’s a review of your `get_data` function, highlighting issues and suggesting improvements. ## Overall Observations - The function works but has several readability, robustness, and maintainability issues. - Imports are inside the function, bare `except` hides errors, and the filtering logic is not Pythonic. - No type hints or docstring, making it harder to use and understand. ## Specific Improvements ### 1. Move Imports to the Top of the Module **Why:** Imports inside a function are executed every time the function is called, which is slightly slower and violates PEP 8 style guidelines. **Before:** ```python def get_data(url, retries=3): import requests import time # ... `…

40.5s response2277 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the DeepSeek V4 Pro API cost?: On FastMetal, DeepSeek V4 Pro is billed per token in yen: ¥341.32 per 1M input tokens and ¥684.42 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call DeepSeek V4 Pro with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "deepseek-v4-pro" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of DeepSeek V4 Pro?: 1,048,576 tokens, shared between the prompt and the response.
How does DeepSeek V4 Pro rank?: #21 on the public arena's Japanese board (ELO 1,462). Ranks move as the leaderboard is updated.
What do I need to try DeepSeek V4 Pro?: Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.