How much does the deepseek-v4-flash-0731 API cost?

On FastMetal, deepseek-v4-flash-0731 is billed per token: $0.1477 per 1M input tokens and $0.2954 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call deepseek-v4-flash-0731 with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "deepseek-v4-flash-0731" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What do I need to try deepseek-v4-flash-0731?

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.

deepseek-v4-flash-0731 API — pricing, context window, how to use

Back to Models

DeepSeek

deepseek-v4-flash-0731

Global: DeepSeek's V4 Flash 0731

Input: $0.1477/M

Output: $0.2954/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

Output

text

Reasoning Configuration

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

How to control thinking, and what it costs

Data policy

Prompt retention: Unknown — we could not confirm
Training: Not used for training

"Unknown" does not mean "safe". It means we could not confirm it.

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Measured performance

Time to first response (p50)1.0s

Throughput (p50)122 tokens/s

Measured through FastMetal's own gateway over the last 30 days (662 first-response samples).

Throughput is sampled once a day: the median of 23 observations over the last 30 days.

Time to first response is measured to the first streamed chunk; throughput counts all output tokens, including reasoning tokens. These are observations, not a performance guarantee.

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-flash-0731",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How deepseek-v4-flash-0731 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 **“strawberry”** is spelled: **s t r a w b e r r y** Now count the **r**’s: 1. First **r** in “str” → **1** 2. Second **r** in “be**r**ry” → **2** 3. Third **r** in “ber**r**y” → **3** So, there are **3** “r”s in **“strawberry”**.

5.6s response375 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 happens because `users` is `undefined` when the component renders. Your code calls `users.map(...)`, but you can’t call `.map()` on `undefined`. ## Why this happens The `UserList` component expects a prop called `users` that is an array, but nothing passed it, or it was explicitly set to `undefined`. Example of calling it wrong: ```jsx <UserList /> // users is undefined <UserList users={undefined} /> ``` ## How to fix it ### 1. Provide a default value for `users` ```jsx function UserList({ users = [] }) { return ( <ul> {users.map(user => <li key={user.id}>{user.name}</li>)} </ul> ); } ``` Now if `users` is missing, it will default to an empty ar…

12.0s response514 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 revised version with clearer control flow, better exception handling, and more idiomatic Python: ```python import time from typing import Any import requests def get_data(url: str, retries: int = 3, timeout: int = 10) -> list[dict[str, Any]]: """ Fetch a JSON list of items from url and return only active items as [{"name": ..., "id": ...}, ...]. """ with requests.Session() as session: for attempt in range(1, retries + 1): try: response = session.get(url, timeout=timeout) response.raise_for_status() data = response.json() return [ {"name": item["name"], "id…

108.8s response11660 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the deepseek-v4-flash-0731 API cost?: On FastMetal, deepseek-v4-flash-0731 is billed per token: $0.1477 per 1M input tokens and $0.2954 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call deepseek-v4-flash-0731 with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "deepseek-v4-flash-0731" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What do I need to try deepseek-v4-flash-0731?: 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.