How much does the DeepSeek V4 Flash API cost?

On FastMetal, DeepSeek V4 Flash is billed per token: $0.095 per 1M input tokens and $0.1899 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 with the OpenAI SDK?

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

What is the context window of DeepSeek V4 Flash?

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

How does DeepSeek V4 Flash rank?

#91 on the public arena's Japanese board (ELO 1,399). Ranks move as the leaderboard is updated.

What do I need to try DeepSeek V4 Flash?

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-flash

DeepSeek V4 Flash

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

4/24/2026

1,048,576 tokens

#84 Text (Multi-Turn)

Input: $0.095/M

Output: $0.1899/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

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

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)1.1s

Throughput (p50)40 tokens/s

Measured through FastMetal's own gateway over the last 30 days (652 first-response samples).

Throughput is sampled once a day: the median of 27 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",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How DeepSeek V4 Flash 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 as s-t-r-a-w-b-e-r-r-y. I go through each letter: s (no), t (no), r (yes, first), a (no), w (no), b (no), e (no), r (yes, second), r (yes, third), y (no). Thus, there are three 'r's.

3.9s response251 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 occurs because `users` is `undefined` when the component tries to call `.map()` on it. ## Why this happens Your component expects `users` to be an array, but it's receiving `undefined` as a prop. This typically happens when: 1. The parent component doesn't pass the `users` prop 2. The data fetching hasn't completed yet (async data loading) 3. The API response is missing the expected data structure ## How to fix it ### Option 1: Default prop value (Recommended for initial state) ```jsx function UserList({ users = [] }) { return ( <ul> {users.map(user => <li key={user.id}>{user.name}</li>)} </ul> ); } ``` ### Option 2: Guard clause (More explicit) ```jsx func…

6.3s response422 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 comprehensive review with suggested improvements: ## Issues Identified: 1. **Import at wrong location** - Imports inside functions are inefficient and non-standard 2. **Bare `except:` clause** - Catches all exceptions including `KeyboardInterrupt`, `SystemExit` 3. **Missing error handling granularity** - Should distinguish between retryable and non-retryable errors 4. **Duplicate sleep logic** - Same sleep in `else` and `except` blocks 5. **Unnecessary variable** - `data` is only used once 6. **Inefficient list building** - Manual loop instead of list comprehension 7. **Hardcoded error message** - No logging or error context 8. **Missing type hints** - No type annotations 9. **Fun…

12.6s response987 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the DeepSeek V4 Flash API cost?: On FastMetal, DeepSeek V4 Flash is billed per token: $0.095 per 1M input tokens and $0.1899 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 with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "deepseek-v4-flash" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of DeepSeek V4 Flash?: 1,048,576 tokens, shared between the prompt and the response.
How does DeepSeek V4 Flash rank?: #91 on the public arena's Japanese board (ELO 1,399). Ranks move as the leaderboard is updated.
What do I need to try DeepSeek V4 Flash?: 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.

Try DeepSeek V4 Flash right now

DeepSeek V4 Flash is available on FastMetal through one API key. Start in the browser, or call it from the OpenAI SDK.

Create a free account

Leaderboard

Text

russianELO: 1,433

#102

CodingELO: 1,484

#106

MathELO: 1,424

#124

Creative WritingELO: 1,408

#96

Instruction FollowingELO: 1,428

#99

Hard PromptsELO: 1,459

#102

Multi-TurnELO: 1,453

#84

OverallELO: 1,436

#105

JapaneseELO: 1,399

#91

ChineseELO: 1,469

#110

KoreanELO: 1,393

#88

EnglishELO: 1,445

#107

frenchELO: 1,450

#111

germanELO: 1,426

#107

spanishELO: 1,432

#104

Rankings: LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, snapshot 2026-10-22; category names mapped and ratings rounded by FastMetal.