DeepSeek V4.1 Flash API

Input / 1M tokens$0.251~~$0.286~~

Output / 1M tokens$1.01~~$1.14~~

LLMDeepSeekNew12% below official1M contextPrompt caching

Loading playground…

About DeepSeek V4.1 Flash

DeepSeek V4.1 Flash by DeepSeek is available on API Many from $0.251 per million input tokens and $1.01 per million output tokens, and you call it with the same API key you use for every other model.

It accepts OpenAI-style chat requests with streaming and tools, has a 1M context window and can return up to 393,216 tokens per response.

Prompt caching is supported: cached input tokens are billed at the lower cached rate shown in the price table.

You pay only for successful results: failed or rejected requests are refunded automatically, and every call is recorded in your console with its exact cost.

Related models

−12%

DeepSeek OCRdeepseek-ocr

LLMDeepSeek

$0.05 in · $0.226 outTry it

−12%

DeepSeek R1deepseek-r1

LLMDeepSeekReasoning

$0.493 in · $1.97 outTry it

−12%

DeepSeek R1 0528deepseek-r1-0528

LLMDeepSeekReasoning

$0.449 in · $1.36 outTry it

−12%

DeepSeek R1 250528deepseek-r1-250528

LLMDeepSeekReasoning

$0.493 in · $1.97 outTry it

−12%

DeepSeek V3 0324deepseek-v3-0324

LLMDeepSeek

$0.226 in · $0.905 outTry it

−12%

DeepSeek V3.1 Terminusdeepseek-v3.1-terminus

LLMDeepSeek

$0.449 in · $1.35 outTry it

−12%

DeepSeek V3.2deepseek-v3.2

LLMDeepSeek

$0.226 in · $0.339 outTry it

−12%

DeepSeek V3.2 Expdeepseek-v3.2-exp

LLMDeepSeek

$0.226 in · $0.339 outTry it

Frequently asked questions

How much does the DeepSeek V4.1 Flash API cost?

DeepSeek V4.1 Flash starts at $0.251 per million input tokens and $1.01 per million output tokens on API Many. The price table on this page lists every tier; you are charged only for successful requests.

How do I call DeepSeek V4.1 Flash?

Create an API key in the console, then send a request to /v1/chat/completions with "model": "deepseek-v4.1-flash". The API tab has copy-ready examples in cURL, Python and Node.js.

Is this the official DeepSeek V4.1 Flash model?

Yes. Requests are forwarded to the model maker or an authorized channel with the same parameters, so the output matches the official API.

What happens if a request fails?

Failed, rejected or timed-out requests are not charged. Reserved balance is released automatically and the reason is shown in the call record.