---
title: "DeepSeek V4.1 Flash API Pricing & Context | RZ Automate"
description: "DeepSeek V4.1 Flash costs $0.30 per 1M input and $1.20 per 1M output tokens at peak, half off-peak. It replaced V4 Flash. 1M context."
url: https://rzautomate.com/models/deepseek-v4-1-flash
---

[All AI models](https://rzautomate.com/models)

[DeepSeek](https://rzautomate.com/models?provider=DeepSeek#models)

Small model

# DeepSeek V4.1 Flash API pricing and specs

DeepSeek V4.1 Flash costs $0.30 per million input tokens and $1.20 per million output tokens at peak, and half that off-peak. It replaced DeepSeek V4 Flash in September 2026\. DeepSeek V4.1 Flash reads text and images, holds 1 million tokens, and ships open weights under MIT.

[Try the cost calculator](#calculator)
[Compare models →](#compare)

* Tool calling
* Vision
* Reasoning
* Structured output
* Open weights

Input

$0.30 / 1M

Output

$1.20 / 1M

Context

1M tokens

Max output

384K tokens

Looking for DeepSeek V4 Flash? It was retired on September 10, 2026\. Its old model ID now runs V4.1 Flash. 

Pricing

## DeepSeek V4.1 Flash API pricing

Output costs 4× input. Cached input is almost free, so reuse long prompts.

Peak hours run 1 to 4 am and 6 to 10 am UTC, Monday to Friday. Every other hour and all weekend is off-peak.

Prices checked November 14, 2026 on DeepSeek's pricing page.

__DeepSeek V4.1 Flash API pricing per 1M tokens in US dollars__
| Price type   | Peak per 1M | Off-peak per 1M |
| ------------ | ----------- | --------------- |
| Input        | $0.30       | $0.15           |
| Cached input | $0.006      | $0.003          |
| Output       | $1.20       | $0.60           |

Calculator

## DeepSeek V4.1 Flash cost calculator

Pick a job or enter your own numbers. We use peak rates so the estimate stays safe.

Start from a job

1,000 support emails100 invoices500 leads

Rate period

NowOff-peak

Requests per monthInput tokens per requestOutput tokens per requestShare of input from cache (%)

Uses peak rates. Off-peak halves the result. Ignores tax and cache savings unless you set them.

Per month

$1.08

Cost per request

$0.0011

Per year

$12.96

Same job on other models

* [Claude Haiku 5.5$0.40](https://rzautomate.com/models/claude-haiku-5-5)
* [Gemini 3.8 Flash$3.00](https://rzautomate.com/models/gemini-3-8-flash)
* [DeepSeek V4 Pro$4.22](https://rzautomate.com/models/deepseek-v4-pro)

* [AI customer support agents](https://rzautomate.com/services/ai-customer-support-agents)
* [AI document processing](https://rzautomate.com/services/ai-document-processing)
* [AI lead generation & CRM automation](https://rzautomate.com/services/ai-lead-generation)

Want this costed on your real data? [Book a free 30-min call](https://rzautomate.com/book?service=support-agents&source=models&model=deepseek-v4-1-flash)

Specs

## DeepSeek V4.1 Flash context window and specs

Context window

1M tokens

Max output

384K tokens

__DeepSeek V4.1 Flash specifications__
| Spec              | Details                                 |
| ----------------- | --------------------------------------- |
| Input types       | Text, image                             |
| Output types      | Text                                    |
| Tool calling      | Yes                                     |
| Structured output | Yes                                     |
| Reasoning         | Yes, up to max effort                   |
| Knowledge cutoff  | Not published                           |
| Release date      | September 10, 2026                      |
| Open weights      | Yes                                     |
| License           | MIT                                     |
| API model ID      | deepseek-flash                          |
| Old model ID      | deepseek-v4-flash (now runs V4.1 Flash) |

Availability

## Where to access DeepSeek V4.1 Flash

Use deepseek-flash in new code. The old deepseek-v4-flash ID still works for now.

__Platforms that offer DeepSeek V4.1 Flash__
| Platform     | Model ID       | Input $/1M | Output $/1M |
| ------------ | -------------- | ---------- | ----------- |
| DeepSeek API | deepseek-flash | $0.30      | $1.20       |
| OrcaRouter   | —              | $0.30      | $1.20       |

Free access

## Is DeepSeek V4.1 Flash free?

The DeepSeek V4.1 Flash API is paid, with no free tier. It is one of the cheapest capable models, though. The weights are free under MIT if you can host a model of this size.

* No free API tier
* Free weights under MIT
* Needs an 8-GPU node to self-host

Alternatives

## DeepSeek V4.1 Flash vs alternatives

DeepSeek V4.1 Flash is not the cheapest per token. It is the cheapest with open weights and a 1M window.

__DeepSeek V4.1 Flash compared with alternatives__
| Model                                        | Input $/1M | Output $/1M | Context | Why pick it                       |
| -------------------------------------------- | ---------- | ----------- | ------- | --------------------------------- |
| DeepSeek V4.1 Flash                          | $0.30      | $1.20       | 1M      | Open weights, very low price      |
| [DeepSeek V4 Pro](https://rzautomate.com/models/deepseek-v4-pro)   | $1.32      | $3.96       | 1M      | Same family, deeper reasoning     |
| [Gemini 3.8 Flash](https://rzautomate.com/models/gemini-3-8-flash) | $0.75      | $3.75       | 1M      | Google stack, price rises in 2027 |
| [Claude Haiku 5.5](https://rzautomate.com/models/claude-haiku-5-5) | $0.10      | $0.50       | 1M      | Cheapest per token under 100K     |
| [GPT-6 Luna](https://rzautomate.com/models/gpt-6-luna)             | $0.10      | $0.50       | 1.05M   | Cheapest OpenAI option            |

[See all AI models →](https://rzautomate.com/models)

Fit

## What DeepSeek V4.1 Flash is good for

### A good fit for

* Support replies at high volume
* Sorting, tagging and summaries
* Batch jobs run off-peak

### Not the best pick for

* Hard multi-step reasoning
* Strict data residency outside China
* Audio or video input

Our take

We use DeepSeek V4.1 Flash for high-volume support and sorting work, and step up to a bigger model only where it fails.

* [AI customer support agents →](https://rzautomate.com/services/ai-customer-support-agents)

History

## DeepSeek V4 versions

V4.1 Flash replaced V4 Flash on September 10, 2026\. A refreshed checkpoint went live on October 17 at the same price.

1. [DeepSeek V4.1 Flash](https://rzautomate.com/models/deepseek-v4-1-flash)Latest  
2026-09-10  
$0.30 in / $1.20 out per 1M
2. [DeepSeek V4 Pro (0813)](https://rzautomate.com/models/deepseek-v4-pro)Latest  
2026-08-13  
$1.32 in / $3.96 out per 1M
3. DeepSeek V4 FlashDeprecated  
2026-04-24  
$0.44 in / $1.32 out per 1M
4. DeepSeek V3.2Deprecated  
2025-12-01  
$0.28 in / $0.42 out per 1M

Questions

## DeepSeek V4.1 Flash FAQ

Prices checked November 14, 2026.

### How much does DeepSeek V4.1 Flash cost?

DeepSeek V4.1 Flash costs $0.30 per million input tokens and $1.20 per million output tokens at peak. Off-peak it is $0.15 and $0.60\. Cached input is $0.006 at peak. Answering 1,000 support emails a month with DeepSeek V4.1 Flash costs about $1.08 at peak rates.

### Is DeepSeek V4.1 Flash free?

DeepSeek V4.1 Flash has no free API tier. You pay per token, and prices halve outside peak hours. The weights are free to download under the MIT license, so you can run DeepSeek V4.1 Flash on your own servers, but it needs roughly an 8-GPU node.

### What is the DeepSeek V4.1 Flash context window?

DeepSeek V4.1 Flash has a 1 million token context window and can write up to 384K tokens per reply. It takes text and image input. The price per token stays the same across the full window, so DeepSeek V4.1 Flash has no long-context surcharge.

### When was DeepSeek V4.1 Flash released?

DeepSeek V4.1 Flash went live on the DeepSeek API on September 10, 2026, replacing DeepSeek V4 Flash the same day. On October 17, 2026, DeepSeek swapped in a refreshed checkpoint under the same model ID and price. DeepSeek V4.1 Flash is the current Flash model.

### What is the DeepSeek V4.1 Flash API model ID?

The DeepSeek V4.1 Flash API model ID is deepseek-flash. The old IDs deepseek-v4-flash and deepseek-v4-flash-vision-exp still work for now, but they run DeepSeek V4.1 Flash and bill at its rates. DeepSeek recommends deepseek-flash for all new requests, so update old code before those aliases are removed.

### DeepSeek V4.1 Flash vs DeepSeek V4 Pro, which is cheaper?

DeepSeek V4.1 Flash is about four times cheaper. It costs $0.30 input and $1.20 output per million tokens at peak, against $1.32 and $3.96 for DeepSeek V4 Pro. For 1,000 support emails that is $1.08 a month on DeepSeek V4.1 Flash versus $4.22 on V4 Pro.

## Want DeepSeek V4.1 Flash working inside your tools?

We build AI agents and automations that let a business grow without adding headcount. On the call we tell you which model fits your work and what it costs at your volume.

* Email  
[choaib@rzautomate.com](mailto:choaib@rzautomate.com)
* Reply time  
Within two hours
* 160automations running in production
* 32businesses served
* 2,000 hrsof manual work taken off clients every month

Or book directly at [cal.com/rzautomate/30min](https://cal.com/rzautomate/30min)

Want the full picture? See [AI customer support agents](https://rzautomate.com/services/ai-customer-support-agents).

Keep comparing

## Compare more models

* [DeepSeek V4 ProThe bigger DeepSeek for harder tasks](https://rzautomate.com/models/deepseek-v4-pro)
* [Gemini 3.8 FlashGoogle's fast low-cost model](https://rzautomate.com/models/gemini-3-8-flash)
* [Claude Haiku 5.5Anthropic's smallest model](https://rzautomate.com/models/claude-haiku-5-5)

1. [Home](https://rzautomate.com/)
2. [AI Models](https://rzautomate.com/models)
3. [DeepSeek](https://rzautomate.com/models?provider=DeepSeek#models)
4. DeepSeek V4.1 Flash
