Skip to main content
DeepSeek

DeepSeek V4.1 Flash pricing, context window and limits

DeepSeek V4.1 Flash costs $0.15 per million input tokens and $0.6 per million output tokens at DeepSeek list price. It accepts up to 1,000,000 tokens of context and returns up to 393,216 tokens.

  • Model id deepseek-flash
  • Snapshot

What does DeepSeek V4.1 Flash cost?​

List prices in US dollars per million tokens
Input$0.15
Output$0.6
Cached input (read)$0.003
Cache write—
Reasoning$0.6

US dollars per million tokens. A dash means no price is published.

How much can DeepSeek V4.1 Flash read and write?​

Token limits
Context window1,000,000
Max output393,216

What can DeepSeek V4.1 Flash do?​

Capabilities
Vision (image input)Yes
Tool callingYes
Structured outputYes
ReasoningYes
Inputtext, image
Outputtext

What does a request to DeepSeek V4.1 Flash cost?​

Cost of example requests at list price, in US dollars
A typical request: 1,000 tokens in, 500 out$0.00045
A long request: 10,000 tokens in, 1,000 out$0.0021
1,000 typical requests$0.45
1 million tokens in and 1 million out$0.75

Input read from the provider's prompt cache costs $0.003 per million tokens instead of $0.15, 98% less. A request that repeats a 1,000-token prompt from the cache costs $0.0003 instead of $0.00045.

Among 4 DeepSeek models with a published price, DeepSeek V4.1 Flash is the cheapest by input price. Its context window is the largest of 4. List prices only; discounts, batch prices and prices above 200K tokens are not shown.

How do I call DeepSeek V4.1 Flash through DVARA?​

Configure the deepseek provider in the DVARA LLM Gateway and send the model id deepseek-flash. DVARA, the AI governance platform, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.

In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set is counted as costing nothing. Every cost record says which price it used.

What should I check before relying on this data?​

The weekly review marked this entry. A person saw each mark and kept the model listed.

  • The cached-input price is outside the usual 10–50% of the input price.
  • The price differs by more than 1% from another published price list.

Which other DeepSeek models are there?​

All 4 DeepSeek models · Search the full catalogue

Which models from other providers are similar to DeepSeek V4.1 Flash?​

These are the closest in context window and input price, one per provider.

Snapshot 4 October 2026. DVARA reviews every price weekly before it is published. Get the whole catalogue as models.json. Prices are list prices in US dollars per million tokens; check your provider contract before you budget.