DeepSeek V4 Flash vs DeepSeek V4.1 Flash

As of October 21, 2026, DeepSeek V4 Flash costs 233% more per input token than DeepSeek V4.1 Flash ($0.30 vs $0.09 per 1M) and has a 1,000,000-token context window versus 1,048,576.

Prices from LiteLLM's price fileChecked October 21, 2026

DeepSeek V4 Flash vs DeepSeek V4.1 Flash side by side

Headline prices in US dollars per 1M tokens: each model's own lab where it sells it, otherwise its cheapest provider. Source: LiteLLM model price file, as of October 21, 2026.
	DeepSeek V4 Flash	DeepSeek V4.1 Flash
Input, per 1M tokens	$0.30	$0.09
Output, per 1M tokens	$1.20	$0.30
Cache read, per 1M tokens	$0.006	$0.006
Cache write, per 1M tokens	$0	–
Context window	1,000,000 tokens	1,048,576 tokens
Max output	393,216 tokens	1,048,576 tokens
Image input	Yes	Yes
Tool calling	Yes	Yes
Structured output (JSON)	Yes	Yes
Prompt caching	Yes	Yes
Reasoning	Yes	Yes
Providers on LiteLLM	23	14
Price shown is from	DeepSeek	Sail
Added to LiteLLM	June 2026	September 11, 2026

Cheapest provider for each

DeepSeek V4 Flash: DeepInfra at $0.08 input and $0.18 output per 1M tokens (deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731)
DeepSeek V4.1 Flash: Sail at $0.09 input and $0.30 output per 1M tokens (sail/deepseek-ai/DeepSeek-V4.1-Flash)

Benchmark scores

From the Epoch AI Benchmarking Hub (CC BY 4.0), data as of October 13, 2026. Some results were run by Epoch and others collected by Epoch from each benchmark's own leaderboard, linked in the first column. Each model's best reported reasoning setting is shown in brackets. Higher is better. Only benchmarks with a score for both models are shown.
Benchmark	DeepSeek V4 Flash	DeepSeek V4.1 Flash
Coding and agents
FrontierCode	18.8%	43.9% (high)
Reasoning and knowledge
GPQA Diamond	91.0% (max)	89.8% (max)
ARC-AGI-2	61.4% (max)	72.9% (max)
SimpleQA Verified	33.6% (max)	42.9% (max)
Math
FrontierMath (tiers 1-3)	57.5% (max)	67.4% (max)
FrontierMath (tier 4)	24.4% (max)	26.8% (max)
OTIS Mock AIME 2024-2025	94.4% (max)	98.3% (max)

When to pick which

Pick DeepSeek V4.1 Flash for

Costs 70% less per input token: $0.09 vs $0.30 per 1M.
Returns up to 1,048,576 tokens per response, vs 393,216.

From differences in the data above only; where the data is equal, no reason is given.

Call DeepSeek V4 Flash or DeepSeek V4.1 Flash with LiteLLM

Both use the OpenAI format through LiteLLM, so switching is a model name change. Set each provider's API key in the environment first.

Python SDK

from litellm import completion

messages = [{"role": "user", "content": "Hello!"}]

# DeepSeek V4 Flash
response = completion(model="deepseek-v4-flash", messages=messages)

# DeepSeek V4.1 Flash
response = completion(model="sail/deepseek-ai/DeepSeek-V4.1-Flash", messages=messages)

# DeepSeek V4 Flash, falling back to DeepSeek V4.1 Flash if the call fails
response = completion(model="deepseek-v4-flash", messages=messages, fallbacks=["sail/deepseek-ai/DeepSeek-V4.1-Flash"])

FAQ

Which is cheaper, DeepSeek V4 Flash or DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash is cheaper at 3 input tokens per output token: $0.1425 per 1M tokens blended ($0.09 input, $0.30 output), versus $0.525 ($0.30 and $1.20) for DeepSeek V4 Flash, as of October 21, 2026.

Which has the larger context window, DeepSeek V4 Flash or DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash has the larger context window: 1,048,576 tokens, versus 1,000,000 for DeepSeek V4 Flash.

Can I switch from DeepSeek V4 Flash to DeepSeek V4.1 Flash without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "deepseek-v4-flash" to "sail/deepseek-ai/DeepSeek-V4.1-Flash", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.