DeepSeek V4.1 Flash pricing

API list price by DeepSeek · checked Oct 26, 2026
Benchmarks and alternatives →
$0.30 / $1.20per 1M tokens in / out
$0.007cache read · −98%
$0.19per task at non-thinking?

Price sheetper 1M tokens

Input$0.30list
Output$1.20
Cache read$0.007−98% vs input
Context1Mtokens
Saved AA secondary quote for this exact release; not a refreshed first-party tariff.

Cost per task by effort?

non-thinkingAPI default$0.19—
max$0.32—
per task
Same price per token at every effort; the bill grows with reasoning tokens. max costs 1.6× non-thinking.

In DeepSeek's line-upper 1M in / out

DeepSeek OCR 2$0.03 / $0.03−94%
DeepSeek OCR$0.03 / $0.10−91%
DeepSeek R1 Distill Llama 8B$0.20 / $0.32−56%
DeepSeek R1 Distill Qwen 32B$0.27 / $0.27−49%
DeepSeek V4.1 Flash 1017$0.30 / $1.200%
DeepSeek R1 Distill Qwen 14B$0.43 / $1.12+15%
R1 0528$0.39 / $1.63+32%
<

Cheaper for the same workvs DeepSeek V4.1 Flash

MiMo v2.6 Pro thinkingOpen-31%score +88%$0.13
GPT-6.1 Terra high-31%score +78%$0.13
GPT-6.1 Sol low-32%score +71%$0.13
Claude Haiku 5.5 xhigh-36%score +67%$0.12
GPT-6 Luna max-65%score +55%$0.068

Pricing questions

How much does DeepSeek V4.1 Flash cost?›

$0.30 per 1M input tokens and $1.20 per 1M output tokens. Cached input is $0.007. One Intelligence Index task costs about $0.19 at the default effort.

Is DeepSeek V4.1 Flash free to use?›

There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.

How much does prompt caching save?›

Cache reads cost $0.007 per 1M, 98% below the input price.

Is DeepSeek V4.1 Flash cheaper than DeepSeek V4 Flash 0731?›

No: $0.30 / $1.20 against $0.14 / $0.28, 200% more per token.

How does effort change the price?›

The price per token is the same at every effort. Higher effort spends more reasoning tokens: a task costs $0.19 at non-thinking, $0.32 at max.

What is a cheaper alternative to DeepSeek V4.1 Flash?›

MiMo v2.6 Pro at thinking effort costs -31% per task with a score +88% on .