AiCostCompare

DeepSeek V4.1 Flash

by DeepSeek · deepseek/deepseek-v4.1-flash · #101 cheapest of 422 paid models

Prices updated Sep 20, 2026, 12:34 AM UTC · refreshed hourly

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol

Pricing

Input

$0.15

per 1M tokens

Output

$0.60

per 1M tokens

Blended (3:1)

$0.262

3 input : 1 output

Cache read

$0.0030

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for DeepSeek V4.1 Flash with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.262$0.0159
50%$0.207$0.00855−46%
90%$0.163$0.00267−83%

*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.

What a request costs

WorkloadInput tokensOutput tokensCost / requestCost / 1K requests
Short chat message500300$0.000255$0.255
Document summary8,0001,000$0.0018$1.80
Codebase question (RAG)30,0002,000$0.0057$5.70
Long-context analysis150,0005,000$0.0255$25.50

Performance

Intelligence Index

39.5

AA composite quality

Coding Index

Math Index

Agentic Index

Output speed

225 tok/s

median

Time to first token

0.82s

median

Time to first answer

9.70s

after reasoning tokens

Artificial Analysis benchmarks

BenchmarkScore
Humanity's Last Exam39.2%
SciCode51.9%
AA-LCR (Long Context Reasoning)84.0%

Specs

Context window

1.05M

tokens

Max output

384K

tokens

Input modalities

text, image

Tokenizer

DeepSeek