PriceIndex
DeepSeek logo

DeepSeek V4.1 Flash

deepseek-v4.1-flash
APIProvider site

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... Built by DeepSeek.

Prices updated

Input price

$0.05

per 1M tokens · Standard

Output price

$1.20

per 1M tokens · Standard

Input limit

1M

tokens

Output limit

944K

tokens

Input formats

TextImageVideoAudioPDF

Output formats

TextImageVideoAudioPDF
Compare

DeepSeek V4.1 Flash price history

4 price records since 9/25/2026 · 2 changes

DeepSeek V4.1 Flash cost calculator

Input20M tokens
Output5M tokens

$7.00/month

Standard pricing

    Overview

    What is DeepSeek V4.1 Flash?

    DeepSeek V4.1 Flash is a text & reasoning and vision model from DeepSeek. 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... Its 1M context window and $0.05 input price make it a candidate for cost-sensitive, high-throughput applications.

    Image understandingDocument analysisContent workflowsClassification

    Benchmarks

    DeepSeek V4.1 Flash benchmarks & speed

    How DeepSeek V4.1 Flash scores on standardized evaluations, and where it lands among every model we track.

    39.5

    Intelligence Index

    Better than 87% of 153 models

    213tok/s

    Output speed

    Better than 92% of 119 models

    1325

    DesignArena Elo

    Better than 93% of 81 models

    Reasoning

    HLE

    39.2%

    Humanity's Last Exam · top 23%

    Coding

    SciCode

    51.9%

    Python for scientific computing · top 40%

    Latency & design

    Time to first token
    1.05s
    DesignArena win rate
    52.1%
    Design battles judged
    39,579

    Independent scores from Artificial Analysis and DesignArena · updated 10/8/2026. Higher is better; ranks compare against every model we track with that score.

    Rates

    DeepSeek V4.1 Flash pricing

    Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.

    Input · Standard

    $0.05

    Per 1M tokens

    Cached input · Standard

    $0.02

    Per 1M tokens

    Capabilities

    DeepSeek V4.1 Flash Tools

    Tools available when using DeepSeek V4.1 Flash through supported provider APIs.

    Function calling

    Supported

    Structured outputs

    Supported

    JSON mode

    Supported

    Reasoning

    Supported

    Built-in web search

    Not supported

    Log probabilities

    Supported

    Deterministic seed

    Supported

    Parallel tool calls

    Not supported

    Prompt caching

    Supported

    Strengths and limitations

    Strengths

    • Low input cost at $0.05 per million tokens suits high-volume workloads.
    • 1M context supports large documents, repositories and extended conversations.
    • Supports text & reasoning and vision workloads in one model.

    Limitations

    • Generated tokens cost 24× more than input tokens, which matters for verbose responses.
    • Large context capacity does not guarantee consistent retrieval across the entire prompt.
    • Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.

    Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.

    Same provider

    More models from DeepSeek

    View provider →
    164K

    $0.29 in · $1.14 out

    View model
    164K

    $0.25 in · $0.95 out

    View model
    R1 0528

    DeepSeek

    164K

    $0.50 in · $2.15 out

    View model
    8K

    $0.80 in · $0.80 out

    View model

    Frequently asked questions about DeepSeek V4.1 Flash

    DeepSeek V4.1 Flash is a text & reasoning and vision model from DeepSeek. 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...