PriceIndex
DeepSeek logo

DeepSeek V4.1 Flash 1017 Pricing & API Specs

deepseek-v4.1-flash-1017
APIProvider site

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model... Built by DeepSeek.

Prices updated

Input price

$0.15

per 1M tokens · Standard

Output price

$0.50

per 1M tokens · Standard

Input limit

1M

tokens

Output limit

944K

tokens

Input formats

TextImageVideoAudioPDF

Output formats

TextImageVideoAudioPDF
Compare

DeepSeek V4.1 Flash 1017 price history

123 price records since 10/18/2026 · 121 changes

DeepSeek V4.1 Flash 1017 cost calculator

Input20M tokens
Output5M tokens

$5.50/month

Standard pricing

    Overview

    What is DeepSeek V4.1 Flash 1017?

    DeepSeek V4.1 Flash 1017 is a text & reasoning and vision model from DeepSeek priced at $0.15 input and $0.50 output per 1M tokens, with a 1M context window. Its low input price suits high-volume work; no AA Intelligence score has been published yet.

    Price: Nemotron 3.5 Super VL (+$0.000)Price: Qwen3.8 Flash (−$0.008)Price: Qwen3.8 Omni Flash (−$0.008)

    Benchmarks

    DeepSeek V4.1 Flash 1017 benchmarks & speed

    How DeepSeek V4.1 Flash 1017 scores on standardized evaluations, and where it lands among every model we track.

    1289

    DesignArena Elo

    Better than 81% of 95 models

    Latency & design

    DesignArena win rate
    48.3%
    Design battles judged
    5,947

    Independent scores from Artificial Analysis and DesignArena · updated 10/30/2026. Higher is better; ranks compare against every model we track with that score.

    Rates

    DeepSeek V4.1 Flash 1017 pricing

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

    Input · Standard

    $0.15

    Per 1M tokens

    Cached input · Standard

    $0.0050

    Per 1M tokens

    Capabilities

    DeepSeek V4.1 Flash 1017 Tools

    Tools available when using DeepSeek V4.1 Flash 1017 through supported provider APIs.

    JSON mode

    Supported

    Reasoning

    Supported

    Where to run it

    DeepSeek V4.1 Flash 1017 API providers

    25 providers serve DeepSeek V4.1 Flash 1017. Prices are per 1M tokens; uptime is the last 24 hours.

    Relacefp4
    Input
    $0.0060
    Output
    $0.50
    Cached
    $0.0050
    Context
    1M
    Uptime
    100%
    OpenInferencefp4
    Input
    $0.02
    Output
    $0.70
    Cached
    $0.0040
    Context
    1M
    Uptime
    100%
    Morphfp8
    Input
    $0.02
    Output
    $0.40
    Cached
    $0.0040
    Context
    1M
    Uptime
    99.93%
    Particle AI
    Input
    $0.03
    Output
    $0.25
    Cached
    $0.0015
    Context
    1M
    Uptime
    100%
    Wafermxfp4
    Input
    $0.04
    Output
    $0.35
    Cached
    $0.01
    Context
    1M
    Uptime
    100%
    Particle AI
    Input
    $0.05
    Output
    $0.50
    Cached
    $0.0030
    Context
    1M
    Uptime
    100%
    Wafermxfp4
    Input
    $0.07
    Output
    $0.50
    Cached
    $0.0065
    Context
    1M
    Uptime
    100%
    DeepInfrafp8
    Input
    $0.08
    Output
    $0.24
    Cached
    $0.0024
    Context
    1M
    Uptime
    100%
    InferenceNetfp8
    Input
    $0.08
    Output
    $0.55
    Cached
    $0.0080
    Context
    1M
    Uptime
    100%
    InferenceNetfp8
    Input
    $0.08
    Output
    $0.55
    Cached
    $0.0080
    Context
    1M
    Uptime
    100%
    PrimeIntellect
    Input
    $0.09
    Output
    $1.20
    Cached
    $0.0048
    Context
    1M
    Uptime
    100%
    Baidufp8
    Input
    $0.10
    Output
    $0.39
    Cached
    $0.0021
    Context
    1M
    Uptime
    99.93%
    DeepInfrafp8
    Input
    $0.10
    Output
    $0.29
    Cached
    $0.0029
    Context
    1M
    Uptime
    100%
    Cloudflare
    Input
    $0.10
    Output
    $0.60
    Cached
    $0.0030
    Context
    1M
    Uptime
    100%
    Sail Researchfp4
    Input
    $0.10
    Output
    $0.15
    Cached
    $0.0067
    Context
    1M
    Uptime
    0%

    Showing 15 of 25

    Strengths and limitations

    Strengths

    • Price rank 73 of 330 tracked models (1 = cheapest, by blended price).
    • Blended price at 3 input : 1 output is $0.24 per 1M tokens.
    • 1M input + 250K output tokens costs about $0.28.
    • Context window 1M vs a median of 262K (4.0× larger).

    Limitations

    • Generated tokens cost 3× more than input tokens, which matters for verbose responses.
    • Large context capacity does not guarantee consistent retrieval across the entire prompt.
    • Benchmarks are directional; test accuracy, latency and reliability on your own workload before committing.

    Public listed prices, checked Nov 9, 2026. Benchmarks as published by their sources. Confirm with the provider.

    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 1017

    DeepSeek V4.1 Flash 1017 is a text & reasoning and vision model from DeepSeek. DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...

    DeepSeek V4.1 Flash 1017 costs $0.15 per million input tokens and $0.50 per million output tokens on standard pricing. A workload of 20M input and 5M output tokens a month is about $5.50.

    DeepSeek V4.1 Flash 1017 accepts up to 1,048,576 tokens (1M) of input and can return up to 943,718 tokens in one response.

    Yes, DeepSeek V4.1 Flash 1017 supports function/tool calling and structured (JSON) outputs. Supported tools: Function calling, Structured outputs, JSON mode, Reasoning, Log probabilities, Deterministic seed, Parallel tool calls, Prompt caching.

    DeepSeek V4.1 Flash 1017 accepts Text, Image as input and produces Text as output.

    DeepSeek V4.1 Flash 1017 is available from 25 API providers: Relace, OpenInference, Morph, Particle AI, Wafer, Particle AI, Wafer, DeepInfra and more. Prices can differ by provider.

    DeepSeek V4.1 Flash 1017 was released by DeepSeek in 2026-10-17.