DeepSeek: DeepSeek V4 Flash

deepseek
$0.14output / 1M tokens · input $0.05/M

Best price — Output ($/1M tokens)

Markets

One row per access path (venue → underlying provider). Prices are each venue's published list price; performance is measured by Artificial Analysis. Your actual bill may vary by routing settings, fallbacks, region / ZDR, long-context tiers, and request features (JSON mode, tools, vision).

  • #
    1
    Provider
    openrouter → streamlake
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.07
    Output $ / 1M tokens
    $0.14
    Cache read $ / 1M tokens
    $0.01
    -50.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    2
    Provider
    openrouter → wafer
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.7
    Output $ / 1M tokens
    $0.17
    Cache read $ / 1M tokens
    $0.2
    -39.3% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    3
    Provider
    deepinfra
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.09
    Output $ / 1M tokens
    $0.18
    Cache read $ / 1M tokens
    $0.02
    -35.7% vs consensus
    TTFT
    751ms
    reasoning 1.1s
    Throughput
    67.2 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    4
    Provider
    openrouter → deepinfra
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.09
    Output $ / 1M tokens
    $0.18
    Cache read $ / 1M tokens
    $0.02
    -35.7% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    5
    Provider
    gmi
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.09
    Output $ / 1M tokens
    $0.18
    Cache read $ / 1M tokens
    $0.02
    -35.0% vs consensus
    TTFT
    2.8s
    reasoning 12.8s
    Throughput
    113.2 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    6
    Provider
    openrouter → deepseek
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.09
    Output $ / 1M tokens
    $0.18
    Cache read $ / 1M tokens
    $0.02
    -35.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    7
    Provider
    openrouter → gmicloud
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.09
    Output $ / 1M tokens
    $0.18
    Cache read $ / 1M tokens
    $0.02
    -35.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    8
    Provider
    openrouter → venice
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.19
    Cache read $ / 1M tokens
    $0.02
    -31.3% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    9
    Provider
    openrouter → digitalocean
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.2
    Cache read $ / 1M tokens
    $0.02
    -30.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    10
    Provider
    siliconflow
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.03
    +0.0% vs consensus
    TTFT
    1.9s
    reasoning 1.7s
    Throughput
    94.3 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    11
    Provider
    openrouter → siliconflow
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.03
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    12
    Provider
    fireworks
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.03
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    13
    Provider
    wandb
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.07
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    14
    Provider
    novita → deepseek
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.03
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    15
    Provider
    openrouter → atlas-cloud
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.03
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    16
    Provider
    openrouter → baidu
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.03
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    17
    Provider
    openrouter → parasail
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.07
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    18
    Provider
    openrouter → qwen
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.3
    Cache read $ / 1M tokens
    $0.03
    +7.1% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    19
    Provider
    dashscope
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.2
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    $0.04
    +42.9% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    20
    Provider
    openrouter → relace
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.05
    Output $ / 1M tokens
    $0.45
    Cache read $ / 1M tokens
    $0.05
    +60.7% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    21
    Provider
    openrouter → mancer
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.19
    Output $ / 1M tokens
    $0.5
    Cache read $ / 1M tokens
    —
    +78.6% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    22
    Provider
    azure → azure-ai
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.19
    Output $ / 1M tokens
    $0.51
    Cache read $ / 1M tokens
    $0.03
    +82.1% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    23
    Provider
    openrouter → azure
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.21
    Output $ / 1M tokens
    $0.56
    Cache read $ / 1M tokens
    $0.03
    +100.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    24
    Provider
    deepseek
    Class
    Official
    $ / 1M tokens
    Input $ / 1M tokens
    $0.3
    Output $ / 1M tokens
    $1.2
    Cache read $ / 1M tokens
    $0.01
    +328.6% vs consensus
    TTFT
    1.2s
    reasoning 1.3s
    Throughput
    113.1 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    25
    Provider
    openrouter → cloudflare
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.44
    Output $ / 1M tokens
    $1.32
    Cache read $ / 1M tokens
    $0.01
    +371.4% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    26
    Provider
    openrouter → open-inference
    Class
    Reseller
    Disabled by openrouter · disabled · fp4
    $ / 1M tokens
    Input $ / 1M tokens
    $0.003
    Output $ / 1M tokens
    $0.14
    Cache read $ / 1M tokens
    $0.003
    -51.4% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    27
    Provider
    openrouter → dekallm
    Class
    Reseller
    Disabled by openrouter · disabled · unknown
    $ / 1M tokens
    Input $ / 1M tokens
    $0.09
    Output $ / 1M tokens
    $0.18
    Cache read $ / 1M tokens
    $0.02
    -35.7% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    28
    Provider
    openrouter → sail-research
    Class
    Reseller
    Disabled by openrouter · disabled · fp4
    $ / 1M tokens
    Input $ / 1M tokens
    $0.09
    Output $ / 1M tokens
    $0.18
    Cache read $ / 1M tokens
    $0.02
    -35.7% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    29
    Provider
    makora
    Class
    Direct host
    Disabled by makora · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.09
    Output $ / 1M tokens
    $0.2
    Cache read $ / 1M tokens
    —
    -30.4% vs consensus
    TTFT
    652ms
    reasoning 711ms
    Throughput
    232.3 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    30
    Provider
    openrouter → akashml
    Class
    Reseller
    Disabled by openrouter · disabled · fp8
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.2
    Cache read $ / 1M tokens
    $0.01
    -30.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    31
    Provider
    baseten
    Class
    Direct host
    Disabled by baseten · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.26
    Cache read $ / 1M tokens
    —
    -7.1% vs consensus
    TTFT
    572ms
    Throughput
    329.2 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    32
    Provider
    openrouter → reka
    Class
    Reseller
    Disabled by openrouter · disabled · unknown
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.26
    Cache read $ / 1M tokens
    $0.03
    -7.1% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    33
    Provider
    openrouter → io-net
    Class
    Reseller
    Disabled by openrouter · disabled · fp8
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.07
    -0.7% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    34
    Provider
    openrouter → morph
    Class
    Reseller
    Disabled by openrouter · disabled · unknown
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.07
    -0.7% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    35
    Provider
    systalyze
    Class
    —
    Disabled by systalyze · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    —
    +0.0% vs consensus
    TTFT
    1.1s
    Throughput
    326.9 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    36
    Provider
    coreweave
    Class
    Direct host
    Disabled by coreweave · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.07
    +0.0% vs consensus
    TTFT
    1.6s
    reasoning 2.0s
    Throughput
    76.0 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    37
    Provider
    bitdeer
    Class
    Direct host
    Disabled by bitdeer · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    —
    +0.0% vs consensus
    TTFT
    1.3s
    Throughput
    140.9 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    38
    Provider
    crusoe
    Class
    Direct host
    Disabled by crusoe · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    —
    +0.0% vs consensus
    TTFT
    905ms
    Throughput
    306.1 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    39
    Provider
    databricks
    Class
    Direct host
    Disabled by databricks · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    —
    +0.0% vs consensus
    TTFT
    1.8s
    Throughput
    123.4 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    40
    Provider
    digitalocean
    Class
    Direct host
    Disabled by digitalocean · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    —
    +0.0% vs consensus
    TTFT
    909ms
    Throughput
    71.1 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    41
    Provider
    nebius
    Class
    Direct host
    Disabled by nebius · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    —
    +0.0% vs consensus
    TTFT
    1.6s
    Throughput
    264.6 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    42
    Provider
    novita
    Class
    Direct host
    Disabled by novita · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.03
    +0.0% vs consensus
    TTFT
    1.8s
    reasoning 1.9s
    Throughput
    154.6 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    43
    Provider
    parasail
    Class
    Direct host
    Disabled by parasail · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.07
    +0.0% vs consensus
    TTFT
    1.2s
    reasoning 1.4s
    Throughput
    125.0 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    44
    Provider
    wafer
    Class
    Direct host
    Disabled by wafer · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    —
    +0.0% vs consensus
    TTFT
    710ms
    Throughput
    231.5 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    45
    Provider
    openrouter → ambient
    Class
    Reseller
    Disabled by openrouter · disabled · fp4
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.03
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    46
    Provider
    openrouter → coreweave
    Class
    Reseller
    Disabled by openrouter · disabled · fp8
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.07
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    47
    Provider
    openrouter → fireworks
    Class
    Reseller
    Disabled by openrouter · disabled · unknown
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.03
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    48
    Provider
    openrouter → ionstream
    Class
    Reseller
    Disabled by openrouter · disabled · fp4
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.07
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    49
    Provider
    openrouter → novita
    Class
    Reseller
    Disabled by openrouter · disabled · fp8
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.03
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    50
    Provider
    openrouter → wandb
    Class
    Reseller
    Disabled by openrouter · disabled · fp8
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.07
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    51
    Provider
    openrouter → wandb-legacy
    Class
    Reseller
    Disabled by openrouter · disabled · fp8
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    $0.07
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    52
    Provider
    primalabs
    Class
    —
    Disabled by primalabs · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.28
    Cache read $ / 1M tokens
    —
    +0.0% vs consensus
    TTFT
    559ms
    Throughput
    338.3 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    53
    Provider
    openrouter → nextbit
    Class
    Reseller
    Disabled by openrouter · disabled · fp8
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.3
    Cache read $ / 1M tokens
    $0.04
    +7.1% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    54
    Provider
    openrouter → phala
    Class
    Reseller
    Disabled by openrouter · disabled · unknown
    $ / 1M tokens
    Input $ / 1M tokens
    $0.2
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    $0.07
    +42.9% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    55
    Provider
    lithos-ai
    Class
    —
    Disabled by lithos-ai · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    —
    +114.3% vs consensus
    TTFT
    620ms
    Throughput
    510.6 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    56
    Provider
    modal
    Class
    Direct host
    Disabled by modal · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.3
    Output $ / 1M tokens
    $1.2
    Cache read $ / 1M tokens
    —
    +328.6% vs consensus
    TTFT
    642ms
    Throughput
    211.9 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    57
    Provider
    together
    Class
    Direct host
    Disabled by together · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.3
    Output $ / 1M tokens
    $1.2
    Cache read $ / 1M tokens
    —
    +328.6% vs consensus
    TTFT
    374ms
    Throughput
    321.8 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    58
    Provider
    scaleway
    Class
    Direct host
    Disabled by scaleway · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.7
    Output $ / 1M tokens
    $2.09
    Cache read $ / 1M tokens
    —
    +646.4% vs consensus
    TTFT
    1.4s
    Throughput
    233.7 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    59
    Provider
    inco
    Class
    —
    Disabled by inco · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.6
    Output $ / 1M tokens
    $2.4
    Cache read $ / 1M tokens
    —
    +757.1% vs consensus
    TTFT
    1.4s
    Throughput
    1090.5 tps
    Uptime 24h
    —
    Requests 24h
    —
Source ecosystem
Loading…