DeepSeek: DeepSeek V4 Pro

deepseek
$1.2output / 1M tokens · input $0.5/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
    fireworks
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $1.2
    Output $ / 1M tokens
    $1.2
    Cache read $ / 1M tokens
    $0.6
    -62.5% vs consensus
    TTFT
    1.9s
    Throughput
    188.9 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    2
    Provider
    openrouter → relace
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.9
    Output $ / 1M tokens
    $1.5
    Cache read $ / 1M tokens
    $0.25
    -53.1% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    3
    Provider
    openrouter → deepseek
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.96
    Output $ / 1M tokens
    $1.91
    Cache read $ / 1M tokens
    $0.08
    -40.3% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    4
    Provider
    gmi
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.96
    Output $ / 1M tokens
    $1.91
    Cache read $ / 1M tokens
    $0.08
    -40.2% vs consensus
    TTFT
    3.0s
    reasoning 2.5s
    Throughput
    71.7 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    5
    Provider
    openrouter → gmicloud
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.96
    Output $ / 1M tokens
    $1.91
    Cache read $ / 1M tokens
    $0.08
    -40.2% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    6
    Provider
    systalyze
    Class
    —
    $ / 1M tokens
    Input $ / 1M tokens
    $0.5
    Output $ / 1M tokens
    $2
    Cache read $ / 1M tokens
    —
    -37.5% vs consensus
    TTFT
    1.4s
    Throughput
    319.5 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    7
    Provider
    openrouter → digitalocean
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $1.04
    Output $ / 1M tokens
    $2.09
    Cache read $ / 1M tokens
    $0.21
    -34.7% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    8
    Provider
    wandb
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $1.15
    Output $ / 1M tokens
    $2.55
    Cache read $ / 1M tokens
    $0.2
    -20.3% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    9
    Provider
    openrouter → cloudflare
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $1.15
    Output $ / 1M tokens
    $2.55
    Cache read $ / 1M tokens
    $0.2
    -20.3% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    10
    Provider
    deepinfra
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $1.3
    Output $ / 1M tokens
    $2.6
    Cache read $ / 1M tokens
    $0.1
    -18.7% vs consensus
    TTFT
    1.0s
    reasoning 1.7s
    Throughput
    98.5 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    11
    Provider
    openrouter → deepinfra
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $1.3
    Output $ / 1M tokens
    $2.6
    Cache read $ / 1M tokens
    $0.1
    -18.7% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    12
    Provider
    openrouter → qwen
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $1.42
    Output $ / 1M tokens
    $2.83
    Cache read $ / 1M tokens
    $0.12
    -11.5% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    13
    Provider
    siliconflow
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $1.32
    Output $ / 1M tokens
    $3.14
    Cache read $ / 1M tokens
    $0.14
    -2.0% vs consensus
    TTFT
    1.6s
    reasoning 2.1s
    Throughput
    72.2 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    14
    Provider
    openrouter → siliconflow
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $1.5
    Output $ / 1M tokens
    $3.14
    Cache read $ / 1M tokens
    $0.14
    -2.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    15
    Provider
    novita → deepseek
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $1.6
    Output $ / 1M tokens
    $3.2
    Cache read $ / 1M tokens
    $0.14
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    16
    Provider
    openrouter → novita
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $1.6
    Output $ / 1M tokens
    $3.2
    Cache read $ / 1M tokens
    $0.14
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    17
    Provider
    openrouter → venice
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $1.65
    Output $ / 1M tokens
    $3.3
    Cache read $ / 1M tokens
    $0.33
    +3.2% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    18
    Provider
    openrouter → atlas-cloud
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $1.68
    Output $ / 1M tokens
    $3.38
    Cache read $ / 1M tokens
    $0.13
    +5.6% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    19
    Provider
    openrouter → baidu
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $1.69
    Output $ / 1M tokens
    $3.38
    Cache read $ / 1M tokens
    $0.14
    +5.6% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    20
    Provider
    baseten
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $1.32
    Output $ / 1M tokens
    $3.48
    Cache read $ / 1M tokens
    $0.15
    +8.8% vs consensus
    TTFT
    1.8s
    reasoning 1.1s
    Throughput
    132.5 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    21
    Provider
    crusoe
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $1.74
    Output $ / 1M tokens
    $3.48
    Cache read $ / 1M tokens
    —
    +8.8% vs consensus
    TTFT
    1.5s
    Throughput
    139.3 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    22
    Provider
    azure → azure-ai
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $1.74
    Output $ / 1M tokens
    $3.48
    Cache read $ / 1M tokens
    $0.004
    +8.8% vs consensus
    TTFT
    1.7s
    reasoning 1.5s
    Throughput
    172.1 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    23
    Provider
    openrouter → crusoe
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $1.74
    Output $ / 1M tokens
    $3.48
    Cache read $ / 1M tokens
    $0.15
    +8.8% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    24
    Provider
    openrouter → azure
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $1.91
    Output $ / 1M tokens
    $3.83
    Cache read $ / 1M tokens
    $0.16
    +19.7% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    25
    Provider
    deepseek
    Class
    Official
    $ / 1M tokens
    Input $ / 1M tokens
    $1.32
    Output $ / 1M tokens
    $3.96
    Cache read $ / 1M tokens
    $0.04
    +23.8% vs consensus
    TTFT
    1.7s
    reasoning 1.7s
    Throughput
    103.5 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    26
    Provider
    digitalocean
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $1.32
    Output $ / 1M tokens
    $3.96
    Cache read $ / 1M tokens
    —
    +23.8% vs consensus
    TTFT
    857ms
    Throughput
    56.7 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    27
    Provider
    nebius
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $1.32
    Output $ / 1M tokens
    $3.96
    Cache read $ / 1M tokens
    —
    +23.8% vs consensus
    TTFT
    1.3s
    reasoning 3.2s
    Throughput
    90.4 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    28
    Provider
    novita
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $1.32
    Output $ / 1M tokens
    $3.96
    Cache read $ / 1M tokens
    —
    +23.8% vs consensus
    TTFT
    2.2s
    reasoning 2.0s
    Throughput
    68.5 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    29
    Provider
    dashscope
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $2.4
    Output $ / 1M tokens
    $4.8
    Cache read $ / 1M tokens
    $0.2
    +50.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    30
    Provider
    openrouter → fireworks
    Class
    Reseller
    Disabled by openrouter · disabled · unknown
    $ / 1M tokens
    Input $ / 1M tokens
    $1.2
    Output $ / 1M tokens
    $1.2
    Cache read $ / 1M tokens
    $0.6
    -62.5% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    31
    Provider
    openrouter → reka
    Class
    Reseller
    Disabled by openrouter · disabled · unknown
    $ / 1M tokens
    Input $ / 1M tokens
    $0.8
    Output $ / 1M tokens
    $1.6
    Cache read $ / 1M tokens
    $0.08
    -50.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    32
    Provider
    openrouter → streamlake
    Class
    Reseller
    Disabled by openrouter · disabled · unknown
    $ / 1M tokens
    Input $ / 1M tokens
    $0.87
    Output $ / 1M tokens
    $1.74
    Cache read $ / 1M tokens
    $0.07
    -45.6% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    33
    Provider
    openrouter → ionstream
    Class
    Reseller
    Disabled by openrouter · disabled · fp4
    $ / 1M tokens
    Input $ / 1M tokens
    $1.13
    Output $ / 1M tokens
    $2.26
    Cache read $ / 1M tokens
    $0.09
    -29.3% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    34
    Provider
    openrouter → wafer
    Class
    Reseller
    Disabled by openrouter · disabled · fp4
    $ / 1M tokens
    Input $ / 1M tokens
    $1.2
    Output $ / 1M tokens
    $2.4
    Cache read $ / 1M tokens
    $0.1
    -25.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    35
    Provider
    openrouter → coreweave
    Class
    Reseller
    Disabled by openrouter · disabled · fp8
    $ / 1M tokens
    Input $ / 1M tokens
    $1.15
    Output $ / 1M tokens
    $2.55
    Cache read $ / 1M tokens
    $0.2
    -20.3% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    36
    Provider
    lightningai
    Class
    Direct host
    Disabled by lightningai · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.89
    Output $ / 1M tokens
    $3
    Cache read $ / 1M tokens
    —
    -6.2% vs consensus
    TTFT
    876ms
    reasoning 834ms
    Throughput
    122.0 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    37
    Provider
    openrouter → parasail
    Class
    Reseller
    Disabled by openrouter · disabled · fp8
    $ / 1M tokens
    Input $ / 1M tokens
    $0.45
    Output $ / 1M tokens
    $3.48
    Cache read $ / 1M tokens
    $0.1
    +8.8% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    38
    Provider
    together
    Class
    Direct host
    Disabled by together · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $1.74
    Output $ / 1M tokens
    $3.48
    Cache read $ / 1M tokens
    $0.2
    +8.8% vs consensus
    TTFT
    1.1s
    reasoning 1.0s
    Throughput
    322.2 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    39
    Provider
    openrouter → baseten
    Class
    Reseller
    Disabled by openrouter · disabled · fp4
    $ / 1M tokens
    Input $ / 1M tokens
    $1.74
    Output $ / 1M tokens
    $3.48
    Cache read $ / 1M tokens
    $0.15
    +8.8% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    40
    Provider
    openrouter → nextbit
    Class
    Reseller
    Disabled by openrouter · disabled · fp8
    $ / 1M tokens
    Input $ / 1M tokens
    $1.74
    Output $ / 1M tokens
    $3.48
    Cache read $ / 1M tokens
    $0.15
    +8.8% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    41
    Provider
    openrouter → together
    Class
    Reseller
    Disabled by openrouter · disabled · unknown
    $ / 1M tokens
    Input $ / 1M tokens
    $1.74
    Output $ / 1M tokens
    $3.48
    Cache read $ / 1M tokens
    $0.2
    +8.8% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    42
    Provider
    openrouter → wandb
    Class
    Reseller
    Disabled by openrouter · disabled · fp8
    $ / 1M tokens
    Input $ / 1M tokens
    $1.74
    Output $ / 1M tokens
    $3.48
    Cache read $ / 1M tokens
    $0.14
    +8.8% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    43
    Provider
    openrouter → wandb-legacy
    Class
    Reseller
    Disabled by openrouter · disabled · fp8
    $ / 1M tokens
    Input $ / 1M tokens
    $1.74
    Output $ / 1M tokens
    $3.48
    Cache read $ / 1M tokens
    $0.14
    +8.8% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    44
    Provider
    bitdeer
    Class
    Direct host
    Disabled by bitdeer · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $1.25
    Output $ / 1M tokens
    $3.76
    Cache read $ / 1M tokens
    —
    +17.6% vs consensus
    TTFT
    7.2s
    Throughput
    51.7 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    45
    Provider
    makora
    Class
    Direct host
    Disabled by makora · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $1.4
    Output $ / 1M tokens
    $3.8
    Cache read $ / 1M tokens
    —
    +18.8% vs consensus
    TTFT
    831ms
    reasoning 847ms
    Throughput
    248.1 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    46
    Provider
    coreweave
    Class
    Direct host
    Disabled by coreweave · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $1.31
    Output $ / 1M tokens
    $3.96
    Cache read $ / 1M tokens
    —
    +23.8% vs consensus
    TTFT
    914ms
    Throughput
    158.7 tps
    Uptime 24h
    —
    Requests 24h
    —
Source ecosystem
Loading…