Google: Gemma 4 31B

google
freeoutput / 1M tokens · input free/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
    google
    Class
    Official
    $ / 1M tokens
    Input $ / 1M tokens
    free
    Output $ / 1M tokens
    free
    Cache read $ / 1M tokens
    -100.0% vs consensus
    TTFT
    981ms
    Throughput
    34.6 tps
    Uptime 24h
    Requests 24h
  • #
    2
    Provider
    openrouter → deepinfra
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.09
    Output $ / 1M tokens
    $0.34
    Cache read $ / 1M tokens
    $0.05
    -15.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    3
    Provider
    openrouter → google
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.09
    Output $ / 1M tokens
    $0.34
    Cache read $ / 1M tokens
    $0.05
    -15.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    4
    Provider
    zeroeval → deepinfra
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.09
    Output $ / 1M tokens
    $0.34
    Cache read $ / 1M tokens
    -15.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    5
    Provider
    coreweave
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.34
    Cache read $ / 1M tokens
    -15.0% vs consensus
    TTFT
    2.2s
    reasoning 1.0s
    Throughput
    45.2 tps
    Uptime 24h
    Requests 24h
  • #
    6
    Provider
    openrouter → coreweave
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.34
    Cache read $ / 1M tokens
    $0.1
    -15.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    7
    Provider
    wandb → google
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.34
    Cache read $ / 1M tokens
    -15.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    8
    Provider
    openrouter → venice
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.12
    Output $ / 1M tokens
    $0.36
    Cache read $ / 1M tokens
    $0.09
    -10.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    9
    Provider
    openrouter → chutes
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.12
    Output $ / 1M tokens
    $0.37
    Cache read $ / 1M tokens
    $0.01
    -7.5% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    10
    Provider
    deepinfra
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.38
    Cache read $ / 1M tokens
    -5.0% vs consensus
    TTFT
    1.5s
    reasoning 1.0s
    Throughput
    14.6 tps
    Uptime 24h
    Requests 24h
  • #
    11
    Provider
    deepinfra → google
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.38
    Cache read $ / 1M tokens
    -5.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    12
    Provider
    siliconflow
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    3.5s
    reasoning 3.3s
    Throughput
    53.9 tps
    Uptime 24h
    Requests 24h
  • #
    13
    Provider
    crusoe
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    1.3s
    Throughput
    17.2 tps
    Uptime 24h
    Requests 24h
  • #
    14
    Provider
    friendli-ai
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    1.8s
    reasoning 2.2s
    Throughput
    110.4 tps
    Uptime 24h
    Requests 24h
  • #
    15
    Provider
    gmi
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    $0.1
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    16
    Provider
    lightningai
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    636ms
    Throughput
    160.7 tps
    Uptime 24h
    Requests 24h
  • #
    17
    Provider
    novita
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    2.0s
    Throughput
    15.8 tps
    Uptime 24h
    Requests 24h
  • #
    18
    Provider
    novita → google
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    19
    Provider
    openrouter → friendli
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    20
    Provider
    zeroeval → friendli
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    21
    Provider
    zeroeval → novita
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    22
    Provider
    parasail
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    1.5s
    reasoning 3.3s
    Throughput
    39.2 tps
    Uptime 24h
    Requests 24h
  • #
    23
    Provider
    openrouter → parasail
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    $0.06
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    24
    Provider
    modular
    Class
    $ / 1M tokens
    Input $ / 1M tokens
    $0.25
    Output $ / 1M tokens
    $0.65
    Cache read $ / 1M tokens
    +62.5% vs consensus
    TTFT
    432ms
    Throughput
    208.1 tps
    Uptime 24h
    Requests 24h
  • #
    25
    Provider
    together
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.39
    Output $ / 1M tokens
    $0.97
    Cache read $ / 1M tokens
    +142.5% vs consensus
    TTFT
    1.4s
    reasoning 1.3s
    Throughput
    14.4 tps
    Uptime 24h
    Requests 24h
  • #
    26
    Provider
    openrouter → together
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.39
    Output $ / 1M tokens
    $0.97
    Cache read $ / 1M tokens
    +142.5% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    27
    Provider
    together → google
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.39
    Output $ / 1M tokens
    $0.97
    Cache read $ / 1M tokens
    +142.5% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    28
    Provider
    zeroeval → together
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.39
    Output $ / 1M tokens
    $0.97
    Cache read $ / 1M tokens
    +142.5% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    29
    Provider
    openrouter → modelrun
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.75
    Output $ / 1M tokens
    $1
    Cache read $ / 1M tokens
    $0.75
    +150.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    30
    Provider
    openrouter → siliconflow
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.75
    Output $ / 1M tokens
    $1
    Cache read $ / 1M tokens
    $0.25
    +150.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    31
    Provider
    sambanova
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.38
    Output $ / 1M tokens
    $1.15
    Cache read $ / 1M tokens
    +187.5% vs consensus
    TTFT
    2.7s
    reasoning 3.2s
    Throughput
    205.3 tps
    Uptime 24h
    Requests 24h
  • #
    32
    Provider
    openrouter → sambanova
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.38
    Output $ / 1M tokens
    $1.15
    Cache read $ / 1M tokens
    +187.5% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    33
    Provider
    cerebras
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.99
    Output $ / 1M tokens
    $1.49
    Cache read $ / 1M tokens
    +272.5% vs consensus
    TTFT
    565ms
    Throughput
    2020.1 tps
    Uptime 24h
    Requests 24h
  • #
    34
    Provider
    openrouter → open-inference
    Class
    Reseller
    Disabled by openrouter · disabled · bf16
    $ / 1M tokens
    Input $ / 1M tokens
    $0.07
    Output $ / 1M tokens
    $0.35
    Cache read $ / 1M tokens
    $0.1
    -12.5% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    35
    Provider
    openrouter → wandb
    Class
    Reseller
    Disabled by openrouter · disabled · bf16
    $ / 1M tokens
    Input $ / 1M tokens
    $0.12
    Output $ / 1M tokens
    $0.35
    Cache read $ / 1M tokens
    $0.09
    -12.5% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    36
    Provider
    openrouter → wandb-legacy
    Class
    Reseller
    Disabled by openrouter · disabled · bf16
    $ / 1M tokens
    Input $ / 1M tokens
    $0.12
    Output $ / 1M tokens
    $0.35
    Cache read $ / 1M tokens
    $0.09
    -12.5% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    37
    Provider
    openrouter → crusoe
    Class
    Reseller
    Disabled by openrouter · disabled · bf16
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    $0.14
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    38
    Provider
    openrouter → morph
    Class
    Reseller
    Disabled by openrouter · disabled · fp4
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    $0.08
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    39
    Provider
    openrouter → novita
    Class
    Reseller
    Disabled by openrouter · disabled · bf16
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    40
    Provider
    openrouter → nextbit
    Class
    Reseller
    Disabled by openrouter · disabled · bf16
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    $0.06
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    41
    Provider
    openrouter → phala
    Class
    Reseller
    Disabled by openrouter · disabled · unknown
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.46
    Cache read $ / 1M tokens
    $0.08
    +15.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    42
    Provider
    openrouter → ambient
    Class
    Reseller
    Disabled by openrouter · disabled · unknown
    $ / 1M tokens
    Input $ / 1M tokens
    $0.2
    Output $ / 1M tokens
    $0.8
    Cache read $ / 1M tokens
    $0.07
    +100.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    43
    Provider
    openrouter → cerebras
    Class
    Reseller
    Disabled by openrouter · disabled · fp16
    $ / 1M tokens
    Input $ / 1M tokens
    $0.99
    Output $ / 1M tokens
    $1.49
    Cache read $ / 1M tokens
    $0.99
    +272.5% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
Source ecosystem
Loading…