Google: Gemma 4 26B A4B

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
    1.2s
    Throughput
    47.0 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    2
    Provider
    openrouter → darkbloom
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.02
    Output $ / 1M tokens
    $0.1
    Cache read $ / 1M tokens
    $0.01
    -70.6% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    3
    Provider
    openrouter → primeintellect
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.06
    Output $ / 1M tokens
    $0.17
    Cache read $ / 1M tokens
    $0.03
    -48.8% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    4
    Provider
    openrouter → google
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.07
    Output $ / 1M tokens
    $0.23
    Cache read $ / 1M tokens
    $0.04
    -33.8% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    5
    Provider
    openrouter → nextbit
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.07
    Output $ / 1M tokens
    $0.23
    Cache read $ / 1M tokens
    $0.04
    -33.8% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    6
    Provider
    makora
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.07
    Output $ / 1M tokens
    $0.24
    Cache read $ / 1M tokens
    —
    -29.4% vs consensus
    TTFT
    553ms
    reasoning 775ms
    Throughput
    218.9 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    7
    Provider
    openrouter → akashml
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.07
    Output $ / 1M tokens
    $0.24
    Cache read $ / 1M tokens
    $0.05
    -29.4% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    8
    Provider
    openrouter → makora
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.07
    Output $ / 1M tokens
    $0.24
    Cache read $ / 1M tokens
    $0.05
    -29.4% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    9
    Provider
    coreweave
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.3
    Cache read $ / 1M tokens
    —
    -11.8% vs consensus
    TTFT
    819ms
    Throughput
    105.8 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    10
    Provider
    openrouter → cloudflare
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.3
    Cache read $ / 1M tokens
    $0.05
    -11.8% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    11
    Provider
    openrouter → coreweave
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.3
    Cache read $ / 1M tokens
    $0.05
    -11.8% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    12
    Provider
    wandb → google
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.3
    Cache read $ / 1M tokens
    $0.05
    -11.8% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    13
    Provider
    openrouter → io-net
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.09
    Output $ / 1M tokens
    $0.31
    Cache read $ / 1M tokens
    $0.04
    -8.8% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    14
    Provider
    openrouter → dekallm
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.06
    Output $ / 1M tokens
    $0.33
    Cache read $ / 1M tokens
    $0.04
    -2.9% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    15
    Provider
    google-vertex
    Class
    Official
    $ / 1M tokens
    Input $ / 1M tokens
    $0.07
    Output $ / 1M tokens
    $0.34
    Cache read $ / 1M tokens
    $0.02
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    16
    Provider
    deepinfra
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.07
    Output $ / 1M tokens
    $0.34
    Cache read $ / 1M tokens
    —
    +0.0% vs consensus
    TTFT
    560ms
    reasoning 617ms
    Throughput
    73.4 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    17
    Provider
    deepinfra → google
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.07
    Output $ / 1M tokens
    $0.34
    Cache read $ / 1M tokens
    —
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    18
    Provider
    openrouter → deepinfra
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.07
    Output $ / 1M tokens
    $0.34
    Cache read $ / 1M tokens
    —
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    19
    Provider
    zeroeval → deepinfra
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.07
    Output $ / 1M tokens
    $0.34
    Cache read $ / 1M tokens
    —
    +0.0% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    20
    Provider
    systalyze
    Class
    —
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    —
    +17.6% vs consensus
    TTFT
    978ms
    Throughput
    505.6 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    21
    Provider
    gmi
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    —
    +17.6% vs consensus
    TTFT
    3.2s
    Throughput
    36.0 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    22
    Provider
    novita
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    —
    +17.6% vs consensus
    TTFT
    1.3s
    reasoning 2.3s
    Throughput
    104.1 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    23
    Provider
    parasail
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    —
    +17.6% vs consensus
    TTFT
    1.2s
    reasoning 1.7s
    Throughput
    122.6 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    24
    Provider
    novita → google
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    —
    +17.6% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    25
    Provider
    openrouter → novita
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    —
    +17.6% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    26
    Provider
    openrouter → parasail
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    $0.05
    +17.6% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    27
    Provider
    openrouter → venice
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    $0.05
    +17.6% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    28
    Provider
    zeroeval → novita
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    —
    +17.6% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    29
    Provider
    siliconflow
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    $0.05
    +17.6% vs consensus
    TTFT
    2.1s
    Throughput
    90.4 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    30
    Provider
    openrouter → siliconflow
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    $0.05
    +17.6% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    31
    Provider
    scaleway
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.29
    Output $ / 1M tokens
    $0.58
    Cache read $ / 1M tokens
    —
    +70.6% vs consensus
    TTFT
    1.0s
    Throughput
    108.7 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    32
    Provider
    openrouter → google-vertex
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    —
    +76.5% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    33
    Provider
    openrouter → reka
    Class
    Reseller
    Disabled by openrouter · disabled · unknown
    $ / 1M tokens
    Input $ / 1M tokens
    $0.06
    Output $ / 1M tokens
    $0.2
    Cache read $ / 1M tokens
    $0.04
    -41.2% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    34
    Provider
    cloudflare
    Class
    Direct host
    Disabled by cloudflare · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.3
    Cache read $ / 1M tokens
    —
    -11.8% vs consensus
    TTFT
    5.9s
    Throughput
    58.0 tps
    Uptime 24h
    —
    Requests 24h
    —
  • #
    35
    Provider
    openrouter → ionstream
    Class
    Reseller
    Disabled by openrouter · disabled · bf16
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    $0.05
    +17.6% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    36
    Provider
    openrouter → wafer
    Class
    Reseller
    Disabled by openrouter · disabled · fp8
    $ / 1M tokens
    Input $ / 1M tokens
    $0.13
    Output $ / 1M tokens
    $0.4
    Cache read $ / 1M tokens
    $0.05
    +17.6% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
  • #
    37
    Provider
    clarifai
    Class
    Direct host
    Disabled by clarifai · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.67
    Output $ / 1M tokens
    $0.95
    Cache read $ / 1M tokens
    —
    +179.4% vs consensus
    TTFT
    —
    Throughput
    —
    Uptime 24h
    —
    Requests 24h
    —
Source ecosystem
Loading…