OpenAI: gpt-oss-120b

openai
$0.1output / 1M tokens · input $0.03/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
    lightningai
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.03
    Output $ / 1M tokens
    $0.1
    Cache read $ / 1M tokens
    -83.1% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    2
    Provider
    coreweave
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.03
    Output $ / 1M tokens
    $0.17
    Cache read $ / 1M tokens
    -71.2% vs consensus
    TTFT
    1.4s
    Throughput
    47.9 tps
    Uptime 24h
    Requests 24h
  • #
    3
    Provider
    openrouter → akashml
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.03
    Output $ / 1M tokens
    $0.17
    Cache read $ / 1M tokens
    $0.03
    -71.2% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    4
    Provider
    openrouter → coreweave
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.03
    Output $ / 1M tokens
    $0.17
    Cache read $ / 1M tokens
    $0.03
    -71.2% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    5
    Provider
    wandb → openai
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.03
    Output $ / 1M tokens
    $0.17
    Cache read $ / 1M tokens
    -71.2% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    6
    Provider
    deepinfra
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.04
    Output $ / 1M tokens
    $0.17
    Cache read $ / 1M tokens
    -71.2% vs consensus
    TTFT
    621ms
    Throughput
    42.7 tps
    Uptime 24h
    Requests 24h
  • #
    7
    Provider
    deepinfra → openai
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.04
    Output $ / 1M tokens
    $0.17
    Cache read $ / 1M tokens
    -71.2% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    8
    Provider
    openrouter → deepinfra
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.04
    Output $ / 1M tokens
    $0.17
    Cache read $ / 1M tokens
    -71.2% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    9
    Provider
    openrouter → openai
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.04
    Output $ / 1M tokens
    $0.17
    Cache read $ / 1M tokens
    -71.2% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    10
    Provider
    zeroeval → deepinfra
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.04
    Output $ / 1M tokens
    $0.17
    Cache read $ / 1M tokens
    -71.2% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    11
    Provider
    snowflake
    Class
    Official
    $ / 1M tokens
    Input $ / 1M tokens
    $0.22
    Output $ / 1M tokens
    $0.22
    Cache read $ / 1M tokens
    -62.7% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    12
    Provider
    crusoe
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.05
    Output $ / 1M tokens
    $0.25
    Cache read $ / 1M tokens
    -57.6% vs consensus
    TTFT
    351ms
    Throughput
    268.7 tps
    Uptime 24h
    Requests 24h
  • #
    13
    Provider
    gmi
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.05
    Output $ / 1M tokens
    $0.25
    Cache read $ / 1M tokens
    -57.6% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    14
    Provider
    novita
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.05
    Output $ / 1M tokens
    $0.25
    Cache read $ / 1M tokens
    -57.6% vs consensus
    TTFT
    3.4s
    Throughput
    57.6 tps
    Uptime 24h
    Requests 24h
  • #
    15
    Provider
    novita → openai
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.05
    Output $ / 1M tokens
    $0.25
    Cache read $ / 1M tokens
    -57.6% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    16
    Provider
    openrouter → novita
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.05
    Output $ / 1M tokens
    $0.25
    Cache read $ / 1M tokens
    -57.6% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    17
    Provider
    hyperbolic
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.3
    Output $ / 1M tokens
    $0.3
    Cache read $ / 1M tokens
    -49.2% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    18
    Provider
    google
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.09
    Output $ / 1M tokens
    $0.36
    Cache read $ / 1M tokens
    -39.0% vs consensus
    TTFT
    367ms
    Throughput
    224.0 tps
    Uptime 24h
    Requests 24h
  • #
    19
    Provider
    openrouter → google-vertex
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.09
    Output $ / 1M tokens
    $0.36
    Cache read $ / 1M tokens
    -39.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    20
    Provider
    openrouter → digitalocean
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.06
    Output $ / 1M tokens
    $0.39
    Cache read $ / 1M tokens
    $0.02
    -34.7% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    21
    Provider
    siliconflow
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.05
    Output $ / 1M tokens
    $0.45
    Cache read $ / 1M tokens
    -23.7% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    22
    Provider
    ovhcloud
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.09
    Output $ / 1M tokens
    $0.47
    Cache read $ / 1M tokens
    -20.3% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    23
    Provider
    openrouter → mancer
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.06
    Output $ / 1M tokens
    $0.5
    Cache read $ / 1M tokens
    -15.3% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    24
    Provider
    baseten
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.5
    Cache read $ / 1M tokens
    -15.3% vs consensus
    TTFT
    229ms
    Throughput
    293.5 tps
    Uptime 24h
    Requests 24h
  • #
    25
    Provider
    baseten → openai
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.5
    Cache read $ / 1M tokens
    -15.3% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    26
    Provider
    openrouter → baseten
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.5
    Cache read $ / 1M tokens
    $0.1
    -15.3% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    27
    Provider
    sambanova
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.22
    Output $ / 1M tokens
    $0.59
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    1.1s
    Throughput
    708.2 tps
    Uptime 24h
    Requests 24h
  • #
    28
    Provider
    databricks
    Class
    Official
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    +1.7% vs consensus
    TTFT
    625ms
    Throughput
    322.1 tps
    Uptime 24h
    Requests 24h
  • #
    29
    Provider
    azure → azure-ai
    Class
    Official
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    +1.7% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    30
    Provider
    azure → azure-openai
    Class
    Official
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    +1.7% vs consensus
    TTFT
    773ms
    Throughput
    320.1 tps
    Uptime 24h
    Requests 24h
  • #
    31
    Provider
    amazon-bedrock
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    +1.7% vs consensus
    TTFT
    940ms
    Throughput
    79.4 tps
    Uptime 24h
    Requests 24h
  • #
    32
    Provider
    fireworks
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    $0.02
    +1.7% vs consensus
    TTFT
    889ms
    Throughput
    143.4 tps
    Uptime 24h
    Requests 24h
  • #
    33
    Provider
    groq
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    +1.7% vs consensus
    TTFT
    732ms
    Throughput
    475.2 tps
    Uptime 24h
    Requests 24h
  • #
    34
    Provider
    nebius
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    +1.7% vs consensus
    TTFT
    1.0s
    Throughput
    293.7 tps
    Uptime 24h
    Requests 24h
  • #
    35
    Provider
    together
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    +1.7% vs consensus
    TTFT
    513ms
    Throughput
    121.2 tps
    Uptime 24h
    Requests 24h
  • #
    36
    Provider
    openrouter → amazon-bedrock
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    +1.7% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    37
    Provider
    openrouter → groq
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    $0.08
    +1.7% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    38
    Provider
    openrouter → nebius
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    +1.7% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    39
    Provider
    openrouter → phala
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    +1.7% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    40
    Provider
    openrouter → together
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    +1.7% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    41
    Provider
    together → openai
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    +1.7% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    42
    Provider
    scaleway
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.17
    Output $ / 1M tokens
    $0.7
    Cache read $ / 1M tokens
    +18.6% vs consensus
    TTFT
    1.3s
    Throughput
    120.5 tps
    Uptime 24h
    Requests 24h
  • #
    43
    Provider
    replicate → openai
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.18
    Output $ / 1M tokens
    $0.72
    Cache read $ / 1M tokens
    +22.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    44
    Provider
    parasail
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.75
    Cache read $ / 1M tokens
    +27.1% vs consensus
    TTFT
    659ms
    Throughput
    144.1 tps
    Uptime 24h
    Requests 24h
  • #
    45
    Provider
    openrouter → parasail
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.75
    Cache read $ / 1M tokens
    $0.06
    +27.1% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    46
    Provider
    cerebras
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.35
    Output $ / 1M tokens
    $0.75
    Cache read $ / 1M tokens
    +27.1% vs consensus
    TTFT
    483ms
    Throughput
    1654.4 tps
    Uptime 24h
    Requests 24h
  • #
    47
    Provider
    cloudflare
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.35
    Output $ / 1M tokens
    $0.75
    Cache read $ / 1M tokens
    +27.1% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    48
    Provider
    openrouter → cerebras
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.35
    Output $ / 1M tokens
    $0.75
    Cache read $ / 1M tokens
    $0.35
    +27.1% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    49
    Provider
    openrouter → sambanova
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.14
    Output $ / 1M tokens
    $0.95
    Cache read $ / 1M tokens
    +61.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    50
    Provider
    openrouter → wandb
    Class
    Reseller
    Disabled by openrouter · disabled · fp4
    $ / 1M tokens
    Input $ / 1M tokens
    $0.04
    Output $ / 1M tokens
    $0.14
    Cache read $ / 1M tokens
    $0.04
    -76.3% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    51
    Provider
    openrouter → wandb-legacy
    Class
    Reseller
    Disabled by openrouter · disabled · fp4
    $ / 1M tokens
    Input $ / 1M tokens
    $0.04
    Output $ / 1M tokens
    $0.14
    Cache read $ / 1M tokens
    $0.04
    -76.3% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    52
    Provider
    openrouter → open-inference
    Class
    Reseller
    Disabled by openrouter · disabled · int8
    $ / 1M tokens
    Input $ / 1M tokens
    $0.03
    Output $ / 1M tokens
    $0.15
    Cache read $ / 1M tokens
    -74.6% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    53
    Provider
    openrouter → dekallm
    Class
    Reseller
    Disabled by openrouter · disabled · bf16
    $ / 1M tokens
    Input $ / 1M tokens
    $0.03
    Output $ / 1M tokens
    $0.18
    Cache read $ / 1M tokens
    -69.5% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    54
    Provider
    compactifai
    Class
    Direct host
    Disabled by compactifai · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.05
    Output $ / 1M tokens
    $0.23
    Cache read $ / 1M tokens
    -61.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    55
    Provider
    clarifai
    Class
    Direct host
    Disabled by clarifai · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.09
    Output $ / 1M tokens
    $0.36
    Cache read $ / 1M tokens
    -39.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    56
    Provider
    eigenai
    Class
    Direct host
    Disabled by eigenai · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.5
    Cache read $ / 1M tokens
    -15.3% vs consensus
    TTFT
    628ms
    Throughput
    761.0 tps
    Uptime 24h
    Requests 24h
  • #
    57
    Provider
    zeroeval → novita
    Class
    Reseller
    Disabled by zeroeval · disabled · bf16
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.5
    Cache read $ / 1M tokens
    -15.3% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    58
    Provider
    zeroeval → openai
    Class
    Reseller
    Disabled by zeroeval · disabled
    $ / 1M tokens
    Input $ / 1M tokens
    $0.1
    Output $ / 1M tokens
    $0.5
    Cache read $ / 1M tokens
    -15.3% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    59
    Provider
    makora
    Class
    Direct host
    Disabled by makora · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    +1.7% vs consensus
    TTFT
    966ms
    Throughput
    131.0 tps
    Uptime 24h
    Requests 24h
  • #
    60
    Provider
    openrouter → siliconflow
    Class
    Reseller
    Disabled by openrouter · disabled · fp8
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    $0.08
    +1.7% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    61
    Provider
    zeroeval → fireworks
    Class
    Reseller
    Disabled by zeroeval · disabled
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    +1.7% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    62
    Provider
    zeroeval → groq
    Class
    Reseller
    Disabled by zeroeval · disabled
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.6
    Cache read $ / 1M tokens
    +1.7% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    63
    Provider
    openrouter → mara
    Class
    Reseller
    Disabled by openrouter · disabled · unknown
    $ / 1M tokens
    Input $ / 1M tokens
    $0.15
    Output $ / 1M tokens
    $0.75
    Cache read $ / 1M tokens
    +27.1% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
Source ecosystem
Loading…