Qwen: Qwen3.5 397B A17B

qwen
$2.34output / 1M tokens · input $0.39/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
    siliconflow
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.39
    Output $ / 1M tokens
    $2.34
    Cache read $ / 1M tokens
    -35.0% vs consensus
    TTFT
    2.4s
    Throughput
    82.4 tps
    Uptime 24h
    Requests 24h
  • #
    2
    Provider
    openrouter → qwen
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.39
    Output $ / 1M tokens
    $2.34
    Cache read $ / 1M tokens
    $0.23
    -35.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    3
    Provider
    wafer
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.43
    Output $ / 1M tokens
    $2.6
    Cache read $ / 1M tokens
    -27.8% vs consensus
    TTFT
    3.0s
    reasoning 2.4s
    Throughput
    87.9 tps
    Uptime 24h
    Requests 24h
  • #
    4
    Provider
    deepinfra
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.45
    Output $ / 1M tokens
    $3
    Cache read $ / 1M tokens
    $0.22
    -16.7% vs consensus
    TTFT
    967ms
    reasoning 867ms
    Throughput
    39.0 tps
    Uptime 24h
    Requests 24h
  • #
    5
    Provider
    deepinfra → qwen
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.45
    Output $ / 1M tokens
    $3
    Cache read $ / 1M tokens
    $0.22
    -16.7% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    6
    Provider
    openrouter → deepinfra
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.45
    Output $ / 1M tokens
    $3
    Cache read $ / 1M tokens
    $0.22
    -16.7% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    7
    Provider
    digitalocean
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.55
    Output $ / 1M tokens
    $3.5
    Cache read $ / 1M tokens
    -2.8% vs consensus
    TTFT
    1.7s
    reasoning 1.1s
    Throughput
    6.3 tps
    Uptime 24h
    Requests 24h
  • #
    8
    Provider
    openrouter → atlas-cloud
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.55
    Output $ / 1M tokens
    $3.5
    Cache read $ / 1M tokens
    $0.55
    -2.8% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    9
    Provider
    openrouter → digitalocean
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.55
    Output $ / 1M tokens
    $3.5
    Cache read $ / 1M tokens
    $0.11
    -2.8% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    10
    Provider
    openrouter → phala
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.55
    Output $ / 1M tokens
    $3.5
    Cache read $ / 1M tokens
    $0.23
    -2.8% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    11
    Provider
    parasail
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.5
    Output $ / 1M tokens
    $3.6
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    1.2s
    reasoning 934ms
    Throughput
    60.0 tps
    Uptime 24h
    Requests 24h
  • #
    12
    Provider
    openrouter → parasail
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.5
    Output $ / 1M tokens
    $3.6
    Cache read $ / 1M tokens
    $0.3
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    13
    Provider
    alibaba-cloud
    Class
    Official
    $ / 1M tokens
    Input $ / 1M tokens
    $0.6
    Output $ / 1M tokens
    $3.6
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    2.2s
    reasoning 2.8s
    Throughput
    88.4 tps
    Uptime 24h
    Requests 24h
  • #
    14
    Provider
    qwen
    Class
    Official
    $ / 1M tokens
    Input $ / 1M tokens
    $0.6
    Output $ / 1M tokens
    $3.6
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    15
    Provider
    gmi
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.6
    Output $ / 1M tokens
    $3.6
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    3.6s
    Throughput
    52.6 tps
    Uptime 24h
    Requests 24h
  • #
    16
    Provider
    nebius
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.6
    Output $ / 1M tokens
    $3.6
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    2.0s
    reasoning 2.0s
    Throughput
    131.3 tps
    Uptime 24h
    Requests 24h
  • #
    17
    Provider
    novita
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.6
    Output $ / 1M tokens
    $3.6
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    1.6s
    reasoning 1.7s
    Throughput
    86.1 tps
    Uptime 24h
    Requests 24h
  • #
    18
    Provider
    together
    Class
    Direct host
    $ / 1M tokens
    Input $ / 1M tokens
    $0.6
    Output $ / 1M tokens
    $3.6
    Cache read $ / 1M tokens
    $0.35
    +0.0% vs consensus
    TTFT
    649ms
    reasoning 29.3s
    Throughput
    301.8 tps
    Uptime 24h
    Requests 24h
  • #
    19
    Provider
    novita → qwen
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.6
    Output $ / 1M tokens
    $3.6
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    20
    Provider
    openrouter → gmicloud
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.6
    Output $ / 1M tokens
    $3.6
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    21
    Provider
    openrouter → novita
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.6
    Output $ / 1M tokens
    $3.6
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    22
    Provider
    openrouter → streamlake
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.6
    Output $ / 1M tokens
    $3.6
    Cache read $ / 1M tokens
    $0.12
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    23
    Provider
    together → qwen
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.6
    Output $ / 1M tokens
    $3.6
    Cache read $ / 1M tokens
    $0.35
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    24
    Provider
    openrouter → venice
    Class
    Reseller
    $ / 1M tokens
    Input $ / 1M tokens
    $0.75
    Output $ / 1M tokens
    $4.5
    Cache read $ / 1M tokens
    +25.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    25
    Provider
    openrouter → wafer
    Class
    Reseller
    Disabled by openrouter · stale · fp4
    $ / 1M tokens
    Input $ / 1M tokens
    $0.43
    Output $ / 1M tokens
    $2.6
    Cache read $ / 1M tokens
    $0.04
    -27.8% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    26
    Provider
    openrouter → chutes
    Class
    Reseller
    Disabled by openrouter · disabled · fp8
    $ / 1M tokens
    Input $ / 1M tokens
    $0.45
    Output $ / 1M tokens
    $3
    Cache read $ / 1M tokens
    $0.05
    -16.7% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    27
    Provider
    openrouter → morph
    Class
    Reseller
    Disabled by openrouter · disabled · fp4
    $ / 1M tokens
    Input $ / 1M tokens
    $0.5
    Output $ / 1M tokens
    $3.5
    Cache read $ / 1M tokens
    $0.3
    -2.8% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    28
    Provider
    clarifai
    Class
    Direct host
    Disabled by clarifai · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.6
    Output $ / 1M tokens
    $3.6
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    593ms
    Throughput
    311.7 tps
    Uptime 24h
    Requests 24h
  • #
    29
    Provider
    eigenai
    Class
    Direct host
    Disabled by eigenai · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.6
    Output $ / 1M tokens
    $3.6
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    950ms
    reasoning 979ms
    Throughput
    323.2 tps
    Uptime 24h
    Requests 24h
  • #
    30
    Provider
    openrouter → together
    Class
    Reseller
    Disabled by openrouter · disabled · unknown
    $ / 1M tokens
    Input $ / 1M tokens
    $0.6
    Output $ / 1M tokens
    $3.6
    Cache read $ / 1M tokens
    $0.35
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
  • #
    31
    Provider
    zeroeval → novita
    Class
    Reseller
    Disabled by zeroeval · stale
    $ / 1M tokens
    Input $ / 1M tokens
    $0.6
    Output $ / 1M tokens
    $3.6
    Cache read $ / 1M tokens
    +0.0% vs consensus
    TTFT
    Throughput
    Uptime 24h
    Requests 24h
Source ecosystem
Loading…