modelstatus.dev

gpt-oss-20b

gpt-oss-20b: providers compared

Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.

  • Amazon Bedrock100% (best)
    Healthy24h 99.65%
    7d
    99.15%
    30d
    99.15%
    p50
    424ms
    p99
    1.37s
    Throughput
    255 tps
    Context
    131K
    $/Mtok
    $0.070 / $0.150
    amazon-bedrock
  • DeepInfra100% (best)
    Healthy24h 99.89%
    7d
    99.54% (best)
    30d
    99.54% (best)
    p50
    262ms (best)
    p99
    12.2s
    Throughput
    86 tps
    Context
    131K
    $/Mtok
    $0.030 / $0.140 (best)
    deepinfra/bf16bf16
  • Fireworks100% (best)
    Healthy24h 97.43%
    7d
    97.16%
    30d
    97.16%
    p50
    326ms
    p99
    9.84s
    Throughput
    151 tps
    Context
    131K
    $/Mtok
    $0.070 / $0.300
    fireworks
  • Google100% (best)
    Down24h 82.39%
    7d
    79.84%
    30d
    79.84%
    p50
    6.63s
    p99
    49.0s
    Throughput
    24 tps
    Context
    131K
    $/Mtok
    $0.070 / $0.250
    google-vertex/us-central1
  • Parasail100% (best)
    Healthy24h 99.07%
    7d
    98.75%
    30d
    98.75%
    p50
    484ms
    p99
    19.3s
    Throughput
    76 tps
    Context
    131K
    $/Mtok
    $0.030 / $0.150 (best)
    parasail/fp4fp4
  • Phala100% (best)
    Healthy24h 93.38%
    7d
    92.14%
    30d
    92.14%
    p50
    1.38s
    p99
    21.6s
    Throughput
    47 tps
    Context
    131K
    $/Mtok
    $0.040 / $0.150
    phala
  • SiliconFlow100% (best)
    Healthy24h 97.32%
    7d
    97.98%
    30d
    97.98%
    p50
    1.30s
    p99
    60.1s
    Throughput
    31 tps
    Context
    131K
    $/Mtok
    $0.040 / $0.180
    siliconflow/fp8fp8
  • CoreWeave99.96%
    Healthy24h 99.30%
    7d
    99.24%
    30d
    99.24%
    p50
    283ms
    p99
    7.91s
    Throughput
    93 tps
    Context
    131K
    $/Mtok
    $0.030 / $0.130 (best)
    coreweave/fp4fp4
  • Groq99.71%
    Healthy24h 98.34%
    7d
    98.17%
    30d
    98.17%
    p50
    419ms
    p99
    2.96s
    Throughput
    296 tps (best)
    Context
    131K
    $/Mtok
    $0.075 / $0.300
    groq
  • Novita99.69%
    Healthy24h 95.87%
    7d
    98.91%
    30d
    98.91%
    p50
    591ms
    p99
    16.4s
    Throughput
    113 tps
    Context
    131K
    $/Mtok
    $0.040 / $0.150
    novita/fp4fp4
  • No data24h
    7d
    30d
    p50
    p99
    Throughput
    Context
    131K
    $/Mtok
    $0.070 / $0.150
    amazon-bedrock/eu-west-1
  • No data24h 96.81%
    7d
    30d
    p50
    326ms
    p99
    656ms (best)
    Throughput
    72 tps
    Context
    131K
    $/Mtok
    $0.050 / $0.200
    together

Measured 50s ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.

Price vs latency

One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag

History

Availability

Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.

Time to first token

Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window, averaged over the hour.

Throughput

Median tokens per second.