modelstatus.dev

gpt-oss-20b

openai/gpt-oss-20bInputtextOutputtext

Compare its 18 providersIncident RSSCompare with GPT Audio, GPT Audio Mini, GPT Chat Latest

Comparegpt-oss-20b
  • Healthy24h 100%
    7d
    99.99%
    30d
    99.80%
    p50
    411ms
    p99
    2.08s
    Throughput
    146 tps
    Context
    131K
    $/Mtok
    $0.020 / $0.100
    akashml/fp4fp4
  • Healthy24h 100%
    7d
    100%
    30d
    99.96%
    p50
    391ms
    p99
    2.56s
    Throughput
    442 tps
    Context
    131K
    $/Mtok
    $0.070 / $0.150
    amazon-bedrock
  • Healthy24h 100%
    7d
    99.90%
    30d
    99.93%
    p50
    251ms
    p99
    1.76s
    Throughput
    170 tps
    Context
    131K
    $/Mtok
    $0.030 / $0.130
    coreweave/fp4fp4
  • Healthy24h 99.93%
    7d
    99.99%
    30d
    99.67%
    p50
    965ms
    p99
    18.1s
    Throughput
    66 tps
    Context
    131K
    $/Mtok
    $0.018 / $0.090
    darkbloom/fp8fp8
  • Healthy24h 99.76%
    7d
    99.21%
    30d
    99.29%
    p50
    274ms
    p99
    4.08s
    Throughput
    102 tps
    Context
    131K
    $/Mtok
    $0.030 / $0.140
    deepinfra/bf16bf16
  • Healthy24h 100%
    7d
    99.71%
    30d
    99.80%
    p50
    426ms
    p99
    2.89s
    Throughput
    61 tps
    Context
    131K
    $/Mtok
    $0.029 / $0.140
    dekallm/bf16bf16
  • Groq100%
    Healthy24h 100%
    7d
    99.82%
    30d
    95.71%
    p50
    562ms
    p99
    3.55s
    Throughput
    344 tps
    Context
    131K
    $/Mtok
    $0.075 / $0.300
    groq
  • Healthy24h 100%
    7d
    96.64%
    30d
    98.95%
    p50
    1.43s
    p99
    3.51s
    Throughput
    68 tps
    Context
    131K
    $/Mtok
    $0.030 / $0.150
    parasail/fp4fp4
  • Healthy24h 98.98%
    7d
    98.07%
    30d
    98.07%
    p50
    386ms
    p99
    10.6s
    Throughput
    128 tps
    Context
    131K
    $/Mtok
    $0.018 / $0.074
    primeintellect/fp4fp4
  • No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    131K
    $/Mtok
    $0.020 / $0.100
    akashml/bf16bf16
  • No data24h 100%
    7d
    100%
    30d
    99.97%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    131K
    $/Mtok
    $0.070 / $0.150
    amazon-bedrock/eu-west-1
  • No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    131K
    $/Mtok
    $0.070 / $0.300
    fireworks
  • No data24h —
    7d
    0.00%
    30d
    70.57%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    131K
    $/Mtok
    $0.070 / $0.250
    google-vertex/us-central1
  • No data24h —
    7d
    —
    30d
    99.93%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    131K
    $/Mtok
    $0.040 / $0.150
    novita/fp4fp4
  • No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    131K
    $/Mtok
    $0.040 / $0.150
    phala
  • No data24h —
    7d
    —
    30d
    99.61%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    131K
    $/Mtok
    $0.070 / $0.300
    primeintellect
  • Down24h 94.33%
    7d
    79.75%
    30d
    85.36%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    131K
    $/Mtok
    $0.040 / $0.180
    siliconflow/fp8fp8
  • No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    131K
    $/Mtok
    $0.050 / $0.200
    together

Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

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.

Daily availability

One row per endpoint · one dot per day · last 90 days.

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 18 endpoints · 76 days with data, 203 endpoint-days below 90%.

Price changes