modelstatus.dev

GPT-5.4

GPT-5.4: providers compared

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

  • Azure100% (best)
    Healthy24h 99.95%
    7d
    99.93%
    30d
    99.93%
    p50
    3.36s
    p99
    30.9s
    Throughput
    52 tps
    Context
    1.1M
    $/Mtok
    $2.50 / $15.00
    azure
  • OpenAI99.51%
    Healthy24h 99.14%
    7d
    99.36%
    30d
    99.36%
    p50
    1.25s (best)
    p99
    75.3s
    Throughput
    43 tps
    Context
    1.1M
    $/Mtok
    $2.50 / $15.00
    openai
  • OpenAI99.51%
    Healthy24h 99.14%
    7d
    99.36%
    30d
    99.36%
    p50
    15.7s
    p99
    69.1s
    Throughput
    128 tps (best)
    Context
    1.1M
    $/Mtok
    $1.25 / $7.50 (best)
    openai/flex
  • OpenAI99.51%
    Healthy24h 99.14%
    7d
    99.36%
    30d
    99.36%
    p50
    3.61s
    p99
    9.33s
    Throughput
    92 tps
    Context
    1.1M
    $/Mtok
    $5.00 / $30.00
    openai/priority
  • No data24h
    7d
    30d
    p50
    p99
    Throughput
    Context
    1.1M
    $/Mtok
    $2.75 / $16.50
    amazon-bedrock/us-east-1
  • No data24h 100%
    7d
    100% (best)
    30d
    100% (best)
    p50
    3.36s
    p99
    13.4s
    Throughput
    50 tps
    Context
    1.1M
    $/Mtok
    $2.75 / $16.50
    azure/eu
  • No data24h 98.79%
    7d
    100% (best)
    30d
    100% (best)
    p50
    5.82s
    p99
    5.90s (best)
    Throughput
    47 tps
    Context
    1.1M
    $/Mtok
    $2.75 / $16.50
    azure/us

Measured 1m 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.

Throughput

Median tokens per second.