modelstatus.dev

Claude Opus 4.5

Claude Opus 4.5: 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 100%
    7d
    100% (best)
    30d
    100% (best)
    p50
    1.75s
    p99
    3.50s
    Throughput
    41 tps
    Context
    200K
    $/Mtok
    $5.50 / $27.50
    amazon-bedrock/eu-west-1
  • Google100% (best)
    Healthy24h 99.71%
    7d
    99.88%
    30d
    99.88%
    p50
    1.58s
    p99
    4.44s
    Throughput
    42 tps
    Context
    200K
    $/Mtok
    $5.00 / $25.00 (best)
    google-vertex/global
  • Healthy24h 99.29%
    7d
    99.61%
    30d
    99.61%
    p50
    1.65s
    p99
    9.55s
    Throughput
    35 tps
    Context
    200K
    $/Mtok
    $5.00 / $25.00 (best)
    amazon-bedrock
  • No data24h 99.96%
    7d
    99.87%
    30d
    99.87%
    p50
    1.52s
    p99
    10.7s
    Throughput
    36 tps
    Context
    200K
    $/Mtok
    $5.00 / $25.00 (best)
    anthropic
  • No data24h 100%
    7d
    100% (best)
    30d
    100% (best)
    p50
    1.44s (best)
    p99
    2.90s (best)
    Throughput
    64 tps (best)
    Context
    200K
    $/Mtok
    $5.00 / $25.00 (best)
    azure/global
  • No data24h 96.91%
    7d
    100% (best)
    30d
    100% (best)
    p50
    p99
    Throughput
    Context
    200K
    $/Mtok
    $5.00 / $25.00 (best)
    claude-on-aws

Measured 2m 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.