modelstatus.dev

Claude Opus 4.5

anthropic/claude-opus-4.5

Compare with Claude Haiku 4.5, Claude Sonnet 4.5, Claude Sonnet 4.6

CompareClaude Opus 4.5
  • Amazon Bedrock100%
    Healthy24h 99.76%
    p50
    1.91s
    p99
    12.1s
    Throughput
    40 tps
    Context
    200K
    $/Mtok
    $5.00 / $25.00
    amazon-bedrock
  • Amazon Bedrock
    No data24h 100%
    p50
    1.69s
    p99
    2.60s
    Throughput
    31 tps
    Context
    200K
    $/Mtok
    $5.50 / $27.50
    amazon-bedrock/eu-west-1
  • Anthropic
    No data24h 99.85%
    p50
    1.44s
    p99
    5.42s
    Throughput
    35 tps
    Context
    200K
    $/Mtok
    $5.00 / $25.00
    anthropic
  • Azure
    No data24h 100%
    p50
    1.54s
    p99
    1.86s
    Throughput
    68 tps
    Context
    200K
    $/Mtok
    $5.00 / $25.00
    azure/global
  • Claude Platform on AWS
    No data24h
    p50
    3.08s
    p99
    3.47s
    Throughput
    44 tps
    Context
    200K
    $/Mtok
    $5.00 / $25.00
    claude-on-aws
  • Google
    No data24h 99.79%
    p50
    1.59s
    p99
    4.53s
    Throughput
    46 tps
    Context
    200K
    $/Mtok
    $5.00 / $25.00
    google-vertex/global

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

5 endpoints reporting no data are omitted from the charts.

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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.

Throughput

Median tokens per second.