modelstatus.dev

Claude Sonnet 5

anthropic/claude-sonnet-5

Compare with Claude Opus 5, Claude Fable 5, Claude Opus 5 (Fast)

CompareClaude Sonnet 5
  • Healthy24h 99.97%
    7d
    99.84%
    30d
    99.84%
    p50
    3.21s
    p99
    8.03s
    Throughput
    57 tps
    Context
    1.0M
    $/Mtok
    $2.00 / $10.00
    amazon-bedrock/global
  • Healthy24h 99.98%
    7d
    99.98%
    30d
    99.98%
    p50
    2.35s
    p99
    10.4s
    Throughput
    56 tps
    Context
    1.0M
    $/Mtok
    $2.00 / $10.00
    anthropic
  • Azure100%
    Healthy24h 99.59%
    7d
    99.76%
    30d
    99.76%
    p50
    3.25s
    p99
    8.16s
    Throughput
    56 tps
    Context
    1.0M
    $/Mtok
    $2.00 / $10.00
    azure/global
  • Azure100%
    Healthy24h 99.98%
    7d
    99.98%
    30d
    99.98%
    p50
    2.82s
    p99
    4.93s
    Throughput
    98 tps
    Context
    1.0M
    $/Mtok
    $2.00 / $10.00
    azure/us
  • Google100%
    Healthy24h 99.99%
    7d
    99.97%
    30d
    99.97%
    p50
    1.79s
    p99
    5.41s
    Throughput
    52 tps
    Context
    1.0M
    $/Mtok
    $2.20 / $11.00
    google-vertex/europe
  • Google100%
    Healthy24h 99.92%
    7d
    99.92%
    30d
    99.92%
    p50
    2.74s
    p99
    7.32s
    Throughput
    62 tps
    Context
    1.0M
    $/Mtok
    $2.00 / $10.00
    google-vertex/global
  • Healthy24h 99.96%
    7d
    99.94%
    30d
    99.94%
    p50
    2.84s
    p99
    9.30s
    Throughput
    44 tps
    Context
    1.0M
    $/Mtok
    $2.00 / $10.00
    claude-on-aws
  • No data24h 100%
    7d
    100%
    30d
    100%
    p50
    1.82s
    p99
    1.97s
    Throughput
    79 tps
    Context
    1.0M
    $/Mtok
    $2.20 / $11.00
    amazon-bedrock/us-east-1
  • No data24h
    7d
    30d
    p50
    p99
    Throughput
    Context
    1.0M
    $/Mtok
    $2.20 / $11.00
    google-vertex/us

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

2 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 is OpenRouter's rolling 30-minute window.

Throughput

Median tokens per second.