modelstatus.dev

Claude Sonnet 4.6

anthropic/claude-sonnet-4.6

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

CompareClaude Sonnet 4.6
  • Healthy24h 99.82%
    p50
    1.62s
    p99
    10.3s
    Throughput
    29 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    anthropic
  • Azure100%
    Healthy24h 100%
    p50
    1.68s
    p99
    36.2s
    Throughput
    33 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    azure/global
  • Healthy24h 99.94%
    p50
    1.15s
    p99
    3.66s
    Throughput
    38 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    claude-on-aws
  • Google100%
    Healthy24h 99.95%
    p50
    1.43s
    p99
    5.14s
    Throughput
    42 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    google-vertex/global
  • Healthy24h 99.95%
    p50
    1.24s
    p99
    6.29s
    Throughput
    34 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    amazon-bedrock/global
  • No data24h
    p50
    978ms
    p99
    1.15s
    Throughput
    61 tps
    Context
    1.0M
    $/Mtok
    $3.30 / $16.50
    amazon-bedrock/eu-west-1
  • No data24h
    p50
    1.37s
    p99
    1.41s
    Throughput
    56 tps
    Context
    1.0M
    $/Mtok
    $3.30 / $16.50
    amazon-bedrock/us
  • No data24h 99.63%
    p50
    1.68s
    p99
    3.32s
    Throughput
    54 tps
    Context
    1.0M
    $/Mtok
    $3.30 / $16.50
    google-vertex/europe
  • No data24h 100%
    p50
    1.08s
    p99
    1.16s
    Throughput
    14 tps
    Context
    1.0M
    $/Mtok
    $3.30 / $16.50
    google-vertex/us-east5

Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

4 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, averaged over the hour.

Throughput

Median tokens per second.