modelstatus.dev

Claude Haiku 4.5

anthropic/claude-haiku-4.5

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

CompareClaude Haiku 4.5
  • Healthy24h 99.25%
    7d
    99.36%
    30d
    99.36%
    p50
    714ms
    p99
    7.80s
    Throughput
    70 tps
    Context
    200K
    $/Mtok
    $1.00 / $5.00
    anthropic
  • Google100%
    Healthy24h 99.92%
    7d
    99.93%
    30d
    99.93%
    p50
    458ms
    p99
    1.83s
    Throughput
    92 tps
    Context
    200K
    $/Mtok
    $1.00 / $5.00
    google-vertex/global
  • Healthy24h 99.94%
    7d
    99.94%
    30d
    99.94%
    p50
    954ms
    p99
    4.24s
    Throughput
    59 tps
    Context
    200K
    $/Mtok
    $1.00 / $5.00
    amazon-bedrock/global
  • No data24h 100%
    7d
    100%
    30d
    100%
    p50
    p99
    Throughput
    Context
    200K
    $/Mtok
    $1.10 / $5.50
    amazon-bedrock/eu-west-1
  • No data24h 100%
    7d
    100%
    30d
    100%
    p50
    p99
    Throughput
    Context
    200K
    $/Mtok
    $1.10 / $5.50
    amazon-bedrock/us
  • No data24h 99.68%
    7d
    99.74%
    30d
    99.74%
    p50
    816ms
    p99
    4.31s
    Throughput
    73 tps
    Context
    200K
    $/Mtok
    $1.00 / $5.00
    azure/global
  • No data24h 99.99%
    7d
    100%
    30d
    100%
    p50
    354ms
    p99
    1.42s
    Throughput
    95 tps
    Context
    200K
    $/Mtok
    $1.10 / $5.50
    google-vertex/europe
  • No data24h
    7d
    30d
    p50
    p99
    Throughput
    Context
    200K
    $/Mtok
    $1.10 / $5.50
    google-vertex/us-east5

Measured 1m 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 is OpenRouter's rolling 30-minute window.

Throughput

Median tokens per second.