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
  • Azure100%
    Healthy24h 99.66%
    p50
    668ms
    p99
    2.20s
    Throughput
    72 tps
    Context
    200K
    $/Mtok
    $1.00 / $5.00
    azure/global
  • Google100%
    Healthy24h 99.90%
    p50
    455ms
    p99
    2.10s
    Throughput
    76 tps
    Context
    200K
    $/Mtok
    $1.00 / $5.00
    google-vertex/global
  • Amazon Bedrock99.97%
    Healthy24h 99.95%
    p50
    1.04s
    p99
    5.34s
    Throughput
    47 tps
    Context
    200K
    $/Mtok
    $1.00 / $5.00
    amazon-bedrock/global
  • Anthropic99.16%
    Healthy24h 99.46%
    p50
    714ms
    p99
    2.99s
    Throughput
    63 tps
    Context
    200K
    $/Mtok
    $1.00 / $5.00
    anthropic
  • Amazon Bedrock
    No data24h 100%
    p50
    p99
    Throughput
    Context
    200K
    $/Mtok
    $1.10 / $5.50
    amazon-bedrock/eu-west-1
  • Amazon Bedrock
    No data24h
    p50
    p99
    Throughput
    Context
    200K
    $/Mtok
    $1.10 / $5.50
    amazon-bedrock/us
  • Google
    No data24h 99.99%
    p50
    360ms
    p99
    1.31s
    Throughput
    89 tps
    Context
    200K
    $/Mtok
    $1.10 / $5.50
    google-vertex/europe
  • Google
    No data24h
    p50
    p99
    Throughput
    Context
    200K
    $/Mtok
    $1.10 / $5.50
    google-vertex/us-east5

Measured 3m 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.

Throughput

Median tokens per second.