modelstatus.dev

Claude Haiku 4.5

anthropic/claude-haiku-4.5InputtextimagefileOutputtext

Compare its 8 providersIncident RSSCompare with Claude Sonnet 4.5, Claude Opus 4.5, Claude Sonnet 4.6

CompareClaude Haiku 4.5
  • Healthy24h 99.94%
    7d
    99.90%
    30d
    99.94%
    p50
    612ms
    p99
    2.25s
    Throughput
    72 tps
    Context
    200K
    $/Mtok
    $1.00 / $5.00
    anthropic
  • Google100%
    Healthy24h 99.42%
    7d
    99.63%
    30d
    99.74%
    p50
    410ms
    p99
    3.78s
    Throughput
    84 tps
    Context
    200K
    $/Mtok
    $1.00 / $5.00
    google-vertex/global
  • Healthy24h 99.95%
    7d
    99.95%
    30d
    99.96%
    p50
    811ms
    p99
    3.91s
    Throughput
    71 tps
    Context
    200K
    $/Mtok
    $1.00 / $5.00
    amazon-bedrock/global
  • No data24h 99.96%
    7d
    99.92%
    30d
    99.96%
    p50
    490ms
    p99
    1.81s
    Throughput
    100 tps
    Context
    200K
    $/Mtok
    $1.10 / $5.50
    amazon-bedrock/eu-west-1
  • No data24h 99.91%
    7d
    99.75%
    30d
    99.83%
    p50
    510ms
    p99
    715ms
    Throughput
    78 tps
    Context
    200K
    $/Mtok
    $1.10 / $5.50
    amazon-bedrock/us
  • No data24h 99.99%
    7d
    99.74%
    30d
    99.89%
    p50
    473ms
    p99
    1.94s
    Throughput
    87 tps
    Context
    200K
    $/Mtok
    $1.00 / $5.00
    azure/global
  • No data24h 100%
    7d
    100%
    30d
    99.99%
    p50
    399ms
    p99
    856ms
    Throughput
    82 tps
    Context
    200K
    $/Mtok
    $1.10 / $5.50
    google-vertex/europe
  • No data24h 99.94%
    7d
    100%
    30d
    99.96%
    p50
    2.54s
    p99
    3.35s
    Throughput
    196 tps
    Context
    200K
    $/Mtok
    $1.10 / $5.50
    google-vertex/us-east5

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

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.

Daily availability

One row per endpoint · one dot per day · last 90 days.

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 8 endpoints · 48 days with data, 7 endpoint-days below 90%.