modelstatus.dev

Gemini 3.7 Flash

Gemini 3.7 Flash: providers compared

Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.

  • Google AI Studio99.58% (best)
    Healthy24h 99.78%
    7d
    99.76% (best)
    30d
    99.76% (best)
    p50
    1.99s (best)
    p99
    12.4s
    Throughput
    120 tps
    Context
    1.0M
    $/Mtok
    $0.750 / $3.75
    google-ai-studio
  • Google AI Studio99.58% (best)
    Healthy24h 99.78%
    7d
    99.76% (best)
    30d
    99.76% (best)
    p50
    2.90s
    p99
    9.82s
    Throughput
    167 tps
    Context
    1.0M
    $/Mtok
    $0.375 / $1.88
    google-ai-studio/flex
  • Google AI Studio99.58% (best)
    Healthy24h 99.78%
    7d
    99.76% (best)
    30d
    99.76% (best)
    p50
    2.17s
    p99
    9.74s
    Throughput
    210 tps (best)
    Context
    1.0M
    $/Mtok
    $1.35 / $6.75
    google-ai-studio/priority
  • Google99.35%
    Healthy24h 98.44%
    7d
    98.44%
    30d
    98.44%
    p50
    2.60s
    p99
    33.4s
    Throughput
    84 tps
    Context
    1.0M
    $/Mtok
    $0.375 / $1.88
    google-vertex/global
  • Google99.35%
    Healthy24h 98.44%
    7d
    98.44%
    30d
    98.44%
    p50
    15.8s
    p99
    77.3s
    Throughput
    15 tps
    Context
    1.0M
    $/Mtok
    $0.188 / $0.938 (best)
    google-vertex/global/flex
  • Google99.35%
    Healthy24h 98.44%
    7d
    98.44%
    30d
    98.44%
    p50
    2.23s
    p99
    4.12s (best)
    Throughput
    137 tps
    Context
    1.0M
    $/Mtok
    $0.675 / $3.38
    google-vertex/global/priority

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.

Price vs latency

One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag

History

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.