modelstatus.dev

Gemini 3.8 Flash

Gemini 3.8 Flash: providers compared

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

  • Google100% (best)
    Healthy24h 99.84%
    7d
    99.89% (best)
    30d
    99.81% (best)
    p50
    2.02s
    p99
    7.72s
    Throughput
    100 tps
    Context
    1.0M
    $/Mtok
    $1.35 / $6.75
    google-vertex/global/priority
  • Google AI Studio100% (best)
    Healthy24h 99.91%
    7d
    99.82%
    30d
    99.73%
    p50
    1.36s
    p99
    9.11s
    Throughput
    146 tps
    Context
    1.0M
    $/Mtok
    $0.750 / $3.75
    google-ai-studio
  • Google AI Studio100% (best)
    Healthy24h 99.81%
    7d
    99.89%
    30d
    99.68%
    p50
    1.32s (best)
    p99
    8.11s
    Throughput
    189 tps (best)
    Context
    1.0M
    $/Mtok
    $0.375 / $1.88 (best)
    google-ai-studio/flex
  • Google AI Studio100% (best)
    Healthy24h 99.69%
    7d
    98.69%
    30d
    98.63%
    p50
    1.92s
    p99
    5.52s (best)
    Throughput
    50 tps
    Context
    1.0M
    $/Mtok
    $1.35 / $6.75
    google-ai-studio/priority
  • Google98.61%
    Healthy24h 97.45%
    7d
    95.86%
    30d
    97.43%
    p50
    2.40s
    p99
    26.1s
    Throughput
    77 tps
    Context
    1.0M
    $/Mtok
    $0.750 / $3.75
    google-vertex/global
  • Down24h 76.33%
    7d
    83.04%
    30d
    87.46%
    p50
    13.2s
    p99
    134s
    Throughput
    46 tps
    Context
    1.0M
    $/Mtok
    $0.375 / $1.88 (best)
    google-vertex/global/flex

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.