modelstatus.dev

Gemini 3.5 Flash

Gemini 3.5 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 Studio100% (best)
    Healthy24h 99.45%
    7d
    99.42%
    30d
    99.42%
    p50
    1.81s
    p99
    13.5s
    Throughput
    195 tps
    Context
    1.0M
    $/Mtok
    $1.50 / $9.00
    google-ai-studio
  • Google AI Studio100% (best)
    Healthy24h 99.45%
    7d
    99.42%
    30d
    99.42%
    p50
    1.03s
    p99
    9.27s
    Throughput
    117 tps
    Context
    1.0M
    $/Mtok
    $0.750 / $4.50 (best)
    google-ai-studio/flex
  • Google AI Studio100% (best)
    Healthy24h 99.45%
    7d
    99.42%
    30d
    99.42%
    p50
    1.62s
    p99
    4.01s
    Throughput
    196 tps (best)
    Context
    1.0M
    $/Mtok
    $2.70 / $16.20
    google-ai-studio/priority
  • Google99.69%
    Healthy24h 99.68%
    7d
    99.67% (best)
    30d
    99.67% (best)
    p50
    1.70s
    p99
    10.7s
    Throughput
    128 tps
    Context
    1.0M
    $/Mtok
    $1.50 / $9.00
    google-vertex/global
  • Google99.69%
    Healthy24h 99.68%
    7d
    99.67% (best)
    30d
    99.67% (best)
    p50
    14.4s
    p99
    37.1s
    Throughput
    57 tps
    Context
    1.0M
    $/Mtok
    $0.750 / $4.50 (best)
    google-vertex/global/flex
  • Google99.69%
    Healthy24h 99.68%
    7d
    99.67% (best)
    30d
    99.67% (best)
    p50
    963ms (best)
    p99
    2.38s (best)
    Throughput
    98 tps
    Context
    1.0M
    $/Mtok
    $2.70 / $16.20
    google-vertex/global/priority
  • No data24h
    7d
    30d
    p50
    p99
    Throughput
    Context
    1.0M
    $/Mtok
    $1.65 / $9.90
    google-vertex/us

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.