modelstatus.dev

Gemini 3 Flash Preview

Gemini 3 Flash Preview: providers compared

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

  • Google AI Studio99.70% (best)
    Healthy24h 99.47%
    7d
    99.63% (best)
    30d
    99.63% (best)
    p50
    1.02s
    p99
    11.3s
    Throughput
    64 tps
    Context
    1.0M
    $/Mtok
    $0.500 / $3.00
    google-ai-studio
  • Google AI Studio99.70% (best)
    Healthy24h 99.47%
    7d
    99.63% (best)
    30d
    99.63% (best)
    p50
    2.22s
    p99
    56.7s
    Throughput
    66 tps
    Context
    1.0M
    $/Mtok
    $0.250 / $1.50 (best)
    google-ai-studio/flex
  • Google AI Studio99.70% (best)
    Healthy24h 99.47%
    7d
    99.63% (best)
    30d
    99.63% (best)
    p50
    968ms (best)
    p99
    3.38s (best)
    Throughput
    67 tps (best)
    Context
    1.0M
    $/Mtok
    $0.900 / $5.40
    google-ai-studio/priority
  • Google98.35%
    Healthy24h 99.10%
    7d
    98.41%
    30d
    98.41%
    p50
    1.26s
    p99
    11.6s
    Throughput
    56 tps
    Context
    1.0M
    $/Mtok
    $0.500 / $3.00
    google-vertex/global
  • Google98.35%
    Healthy24h 99.10%
    7d
    98.41%
    30d
    98.41%
    p50
    23.0s
    p99
    104s
    Throughput
    9.0 tps
    Context
    1.0M
    $/Mtok
    $0.250 / $1.50 (best)
    google-vertex/global/flex
  • Google98.35%
    Healthy24h 99.10%
    7d
    98.41%
    30d
    98.41%
    p50
    1.03s
    p99
    3.52s
    Throughput
    65 tps
    Context
    1.0M
    $/Mtok
    $0.900 / $5.40
    google-vertex/global/priority

Measured 3m 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.