modelstatus.dev

Gemini 2.5 Pro Preview 06-05

google/gemini-2.5-pro-preview

Compare with Gemini 2.5 Pro, Gemini 2.5 Pro Preview 05-06, Gemini 2.5 Pro (batch)

CompareGemini 2.5 Pro Preview 06-05
  • Healthy24h 85.48%
    7d
    94.54%
    30d
    94.54%
    p50
    3.12s
    p99
    15.9s
    Throughput
    104 tps
    Context
    1.0M
    $/Mtok
    $1.25 / $10.00
    google-ai-studio
  • Healthy24h 85.48%
    7d
    94.54%
    30d
    94.54%
    p50
    4.79s
    p99
    11.8s
    Throughput
    20 tps
    Context
    1.0M
    $/Mtok
    $0.625 / $5.00
    google-ai-studio/flex
  • Healthy24h 85.48%
    7d
    94.54%
    30d
    94.54%
    p50
    p99
    Throughput
    Context
    1.0M
    $/Mtok
    $2.25 / $18.00
    google-ai-studio/priority
  • Google97.58%
    Healthy24h 99.16%
    7d
    99.25%
    30d
    99.25%
    p50
    2.58s
    p99
    10.2s
    Throughput
    84 tps
    Context
    1.0M
    $/Mtok
    $1.25 / $10.00
    google-vertex/global
  • Google97.58%
    Healthy24h 99.16%
    7d
    99.25%
    30d
    99.25%
    p50
    p99
    Throughput
    Context
    1.0M
    $/Mtok
    $0.625 / $5.00
    google-vertex/global/flex
  • Google97.58%
    Healthy24h 99.16%
    7d
    99.25%
    30d
    99.25%
    p50
    2.12s
    p99
    3.29s
    Throughput
    72 tps
    Context
    1.0M
    $/Mtok
    $2.25 / $18.00
    google-vertex/global/priority
  • Google76.32%
    Down24h 85.28%
    7d
    66.58%
    30d
    66.58%
    p50
    7.70s
    p99
    21.9s
    Throughput
    97 tps
    Context
    1.0M
    $/Mtok
    $1.25 / $10.00
    google-vertex/us
  • No data24h 95.23%
    7d
    86.26%
    30d
    86.26%
    p50
    12.1s
    p99
    40.9s
    Throughput
    98 tps
    Context
    1.0M
    $/Mtok
    $1.25 / $10.00
    google-vertex/eu

Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

1 endpoint reporting no data is omitted from the charts.

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.