modelstatus.dev

Gemma 3 27B

google/gemma-3-27b-itInputtextimageOutputtext

Compare its 5 providersIncident RSSCompare with Gemma 3 12B, Gemma 3 4B, Gemma 4 31B

CompareGemma 3 27B
  • DeepInfra99.84%
    Healthy24h 98.78%
    7d
    99.44%
    30d
    99.47%
    p50
    2.38s
    p99
    14.1s
    Throughput
    16 tps
    Context
    131K
    $/Mtok
    $0.080 / $0.160
    deepinfra/fp8fp8
  • Novita99.64%
    Healthy24h 98.96%
    7d
    95.44%
    30d
    93.99%
    p50
    1.44s
    p99
    7.27s
    Throughput
    29 tps
    Context
    98K
    $/Mtok
    $0.119 / $0.200
    novita/bf16bf16
  • Parasail99.47%
    Healthy24h 99.07%
    7d
    99.22%
    30d
    99.30%
    p50
    620ms
    p99
    7.10s
    Throughput
    38 tps
    Context
    131K
    $/Mtok
    $0.080 / $0.450
    parasail/fp8fp8
  • Nebius93.37%
    Down24h 89.21%
    7d
    89.63%
    30d
    88.35%
    p50
    2.20s
    p99
    27.2s
    Throughput
    10 tps
    Context
    110K
    $/Mtok
    $0.100 / $0.300
    nebius/fp8fp8
  • No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    262K
    $/Mtok
    $0.150 / $0.460
    phala

Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

1 endpoint has no chartable data in this range.

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, averaged over the hour.

Throughput

Median tokens per second.

Daily availability

One row per endpoint · one dot per day · last 90 days.

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 5 endpoints · 47 days with data, 102 endpoint-days below 90%.