modelstatus.dev

Gemma 4 26B A4B

google/gemma-4-26b-a4b-itInputimagetextvideoOutputtext

Compare its 14 providersIncident RSSCompare with Gemma 4 31B, Gemma 4 26B A4B (free), Gemma 4 31B (free)

CompareGemma 4 26B A4B
  • Healthy24h 99.98%
    7d
    99.98%
    30d
    99.47%
    p50
    196ms
    p99
    1.13s
    Throughput
    92 tps
    Context
    262K
    $/Mtok
    $0.100 / $0.300
    coreweave/bf16bf16
  • Healthy24h 99.79%
    7d
    99.63%
    30d
    99.41%
    p50
    708ms
    p99
    5.70s
    Throughput
    31 tps
    Context
    262K
    $/Mtok
    $0.070 / $0.340
    deepinfra/fp8fp8
  • Google100%
    Healthy24h 99.21%
    7d
    96.32%
    30d
    96.90%
    p50
    983ms
    p99
    8.32s
    Throughput
    42 tps
    Context
    262K
    $/Mtok
    $0.150 / $0.600
    google-vertex/global
  • Io Net100%
    Healthy24h 98.65%
    7d
    98.59%
    30d
    98.77%
    p50
    321ms
    p99
    2.56s
    Throughput
    81 tps
    Context
    262K
    $/Mtok
    $0.150 / $0.500
    io-net/bf16bf16
  • Healthy24h 99.91%
    7d
    99.72%
    30d
    99.23%
    p50
    279ms
    p99
    1.82s
    Throughput
    82 tps
    Context
    262K
    $/Mtok
    $0.068 / $0.225
    nextbit/bf16bf16
  • Novita100%
    Healthy24h 99.89%
    7d
    99.54%
    30d
    99.49%
    p50
    942ms
    p99
    3.16s
    Throughput
    67 tps
    Context
    262K
    $/Mtok
    $0.130 / $0.400
    novita/bf16bf16
  • Healthy24h 97.72%
    7d
    94.86%
    30d
    96.92%
    p50
    1.69s
    p99
    11.2s
    Throughput
    36 tps
    Context
    262K
    $/Mtok
    $0.140 / $0.400
    siliconflow/fp8fp8
  • Venice100%
    Healthy24h 99.77%
    7d
    99.48%
    30d
    98.92%
    p50
    1.13s
    p99
    6.29s
    Throughput
    47 tps
    Context
    256K
    $/Mtok
    $0.130 / $0.400
    venice/bf16bf16
  • Healthy24h 99.84%
    7d
    99.82%
    30d
    99.56%
    p50
    435ms
    p99
    4.33s
    Throughput
    42 tps
    Context
    256K
    $/Mtok
    $0.100 / $0.300
    cloudflare
  • Darkbloom99.92%
    Healthy24h 99.98%
    7d
    99.99%
    30d
    99.94%
    p50
    1.06s
    p99
    5.99s
    Throughput
    63 tps
    Context
    131K
    $/Mtok
    $0.042 / $0.220
    darkbloom
  • DekaLLM99.90%
    Healthy24h 99.87%
    7d
    99.85%
    30d
    99.80%
    p50
    628ms
    p99
    4.39s
    Throughput
    70 tps
    Context
    262K
    $/Mtok
    $0.060 / $0.330
    dekallm/bf16bf16
  • Parasail99.86%
    Healthy24h 99.81%
    7d
    99.39%
    30d
    99.00%
    p50
    736ms
    p99
    5.40s
    Throughput
    56 tps
    Context
    262K
    $/Mtok
    $0.130 / $0.400
    parasail/bf16bf16
  • No data24h —
    7d
    97.80%
    30d
    97.68%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    256K
    $/Mtok
    $0.080 / $0.320
    makora
  • Reka—
    No data24h —
    7d
    97.99%
    30d
    98.59%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    262K
    $/Mtok
    $0.060 / $0.200
    reka

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

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 · 14 endpoints · 47 days with data, 94 endpoint-days below 90%.

Price changes