modelstatus.dev

Gemma 4 26B A4B

Gemma 4 26B A4B : providers compared

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

  • Cloudflare100% (best)
    Healthy24h 99.53%
    7d
    94.59%
    30d
    94.59%
    p50
    566ms
    p99
    11.7s
    Throughput
    54 tps (best)
    Context
    256K
    $/Mtok
    $0.100 / $0.300
    cloudflare
  • Novita100% (best)
    Healthy24h 97.48%
    7d
    95.77%
    30d
    95.77%
    p50
    830ms
    p99
    5.72s
    Throughput
    23 tps
    Context
    262K
    $/Mtok
    $0.130 / $0.400
    novita/bf16bf16
  • DeepInfra99.86%
    Healthy24h 99.84%
    7d
    99.45%
    30d
    99.45%
    p50
    420ms
    p99
    4.13s (best)
    Throughput
    20 tps
    Context
    262K
    $/Mtok
    $0.070 / $0.340
    deepinfra/fp8fp8
  • NextBit99.64%
    Healthy24h 99.83%
    7d
    99.82% (best)
    30d
    99.82% (best)
    p50
    814ms
    p99
    5.56s
    Throughput
    19 tps
    Context
    262K
    $/Mtok
    $0.100 / $0.400
    nextbit/bf16bf16
  • Healthy24h 99.50%
    7d
    99.36%
    30d
    99.36%
    p50
    1.31s
    p99
    7.49s
    Throughput
    19 tps
    Context
    262K
    $/Mtok
    $0.120 / $0.400
    siliconflow/fp8fp8
  • Venice99.40%
    Healthy24h 99.39%
    7d
    99.34%
    30d
    99.34%
    p50
    960ms
    p99
    7.27s
    Throughput
    19 tps
    Context
    256K
    $/Mtok
    $0.130 / $0.400
    venice/bf16bf16
  • Parasail99.10%
    Healthy24h 98.96%
    7d
    98.65%
    30d
    98.65%
    p50
    677ms
    p99
    8.13s
    Throughput
    23 tps
    Context
    262K
    $/Mtok
    $0.130 / $0.400
    parasail/bf16bf16
  • Google98.84%
    Healthy24h 98.57%
    7d
    98.10%
    30d
    98.10%
    p50
    386ms (best)
    p99
    9.33s
    Throughput
    29 tps
    Context
    262K
    $/Mtok
    $0.150 / $0.600
    google-vertex/global
  • Darkbloom97.09%
    Healthy24h 95.66%
    7d
    95.82%
    30d
    95.82%
    p50
    3.46s
    p99
    21.0s
    Throughput
    6.0 tps
    Context
    131K
    $/Mtok
    $0.050 / $0.250 (best)
    darkbloom

Measured 4m 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.