modelstatus.dev

Gemma 4 31B

google/gemma-4-31b-it

Compare with Gemma 4 26B A4B , Gemma 4 26B A4B (free), Gemma 4 31B (free)

CompareGemma 4 31B
  • Healthy24h 100%
    7d
    99.99%
    30d
    99.99%
    p50
    284ms
    p99
    1.48s
    Throughput
    114 tps
    Context
    131K
    $/Mtok
    $0.990 / $1.49
    cerebras/fp16fp16
  • Crusoe100%
    Healthy24h 98.79%
    7d
    98.60%
    30d
    98.60%
    p50
    619ms
    p99
    6.69s
    Throughput
    37 tps
    Context
    262K
    $/Mtok
    $0.140 / $0.400
    crusoe
  • Healthy24h 99.19%
    7d
    99.55%
    30d
    99.55%
    p50
    603ms
    p99
    5.56s
    Throughput
    90 tps
    Context
    262K
    $/Mtok
    $0.140 / $0.400
    friendli
  • Healthy24h 97.01%
    7d
    97.44%
    30d
    97.44%
    p50
    573ms
    p99
    18.4s
    Throughput
    34 tps
    Context
    262K
    $/Mtok
    $0.080 / $0.350
    open-inference/bf16bf16
  • Venice100%
    Healthy24h 99.75%
    7d
    99.73%
    30d
    99.73%
    p50
    1.21s
    p99
    8.19s
    Throughput
    39 tps
    Context
    256K
    $/Mtok
    $0.120 / $0.360
    venice/bf16bf16
  • DeepInfra99.93%
    Healthy24h 99.85%
    7d
    99.51%
    30d
    99.51%
    p50
    491ms
    p99
    3.53s
    Throughput
    45 tps
    Context
    262K
    $/Mtok
    $0.090 / $0.340
    deepinfra/turbofp4
  • ModelRun99.91%
    Healthy24h 99.92%
    7d
    99.64%
    30d
    99.64%
    p50
    194ms
    p99
    7.17s
    Throughput
    94 tps
    Context
    262K
    $/Mtok
    $0.750 / $1.00
    modelrun/fp4fp4
  • Parasail99.60%
    Healthy24h 99.49%
    7d
    99.27%
    30d
    99.27%
    p50
    898ms
    p99
    13.9s
    Throughput
    42 tps
    Context
    262K
    $/Mtok
    $0.150 / $0.400
    parasail/fp8fp8
  • Together99.34%
    Healthy24h 89.71%
    7d
    95.30%
    30d
    95.30%
    p50
    222ms
    p99
    64.2s
    Throughput
    33 tps
    Context
    262K
    $/Mtok
    $0.390 / $0.970
    together
  • Novita99.29%
    Healthy24h 99.06%
    7d
    78.32%
    30d
    78.32%
    p50
    900ms
    p99
    4.74s
    Throughput
    10 tps
    Context
    262K
    $/Mtok
    $0.140 / $0.400
    novita/bf16bf16
  • Healthy24h 74.90%
    7d
    93.86%
    30d
    93.86%
    p50
    1.44s
    p99
    10.4s
    Throughput
    27 tps
    Context
    262K
    $/Mtok
    $0.130 / $0.400
    siliconflow/fp8fp8
  • DeepInfra98.27%
    Healthy24h 98.35%
    7d
    90.43%
    30d
    90.43%
    p50
    729ms
    p99
    9.72s
    Throughput
    46 tps
    Context
    262K
    $/Mtok
    $0.130 / $0.380
    deepinfra/fp8fp8
  • CoreWeave96.40%
    Healthy24h 98.14%
    7d
    98.52%
    30d
    98.52%
    p50
    700ms
    p99
    24.7s
    Throughput
    28 tps
    Context
    262K
    $/Mtok
    $0.100 / $0.340
    coreweave/bf16bf16
  • Down24h 86.35%
    7d
    63.05%
    30d
    63.05%
    p50
    16.4s
    p99
    150s
    Throughput
    4.0 tps
    Context
    131K
    $/Mtok
    $0.120 / $0.370
    chutes/fp4fp4
  • No data24h 74.54%
    7d
    87.73%
    30d
    87.73%
    p50
    2.37s
    p99
    8.86s
    Throughput
    21 tps
    Context
    131K
    $/Mtok
    $0.270 / $0.760
    deepinfra/ultrafp8
  • Down24h 80.45%
    7d
    88.05%
    30d
    88.05%
    p50
    561ms
    p99
    4.19s
    Throughput
    52 tps
    Context
    262K
    $/Mtok
    $0.150 / $0.460
    phala
  • No data24h 98.66%
    7d
    96.98%
    30d
    96.98%
    p50
    1.53s
    p99
    5.55s
    Throughput
    25 tps
    Context
    131K
    $/Mtok
    $0.380 / $1.15
    sambanova

Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

Price changes

2 endpoints reporting no data are 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.