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
    261ms
    p99
    1.91s
    Throughput
    143 tps
    Context
    131K
    $/Mtok
    $0.990 / $1.49
    cerebras/fp16fp16
  • Healthy24h 99.84%
    7d
    99.51%
    30d
    99.51%
    p50
    575ms
    p99
    3.66s
    Throughput
    42 tps
    Context
    262K
    $/Mtok
    $0.090 / $0.340
    deepinfra/turbofp4
  • Healthy24h 99.20%
    7d
    99.55%
    30d
    99.55%
    p50
    698ms
    p99
    6.19s
    Throughput
    86 tps
    Context
    262K
    $/Mtok
    $0.140 / $0.400
    friendli
  • Healthy24h 99.92%
    7d
    99.63%
    30d
    99.63%
    p50
    196ms
    p99
    2.53s
    Throughput
    91 tps
    Context
    262K
    $/Mtok
    $0.750 / $1.00
    modelrun/fp4fp4
  • Venice99.86%
    Healthy24h 99.74%
    7d
    99.73%
    30d
    99.73%
    p50
    1.32s
    p99
    6.72s
    Throughput
    37 tps
    Context
    256K
    $/Mtok
    $0.120 / $0.360
    venice/bf16bf16
  • Crusoe99.66%
    Healthy24h 98.77%
    7d
    98.60%
    30d
    98.60%
    p50
    559ms
    p99
    14.2s
    Throughput
    37 tps
    Context
    262K
    $/Mtok
    $0.140 / $0.400
    crusoe
  • Novita99.30%
    Healthy24h 99.08%
    7d
    77.95%
    30d
    77.95%
    p50
    918ms
    p99
    3.35s
    Throughput
    9.0 tps
    Context
    262K
    $/Mtok
    $0.140 / $0.400
    novita/bf16bf16
  • DeepInfra99.24%
    Healthy24h 98.33%
    7d
    90.52%
    30d
    90.52%
    p50
    640ms
    p99
    8.12s
    Throughput
    57 tps
    Context
    262K
    $/Mtok
    $0.130 / $0.380
    deepinfra/fp8fp8
  • Parasail99.06%
    Healthy24h 99.49%
    7d
    99.27%
    30d
    99.27%
    p50
    912ms
    p99
    11.4s
    Throughput
    38 tps
    Context
    262K
    $/Mtok
    $0.150 / $0.400
    parasail/fp8fp8
  • Together98.52%
    Healthy24h 89.68%
    7d
    95.27%
    30d
    95.27%
    p50
    364ms
    p99
    11.2s
    Throughput
    32 tps
    Context
    262K
    $/Mtok
    $0.390 / $0.970
    together
  • CoreWeave98.43%
    Healthy24h 98.18%
    7d
    98.52%
    30d
    98.52%
    p50
    550ms
    p99
    21.4s
    Throughput
    31 tps
    Context
    262K
    $/Mtok
    $0.100 / $0.340
    coreweave/bf16bf16
  • Healthy24h 97.01%
    7d
    97.42%
    30d
    97.42%
    p50
    867ms
    p99
    9.71s
    Throughput
    27 tps
    Context
    262K
    $/Mtok
    $0.080 / $0.350
    open-inference/bf16bf16
  • Degraded24h 74.93%
    7d
    93.79%
    30d
    93.79%
    p50
    1.42s
    p99
    8.87s
    Throughput
    25 tps
    Context
    262K
    $/Mtok
    $0.130 / $0.400
    siliconflow/fp8fp8
  • Phala0.00%
    Down24h 81.36%
    7d
    89.69%
    30d
    89.69%
    p50
    p99
    Throughput
    Context
    262K
    $/Mtok
    $0.150 / $0.460
    phala
  • Down24h 86.41%
    7d
    63.42%
    30d
    63.42%
    p50
    10.1s
    p99
    115s
    Throughput
    5.0 tps
    Context
    131K
    $/Mtok
    $0.120 / $0.370
    chutes/fp4fp4
  • No data24h 74.45%
    7d
    87.46%
    30d
    87.46%
    p50
    2.09s
    p99
    8.26s
    Throughput
    21 tps
    Context
    131K
    $/Mtok
    $0.270 / $0.760
    deepinfra/ultrafp8
  • No data24h 98.67%
    7d
    96.98%
    30d
    96.98%
    p50
    1.60s
    p99
    9.55s
    Throughput
    20 tps
    Context
    131K
    $/Mtok
    $0.380 / $1.15
    sambanova

Measured 5m 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.