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
  • Cerebras100%
    Healthy24h 100%
    p50
    252ms
    p99
    3.50s
    Throughput
    203 tps
    Context
    131K
    $/Mtok
    $0.990 / $1.49
    cerebras/fp16fp16
  • ModelRun99.98%
    Healthy24h 98.91%
    p50
    216ms
    p99
    2.83s
    Throughput
    43 tps
    Context
    262K
    $/Mtok
    $0.750 / $1.00
    modelrun/fp4fp4
  • Friendli99.94%
    Healthy24h 99.83%
    p50
    627ms
    p99
    6.28s
    Throughput
    57 tps
    Context
    262K
    $/Mtok
    $0.140 / $0.400
    friendli
  • Parasail99.80%
    Healthy24h 99.12%
    p50
    433ms
    p99
    6.64s
    Throughput
    21 tps
    Context
    262K
    $/Mtok
    $0.150 / $0.400
    parasail/fp8fp8
  • DeepInfra99.66%
    Healthy24h 99.12%
    p50
    432ms
    p99
    2.71s
    Throughput
    32 tps
    Context
    262K
    $/Mtok
    $0.090 / $0.340
    deepinfra/turbofp4
  • Venice99.46%
    Healthy24h 99.61%
    p50
    744ms
    p99
    20.7s
    Throughput
    31 tps
    Context
    256K
    $/Mtok
    $0.120 / $0.360
    venice/bf16bf16
  • CoreWeave99.39%
    Healthy24h 98.24%
    p50
    674ms
    p99
    17.7s
    Throughput
    27 tps
    Context
    262K
    $/Mtok
    $0.100 / $0.340
    coreweave/bf16bf16
  • Phala98.95%
    Healthy24h 95.30%
    p50
    1.53s
    p99
    25.4s
    Throughput
    18 tps
    Context
    262K
    $/Mtok
    $0.150 / $0.460
    phala
  • Crusoe98.48%
    Healthy24h 98.97%
    p50
    911ms
    p99
    18.8s
    Throughput
    23 tps
    Context
    262K
    $/Mtok
    $0.140 / $0.400
    crusoe
  • OpenInference96.88%
    Healthy24h 95.74%
    p50
    1.75s
    p99
    30.3s
    Throughput
    10 tps
    Context
    262K
    $/Mtok
    $0.080 / $0.350
    open-inference/bf16bf16
  • SiliconFlow94.93%
    Degraded24h 95.96%
    p50
    2.33s
    p99
    13.1s
    Throughput
    13 tps
    Context
    262K
    $/Mtok
    $0.130 / $0.400
    siliconflow/fp8fp8
  • SambaNova94.59%
    Degraded24h 97.32%
    p50
    1.86s
    p99
    9.66s
    Throughput
    48 tps
    Context
    262K
    $/Mtok
    $0.380 / $1.15
    sambanova
  • Together86.10%
    Down24h 92.41%
    p50
    1.57s
    p99
    14.4s
    Throughput
    4.0 tps
    Context
    262K
    $/Mtok
    $0.390 / $0.970
    together
  • DeepInfra78.99%
    Down24h 58.15%
    p50
    6.51s
    p99
    17.4s
    Throughput
    15 tps
    Context
    131K
    $/Mtok
    $0.270 / $0.760
    deepinfra/ultrafp8
  • DeepInfra70.45%
    Down24h 94.25%
    p50
    2.57s
    p99
    22.8s
    Throughput
    5.0 tps
    Context
    262K
    $/Mtok
    $0.130 / $0.380
    deepinfra/fp8fp8
  • Novita56.40%
    Down24h 61.64%
    p50
    3.63s
    p99
    28.4s
    Throughput
    2.0 tps
    Context
    262K
    $/Mtok
    $0.140 / $0.400
    novita/bf16bf16
  • Chutes
    No data24h 90.50%
    p50
    p99
    Throughput
    Context
    131K
    $/Mtok
    $0.120 / $0.370
    chutes/fp4fp4

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

1 endpoint reporting no data is 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 and p99 are OpenRouter's rolling 30-minute windows.

Throughput

Median tokens per second.