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
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Cerebrascerebras/fp16fp16 | Healthy | 100% | 100% | 252ms | 3.50s | 203 tps | 131K | $0.990 / $1.49 |
ModelRunmodelrun/fp4fp4 | Healthy | 99.98% | 98.91% | 216ms | 2.83s | 43 tps | 262K | $0.750 / $1.00 |
Friendlifriendli | Healthy | 99.94% | 99.83% | 627ms | 6.28s | 57 tps | 262K | $0.140 / $0.400 |
Parasailparasail/fp8fp8 | Healthy | 99.80% | 99.12% | 433ms | 6.64s | 21 tps | 262K | $0.150 / $0.400 |
DeepInfradeepinfra/turbofp4 | Healthy | 99.66% | 99.12% | 432ms | 2.71s | 32 tps | 262K | $0.090 / $0.340 |
Venicevenice/bf16bf16 | Healthy | 99.46% | 99.61% | 744ms | 20.7s | 31 tps | 256K | $0.120 / $0.360 |
CoreWeavecoreweave/bf16bf16 | Healthy | 99.39% | 98.24% | 674ms | 17.7s | 27 tps | 262K | $0.100 / $0.340 |
Phalaphala | Healthy | 98.95% | 95.30% | 1.53s | 25.4s | 18 tps | 262K | $0.150 / $0.460 |
Crusoecrusoe | Healthy | 98.48% | 98.97% | 911ms | 18.8s | 23 tps | 262K | $0.140 / $0.400 |
OpenInferenceopen-inference/bf16bf16 | Healthy | 96.88% | 95.74% | 1.75s | 30.3s | 10 tps | 262K | $0.080 / $0.350 |
SiliconFlowsiliconflow/fp8fp8 | Degraded | 94.93% | 95.96% | 2.33s | 13.1s | 13 tps | 262K | $0.130 / $0.400 |
SambaNovasambanova | Degraded | 94.59% | 97.32% | 1.86s | 9.66s | 48 tps | 262K | $0.380 / $1.15 |
Togethertogether | Down | 86.10% | 92.41% | 1.57s | 14.4s | 4.0 tps | 262K | $0.390 / $0.970 |
DeepInfradeepinfra/ultrafp8 | Down | 78.99% | 58.15% | 6.51s | 17.4s | 15 tps | 131K | $0.270 / $0.760 |
DeepInfradeepinfra/fp8fp8 | Down | 70.45% | 94.25% | 2.57s | 22.8s | 5.0 tps | 262K | $0.130 / $0.380 |
Novitanovita/bf16bf16 | Down | 56.40% | 61.64% | 3.63s | 28.4s | 2.0 tps | 262K | $0.140 / $0.400 |
Chuteschutes/fp4fp4 | No data | — | 90.50% | — | — | — | 131K | $0.120 / $0.370 |
- 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 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
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, averaged over the hour.
Throughput
Median tokens per second.