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

	State
Cerebrascerebras/fp16fp16	Healthy	100%	100%	99.99%	99.99%	261ms	1.54s	166 tps	131K	$0.990 / $1.49
Crusoecrusoe	Healthy	100%	98.76%	98.60%	98.60%	654ms	15.5s	25 tps	262K	$0.140 / $0.400
Friendlifriendli	Healthy	100%	99.19%	99.55%	99.55%	556ms	5.85s	95 tps	262K	$0.140 / $0.400
OpenInferenceopen-inference/bf16bf16	Healthy	100%	97.01%	97.44%	97.44%	680ms	11.9s	34 tps	262K	$0.080 / $0.350
Parasailparasail/fp8fp8	Healthy	100%	99.49%	99.27%	99.27%	977ms	14.5s	38 tps	262K	$0.150 / $0.400
SiliconFlowsiliconflow/fp8fp8	Healthy	100%	74.89%	93.86%	93.86%	1.41s	11.5s	26 tps	262K	$0.130 / $0.400
Venicevenice/bf16bf16	Healthy	100%	99.74%	99.73%	99.73%	1.20s	5.68s	39 tps	256K	$0.120 / $0.360
DeepInfradeepinfra/turbofp4	Healthy	99.96%	99.85%	99.51%	99.51%	564ms	3.83s	43 tps	262K	$0.090 / $0.340
ModelRunmodelrun/fp4fp4	Healthy	99.84%	99.92%	99.64%	99.64%	197ms	7.42s	92 tps	262K	$0.750 / $1.00
Novitanovita/bf16bf16	Healthy	99.76%	99.06%	78.32%	78.32%	897ms	4.49s	9.0 tps	262K	$0.140 / $0.400
DeepInfradeepinfra/fp8fp8	Healthy	99.70%	98.35%	90.43%	90.43%	759ms	8.19s	44 tps	262K	$0.130 / $0.380
CoreWeavecoreweave/bf16bf16	Healthy	98.55%	98.16%	98.52%	98.52%	730ms	26.6s	29 tps	262K	$0.100 / $0.340
Togethertogether	Down	86.49%	89.68%	95.30%	95.30%	406ms	50.6s	38 tps	262K	$0.390 / $0.970
Chuteschutes/fp4fp4	Down	72.92%	86.14%	63.05%	63.05%	10.4s	108s	5.0 tps	131K	$0.120 / $0.370
DeepInfradeepinfra/ultrafp8	No data	—	74.56%	87.73%	87.73%	2.21s	6.06s	23 tps	131K	$0.270 / $0.760
Phalaphala	Down	—	80.49%	88.05%	88.05%	561ms	4.19s	52 tps	262K	$0.150 / $0.460
SambaNovasambanova	No data	—	98.65%	96.98%	96.98%	1.56s	8.66s	20 tps	131K	$0.380 / $1.15

Cerebras100%
Healthy24h 100%
7d
99.99%
30d
99.99%
p50
261ms
p99
1.54s
Throughput
166 tps
Context
131K
$/Mtok
$0.990 / $1.49
cerebras/fp16fp16
Crusoe100%
Healthy24h 98.76%
7d
98.60%
30d
98.60%
p50
654ms
p99
15.5s
Throughput
25 tps
Context
262K
$/Mtok
$0.140 / $0.400
crusoe
Friendli100%
Healthy24h 99.19%
7d
99.55%
30d
99.55%
p50
556ms
p99
5.85s
Throughput
95 tps
Context
262K
$/Mtok
$0.140 / $0.400
friendli
OpenInference100%
Healthy24h 97.01%
7d
97.44%
30d
97.44%
p50
680ms
p99
11.9s
Throughput
34 tps
Context
262K
$/Mtok
$0.080 / $0.350
open-inference/bf16bf16
Parasail100%
Healthy24h 99.49%
7d
99.27%
30d
99.27%
p50
977ms
p99
14.5s
Throughput
38 tps
Context
262K
$/Mtok
$0.150 / $0.400
parasail/fp8fp8
SiliconFlow100%
Healthy24h 74.89%
7d
93.86%
30d
93.86%
p50
1.41s
p99
11.5s
Throughput
26 tps
Context
262K
$/Mtok
$0.130 / $0.400
siliconflow/fp8fp8
Venice100%
Healthy24h 99.74%
7d
99.73%
30d
99.73%
p50
1.20s
p99
5.68s
Throughput
39 tps
Context
256K
$/Mtok
$0.120 / $0.360
venice/bf16bf16
DeepInfra99.96%
Healthy24h 99.85%
7d
99.51%
30d
99.51%
p50
564ms
p99
3.83s
Throughput
43 tps
Context
262K
$/Mtok
$0.090 / $0.340
deepinfra/turbofp4
ModelRun99.84%
Healthy24h 99.92%
7d
99.64%
30d
99.64%
p50
197ms
p99
7.42s
Throughput
92 tps
Context
262K
$/Mtok
$0.750 / $1.00
modelrun/fp4fp4
Novita99.76%
Healthy24h 99.06%
7d
78.32%
30d
78.32%
p50
897ms
p99
4.49s
Throughput
9.0 tps
Context
262K
$/Mtok
$0.140 / $0.400
novita/bf16bf16
DeepInfra99.70%
Healthy24h 98.35%
7d
90.43%
30d
90.43%
p50
759ms
p99
8.19s
Throughput
44 tps
Context
262K
$/Mtok
$0.130 / $0.380
deepinfra/fp8fp8
CoreWeave98.55%
Healthy24h 98.16%
7d
98.52%
30d
98.52%
p50
730ms
p99
26.6s
Throughput
29 tps
Context
262K
$/Mtok
$0.100 / $0.340
coreweave/bf16bf16
Together86.49%
Down24h 89.68%
7d
95.30%
30d
95.30%
p50
406ms
p99
50.6s
Throughput
38 tps
Context
262K
$/Mtok
$0.390 / $0.970
together
Chutes72.92%
Down24h 86.14%
7d
63.05%
30d
63.05%
p50
10.4s
p99
108s
Throughput
5.0 tps
Context
131K
$/Mtok
$0.120 / $0.370
chutes/fp4fp4
DeepInfra—
No data24h 74.56%
7d
87.73%
30d
87.73%
p50
2.21s
p99
6.06s
Throughput
23 tps
Context
131K
$/Mtok
$0.270 / $0.760
deepinfra/ultrafp8
Phala—
Down24h 80.49%
7d
88.05%
30d
88.05%
p50
561ms
p99
4.19s
Throughput
52 tps
Context
262K
$/Mtok
$0.150 / $0.460
phala
SambaNova—
No data24h 98.65%
7d
96.98%
30d
96.98%
p50
1.56s
p99
8.66s
Throughput
20 tps
Context
131K
$/Mtok
$0.380 / $1.15
sambanova

Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

Price changes

Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 10:40 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 10:35 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 10:30 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 10:25 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 10:20 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 10:15 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 10:10 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 10:05 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 10:00 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 09:55 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 09:50 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 09:45 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 09:40 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 09:35 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 09:30 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 09:25 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 09:20 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 09:15 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 09:10 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 09:05 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 09:00 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 08:55 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 08:50 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 08:45 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 08:40 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 08:35 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 08:30 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 08:25 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 08:20 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 08:15 UTC

History

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.