Gemma 4 31B

google/gemma-4-31b-itInputOutput

Compare its 23 providers Incident RSSCompare with Gemma 4 26B A4B , Gemma 4 26B A4B (free), Gemma 4 31B (free)

CompareGemma 4 31B

	State
Friendlifriendli	Healthy	100%	99.06%	98.53%	98.95%	183ms	3.67s	97 tps	262K	$0.140 / $0.400
ModelRunmodelrun/fp4fp4	Healthy	100%	99.73%	99.78%	99.59%	78ms	1.39s	109 tps	262K	$0.750 / $1.00
Novitanovita/bf16bf16	Degraded	100%	81.76%	82.55%	89.07%	2.25s	36.3s	15 tps	262K	$0.140 / $0.400
SambaNovasambanova	Healthy	100%	97.62%	97.43%	94.93%	2.46s	6.40s	104 tps	131K	$0.380 / $1.15
CoreWeavecoreweave/fp4fp4	Healthy	99.92%	99.55%	99.02%	98.42%	457ms	5.88s	38 tps	262K	$0.100 / $0.340
Venicevenice/fp4fp4	Healthy	99.63%	98.95%	99.16%	98.75%	486ms	3.58s	28 tps	256K	$0.120 / $0.360
SiliconFlowsiliconflow/fp8fp8	Healthy	99.56%	84.78%	94.45%	90.69%	1.33s	5.84s	33 tps	262K	$0.750 / $1.00
DeepInfradeepinfra/turbofp4	Healthy	99.52%	98.90%	99.17%	99.11%	567ms	10.1s	28 tps	262K	$0.090 / $0.340
Crusoecrusoe/bf16bf16	Healthy	99.50%	98.86%	98.81%	95.16%	553ms	4.26s	17 tps	262K	$0.140 / $0.400
Parasailparasail/fp8fp8	Healthy	99.49%	99.33%	98.93%	99.06%	861ms	8.22s	20 tps	262K	$0.150 / $0.400
Chuteschutes/fp4fp4	Healthy	99.09%	96.14%	81.86%	86.54%	1.74s	12.4s	23 tps	131K	$0.120 / $0.370
DeepInfradeepinfra/fp8fp8	Healthy	98.14%	97.76%	97.97%	97.11%	2.95s	18.4s	13 tps	262K	$0.150 / $0.400
DekaLLMdekallm	Healthy	96.90%	97.26%	94.60%	94.60%	1.17s	25.5s	19 tps	262K	$0.100 / $0.330
Cerebrascerebras/fp16fp16	No data	—	—	—	83.21%	—	—	—	131K	$0.990 / $1.49
CoreWeavecoreweave/bf16bf16	No data	—	—	—	—	—	—	—	262K	$0.100 / $0.340
Crusoecrusoe	No data	—	—	—	95.22%	—	—	—	262K	$0.140 / $0.400
DeepInfradeepinfra/ultrafp8	No data	—	—	89.60%	84.21%	—	—	—	131K	$0.270 / $0.760
Io Netio-net	No data	—	99.12%	98.43%	98.53%	850ms	11.2s	38 tps	262K	$0.380 / $1.15
OpenInferenceopen-inference/bf16bf16	No data	—	—	—	—	—	—	—	262K	$0.070 / $0.350
Phalaphala	No data	—	—	—	—	—	—	—	262K	$0.150 / $0.460
Rekareka	No data	—	—	99.62%	98.23%	—	—	—	262K	$0.080 / $0.300
Togethertogether	No data	—	—	—	92.42%	—	—	—	262K	$0.390 / $0.970
Venicevenice/bf16bf16	No data	—	—	—	98.60%	—	—	—	256K	$0.120 / $0.360

Friendli100%
Healthy24h 99.06%
7d
98.53%
30d
98.95%
p50
183ms
p99
3.67s
Throughput
97 tps
Context
262K
$/Mtok
$0.140 / $0.400
friendli
ModelRun100%
Healthy24h 99.73%
7d
99.78%
30d
99.59%
p50
78ms
p99
1.39s
Throughput
109 tps
Context
262K
$/Mtok
$0.750 / $1.00
modelrun/fp4fp4
Novita100%
Degraded24h 81.76%
7d
82.55%
30d
89.07%
p50
2.25s
p99
36.3s
Throughput
15 tps
Context
262K
$/Mtok
$0.140 / $0.400
novita/bf16bf16
SambaNova100%
Healthy24h 97.62%
7d
97.43%
30d
94.93%
p50
2.46s
p99
6.40s
Throughput
104 tps
Context
131K
$/Mtok
$0.380 / $1.15
sambanova
CoreWeave99.92%
Healthy24h 99.55%
7d
99.02%
30d
98.42%
p50
457ms
p99
5.88s
Throughput
38 tps
Context
262K
$/Mtok
$0.100 / $0.340
coreweave/fp4fp4
Venice99.63%
Healthy24h 98.95%
7d
99.16%
30d
98.75%
p50
486ms
p99
3.58s
Throughput
28 tps
Context
256K
$/Mtok
$0.120 / $0.360
venice/fp4fp4
SiliconFlow99.56%
Healthy24h 84.78%
7d
94.45%
30d
90.69%
p50
1.33s
p99
5.84s
Throughput
33 tps
Context
262K
$/Mtok
$0.750 / $1.00
siliconflow/fp8fp8
DeepInfra99.52%
Healthy24h 98.90%
7d
99.17%
30d
99.11%
p50
567ms
p99
10.1s
Throughput
28 tps
Context
262K
$/Mtok
$0.090 / $0.340
deepinfra/turbofp4
Crusoe99.50%
Healthy24h 98.86%
7d
98.81%
30d
95.16%
p50
553ms
p99
4.26s
Throughput
17 tps
Context
262K
$/Mtok
$0.140 / $0.400
crusoe/bf16bf16
Parasail99.49%
Healthy24h 99.33%
7d
98.93%
30d
99.06%
p50
861ms
p99
8.22s
Throughput
20 tps
Context
262K
$/Mtok
$0.150 / $0.400
parasail/fp8fp8
Chutes99.09%
Healthy24h 96.14%
7d
81.86%
30d
86.54%
p50
1.74s
p99
12.4s
Throughput
23 tps
Context
131K
$/Mtok
$0.120 / $0.370
chutes/fp4fp4
DeepInfra98.14%
Healthy24h 97.76%
7d
97.97%
30d
97.11%
p50
2.95s
p99
18.4s
Throughput
13 tps
Context
262K
$/Mtok
$0.150 / $0.400
deepinfra/fp8fp8
DekaLLM96.90%
Healthy24h 97.26%
7d
94.60%
30d
94.60%
p50
1.17s
p99
25.5s
Throughput
19 tps
Context
262K
$/Mtok
$0.100 / $0.330
dekallm
Cerebras—
No data24h —
7d
—
30d
83.21%
p50
—
p99
—
Throughput
—
Context
131K
$/Mtok
$0.990 / $1.49
cerebras/fp16fp16
CoreWeave—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.100 / $0.340
coreweave/bf16bf16
Crusoe—
No data24h —
7d
—
30d
95.22%
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.140 / $0.400
crusoe
DeepInfra—
No data24h —
7d
89.60%
30d
84.21%
p50
—
p99
—
Throughput
—
Context
131K
$/Mtok
$0.270 / $0.760
deepinfra/ultrafp8
Io Net—
No data24h 99.12%
7d
98.43%
30d
98.53%
p50
850ms
p99
11.2s
Throughput
38 tps
Context
262K
$/Mtok
$0.380 / $1.15
io-net
OpenInference—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.070 / $0.350
open-inference/bf16bf16
Phala—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.150 / $0.460
phala
Reka—
No data24h —
7d
99.62%
30d
98.23%
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.080 / $0.300
reka
Together—
No data24h —
7d
—
30d
92.42%
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.390 / $0.970
together
Venice—
No data24h —
7d
—
30d
98.60%
p50
—
p99
—
Throughput
—
Context
256K
$/Mtok
$0.120 / $0.360
venice/bf16bf16

Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

History

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, averaged over the hour.

Throughput

Median tokens per second.

Daily availability

One row per endpoint · one dot per day · last 90 days.

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 23 endpoints · 47 days with data, 305 endpoint-days below 90%.

Price changes

Gemma 4 31B ModelRunmodelrun/fp4$0.750 / $1.00cache read $0.750 → $0.2002026-10-02 15:20 UTC
Gemma 4 31B DeepInfradeepinfra/fp8$0.130 → $0.150 / $0.380 → $0.4002026-10-01 20:20 UTC
Gemma 4 31B DeepInfradeepinfra/fp8$0.150 → $0.130 / $0.400 → $0.3802026-10-01 20:15 UTC
Gemma 4 31B DeepInfradeepinfra/fp8$0.130 → $0.150 / $0.380 → $0.4002026-10-01 20:05 UTC
Gemma 4 31B DekaLLMdekallm$0.060 → $0.100 / $0.330cache read — → $0.0502026-09-30 15:31 UTC
Gemma 4 31B DekaLLMdekallm$0.100 → $0.060 / $0.330cache read $0.050 → —2026-09-30 15:26 UTC
Gemma 4 31B DekaLLMdekallm$0.060 → $0.100 / $0.330cache read — → $0.0502026-09-30 15:06 UTC
Gemma 4 31B Rekareka$0.090 → $0.080 / $0.340 → $0.3002026-09-26 10:45 UTC
Gemma 4 31B Io Netio-net$0.380 / $1.15cache read — → $0.1902026-09-25 15:55 UTC
Gemma 4 31B SiliconFlowsiliconflow/fp8$0.130 → $0.750 / $0.400 → $1.00cache read — → $0.2502026-09-10 05:40 UTC
Gemma 4 31B OpenInferenceopen-inference/bf16$0.080 → $0.070 / $0.350cache read $0.010 → $0.1002026-08-29 01:40 UTC
Gemma 4 31B Togethertogether$0.280 → $0.390 / $0.860 → $0.9702026-08-27 21:55 UTC
Gemma 4 31B Togethertogether$0.390 → $0.280 / $0.970 → $0.8602026-08-19 02:50 UTC
Gemma 4 31B Togethertogether$0.280 → $0.390 / $0.860 → $0.9702026-08-19 02:45 UTC