Gemma 4 31B: providers compared

Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.

Current state

	State
Crusoecrusoe/bf16bf16	Healthy	100%◆ (best)	99.44%	98.56%	95.61%	691ms	8.65s	14 tps	262K	$0.140 / $0.400
Friendlifriendli	Healthy	100%◆ (best)	99.59%	99.46%	98.97%	984ms	10.00s	62 tps	262K	$0.140 / $0.400
Io Netio-net	Healthy	100%◆ (best)	99.34%	98.76%	98.78%	934ms	16.0s	29 tps	262K	$0.361 / $1.09
ModelRunmodelrun/fp4fp4	Healthy	100%◆ (best)	99.01%	99.69%◆ (best)	99.61%◆ (best)	160ms◆ (best)	5.75s	77 tps	262K	$0.750 / $1.00
SiliconFlowsiliconflow/fp8fp8	Healthy	100%◆ (best)	76.99%	94.70%	90.62%	3.26s	16.9s	36 tps	262K	$0.750 / $1.00
DeepInfradeepinfra/fp8fp8	Healthy	99.79%	98.78%	98.07%	97.57%	3.18s	16.3s	10 tps	262K	$0.200 / $0.400
Parasailparasail/fp8fp8	Healthy	99.60%	99.34%	99.04%	99.06%	2.52s	70.0s	16 tps	262K	$0.150 / $0.400
Novitanovita/bf16bf16	Down	99.51%	82.23%	82.98%	88.42%	3.18s	55.8s	13 tps	262K	$0.140 / $0.400
CoreWeavecoreweave/fp4fp4	Healthy	99.46%	99.24%	99.43%	98.41%	515ms	11.6s	38 tps	262K	$0.100 / $0.340
DeepInfradeepinfra/turbofp4	Healthy	98.93%	99.38%	97.74%	98.72%	692ms	8.00s	22 tps	262K	$0.090 / $0.340
Venicevenice/fp4fp4	Healthy	98.32%	99.49%	97.04%	98.07%	645ms	4.26s◆ (best)	21 tps	256K	$0.120 / $0.360
SambaNovasambanova	Healthy	97.76%	98.55%	97.98%	95.02%	1.97s	8.40s	94 tps◆ (best)	262K	$0.380 / $1.15
Chuteschutes/fp4fp4	Down	61.42%	93.83%	83.95%	86.55%	4.40s	46.0s	18 tps	131K	$0.120 / $0.370
Cerebrascerebras/fp16fp16	No data	—	—	—	72.37%	—	—	—	131K	$0.990 / $1.49
CoreWeavecoreweave/bf16bf16	No data	—	—	—	—	—	—	—	262K	$0.100 / $0.340
Crusoecrusoe	No data	—	—	—	94.84%	—	—	—	262K	$0.140 / $0.400
DeepInfradeepinfra/ultrafp8	No data	—	—	78.88%	82.89%	—	—	—	131K	$0.270 / $0.760
DekaLLMdekallm	No data	—	—	95.29%	95.29%	—	—	—	262K	$0.100 / $0.330
OpenInferenceopen-inference/bf16bf16	No data	—	—	—	—	—	—	—	262K	$0.070 / $0.350◆ (best)
Phalaphala	No data	—	—	—	—	—	—	—	262K	$0.150 / $0.460
Rekareka	No data	—	—	99.49%	98.23%	—	—	—	262K	$0.080 / $0.300
Togethertogether	No data	—	—	—	90.79%	—	—	—	262K	$0.390 / $0.970
Venicevenice/bf16bf16	No data	—	—	—	98.37%	—	—	—	256K	$0.120 / $0.360

Crusoe100%◆ (best)
Healthy24h 99.44%
7d
98.56%
30d
95.61%
p50
691ms
p99
8.65s
Throughput
14 tps
Context
262K
$/Mtok
$0.140 / $0.400
crusoe/bf16bf16
Friendli100%◆ (best)
Healthy24h 99.59%
7d
99.46%
30d
98.97%
p50
984ms
p99
10.00s
Throughput
62 tps
Context
262K
$/Mtok
$0.140 / $0.400
friendli
Io Net100%◆ (best)
Healthy24h 99.34%
7d
98.76%
30d
98.78%
p50
934ms
p99
16.0s
Throughput
29 tps
Context
262K
$/Mtok
$0.361 / $1.09
io-net
ModelRun100%◆ (best)
Healthy24h 99.01%
7d
99.69%◆ (best)
30d
99.61%◆ (best)
p50
160ms◆ (best)
p99
5.75s
Throughput
77 tps
Context
262K
$/Mtok
$0.750 / $1.00
modelrun/fp4fp4
SiliconFlow100%◆ (best)
Healthy24h 76.99%
7d
94.70%
30d
90.62%
p50
3.26s
p99
16.9s
Throughput
36 tps
Context
262K
$/Mtok
$0.750 / $1.00
siliconflow/fp8fp8
DeepInfra99.79%
Healthy24h 98.78%
7d
98.07%
30d
97.57%
p50
3.18s
p99
16.3s
Throughput
10 tps
Context
262K
$/Mtok
$0.200 / $0.400
deepinfra/fp8fp8
Parasail99.60%
Healthy24h 99.34%
7d
99.04%
30d
99.06%
p50
2.52s
p99
70.0s
Throughput
16 tps
Context
262K
$/Mtok
$0.150 / $0.400
parasail/fp8fp8
Novita99.51%
Down24h 82.23%
7d
82.98%
30d
88.42%
p50
3.18s
p99
55.8s
Throughput
13 tps
Context
262K
$/Mtok
$0.140 / $0.400
novita/bf16bf16
CoreWeave99.46%
Healthy24h 99.24%
7d
99.43%
30d
98.41%
p50
515ms
p99
11.6s
Throughput
38 tps
Context
262K
$/Mtok
$0.100 / $0.340
coreweave/fp4fp4
DeepInfra98.93%
Healthy24h 99.38%
7d
97.74%
30d
98.72%
p50
692ms
p99
8.00s
Throughput
22 tps
Context
262K
$/Mtok
$0.090 / $0.340
deepinfra/turbofp4
Venice98.32%
Healthy24h 99.49%
7d
97.04%
30d
98.07%
p50
645ms
p99
4.26s◆ (best)
Throughput
21 tps
Context
256K
$/Mtok
$0.120 / $0.360
venice/fp4fp4
SambaNova97.76%
Healthy24h 98.55%
7d
97.98%
30d
95.02%
p50
1.97s
p99
8.40s
Throughput
94 tps◆ (best)
Context
262K
$/Mtok
$0.380 / $1.15
sambanova
Chutes61.42%
Down24h 93.83%
7d
83.95%
30d
86.55%
p50
4.40s
p99
46.0s
Throughput
18 tps
Context
131K
$/Mtok
$0.120 / $0.370
chutes/fp4fp4
Cerebras—
No data24h —
7d
—
30d
72.37%
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
94.84%
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.140 / $0.400
crusoe
DeepInfra—
No data24h —
7d
78.88%
30d
82.89%
p50
—
p99
—
Throughput
—
Context
131K
$/Mtok
$0.270 / $0.760
deepinfra/ultrafp8
DekaLLM—
No data24h —
7d
95.29%
30d
95.29%
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.100 / $0.330
dekallm
OpenInference—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.070 / $0.350◆ (best)
open-inference/bf16bf16
Phala—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.150 / $0.460
phala
Reka—
No data24h —
7d
99.49%
30d
98.23%
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.080 / $0.300
reka
Together—
No data24h —
7d
—
30d
90.79%
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.390 / $0.970
together
Venice—
No data24h —
7d
—
30d
98.37%
p50
—
p99
—
Throughput
—
Context
256K
$/Mtok
$0.120 / $0.360
venice/bf16bf16

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.

Price vs latency

One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag

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.

Throughput

Median tokens per second.