gpt-oss-120b

openai/gpt-oss-120b

Compare with GPT Audio, GPT Audio Mini, GPT Chat Latest

Comparegpt-oss-120b

	State
Amazon Bedrockamazon-bedrock	Healthy	100%	99.08%	99.26%	99.26%	434ms	2.33s	241 tps	131K	$0.150 / $0.600
BaseTenbaseten/fp4fp4	Healthy	100%	99.60%	99.15%	99.15%	222ms	683ms	286 tps	128K	$0.100 / $0.500
Cerebrascerebras/fp16fp16	Healthy	100%	99.99%	99.99%	99.99%	172ms	1.61s	915 tps	131K	$0.350 / $0.750
DigitalOceandigitalocean	Healthy	100%	99.90%	99.90%	99.90%	839ms	4.72s	25 tps	128K	$0.055 / $0.385
Nebiusnebius/fp4fp4	Healthy	100%	99.52%	98.71%	98.71%	205ms	1.86s	302 tps	131K	$0.150 / $0.600
Parasailparasail/fp4fp4	Healthy	100%	99.65%	99.82%	99.82%	288ms	941ms	124 tps	131K	$0.100 / $0.750
Phalaphala	Healthy	100%	97.30%	97.37%	97.37%	907ms	5.22s	115 tps	131K	$0.150 / $0.600
Togethertogether	Healthy	100%	96.31%	97.40%	97.40%	407ms	2.55s	123 tps	131K	$0.150 / $0.600
Groqgroq	Healthy	99.96%	99.95%	99.93%	99.93%	223ms	2.24s	358 tps	131K	$0.150 / $0.600
DeepInfradeepinfra/bf16bf16	Healthy	99.90%	97.44%	98.24%	98.24%	2.05s	11.6s	28 tps	131K	$0.037 / $0.170
DeepInfradeepinfra/turbobf16	Healthy	99.61%	99.74%	98.92%	98.92%	422ms	1.32s	134 tps	131K	$0.150 / $0.600
Mancer 2mancer/fp8fp8	Healthy	99.48%	99.46%	99.79%	99.79%	658ms	5.13s	84 tps	131K	$0.085 / $0.500
CoreWeavecoreweave/fp4fp4	Healthy	99.20%	94.84%	95.85%	95.85%	394ms	10.1s	33 tps	131K	$0.030 / $0.170
Maramara	Healthy	97.66%	97.72%	95.27%	95.27%	1.37s	12.1s	167 tps	131K	$0.150 / $0.750
AkashMLakashml/bf16bf16	Healthy	96.42%	99.47%	99.73%	99.73%	1.29s	11.3s	66 tps	131K	$0.037 / $0.490
SiliconFlowsiliconflow/fp8fp8	Down	88.95%	85.81%	92.40%	92.40%	1.40s	16.5s	12 tps	131K	$0.050 / $0.450
SambaNovasambanova	Down	82.56%	88.22%	86.04%	86.04%	920ms	8.43s	239 tps	131K	$0.140 / $0.950
Googlegoogle-vertex/global	Down	81.87%	90.02%	89.94%	89.94%	440ms	8.96s	111 tps	131K	$0.090 / $0.360
Amazon Bedrockamazon-bedrock/eu-west-1	No data	—	—	100%	100%	—	—	—	131K	$0.150 / $0.600
Novitanovita/fp4fp4	Degraded	—	92.25%	94.56%	94.56%	614ms	36.7s	42 tps	131K	$0.050 / $0.250

Amazon Bedrock100%
Healthy24h 99.08%
7d
99.26%
30d
99.26%
p50
434ms
p99
2.33s
Throughput
241 tps
Context
131K
$/Mtok
$0.150 / $0.600
amazon-bedrock
BaseTen100%
Healthy24h 99.60%
7d
99.15%
30d
99.15%
p50
222ms
p99
683ms
Throughput
286 tps
Context
128K
$/Mtok
$0.100 / $0.500
baseten/fp4fp4
Cerebras100%
Healthy24h 99.99%
7d
99.99%
30d
99.99%
p50
172ms
p99
1.61s
Throughput
915 tps
Context
131K
$/Mtok
$0.350 / $0.750
cerebras/fp16fp16
DigitalOcean100%
Healthy24h 99.90%
7d
99.90%
30d
99.90%
p50
839ms
p99
4.72s
Throughput
25 tps
Context
128K
$/Mtok
$0.055 / $0.385
digitalocean
Nebius100%
Healthy24h 99.52%
7d
98.71%
30d
98.71%
p50
205ms
p99
1.86s
Throughput
302 tps
Context
131K
$/Mtok
$0.150 / $0.600
nebius/fp4fp4
Parasail100%
Healthy24h 99.65%
7d
99.82%
30d
99.82%
p50
288ms
p99
941ms
Throughput
124 tps
Context
131K
$/Mtok
$0.100 / $0.750
parasail/fp4fp4
Phala100%
Healthy24h 97.30%
7d
97.37%
30d
97.37%
p50
907ms
p99
5.22s
Throughput
115 tps
Context
131K
$/Mtok
$0.150 / $0.600
phala
Together100%
Healthy24h 96.31%
7d
97.40%
30d
97.40%
p50
407ms
p99
2.55s
Throughput
123 tps
Context
131K
$/Mtok
$0.150 / $0.600
together
Groq99.96%
Healthy24h 99.95%
7d
99.93%
30d
99.93%
p50
223ms
p99
2.24s
Throughput
358 tps
Context
131K
$/Mtok
$0.150 / $0.600
groq
DeepInfra99.90%
Healthy24h 97.44%
7d
98.24%
30d
98.24%
p50
2.05s
p99
11.6s
Throughput
28 tps
Context
131K
$/Mtok
$0.037 / $0.170
deepinfra/bf16bf16
DeepInfra99.61%
Healthy24h 99.74%
7d
98.92%
30d
98.92%
p50
422ms
p99
1.32s
Throughput
134 tps
Context
131K
$/Mtok
$0.150 / $0.600
deepinfra/turbobf16
Mancer 299.48%
Healthy24h 99.46%
7d
99.79%
30d
99.79%
p50
658ms
p99
5.13s
Throughput
84 tps
Context
131K
$/Mtok
$0.085 / $0.500
mancer/fp8fp8
CoreWeave99.20%
Healthy24h 94.84%
7d
95.85%
30d
95.85%
p50
394ms
p99
10.1s
Throughput
33 tps
Context
131K
$/Mtok
$0.030 / $0.170
coreweave/fp4fp4
Mara97.66%
Healthy24h 97.72%
7d
95.27%
30d
95.27%
p50
1.37s
p99
12.1s
Throughput
167 tps
Context
131K
$/Mtok
$0.150 / $0.750
mara
AkashML96.42%
Healthy24h 99.47%
7d
99.73%
30d
99.73%
p50
1.29s
p99
11.3s
Throughput
66 tps
Context
131K
$/Mtok
$0.037 / $0.490
akashml/bf16bf16
SiliconFlow88.95%
Down24h 85.81%
7d
92.40%
30d
92.40%
p50
1.40s
p99
16.5s
Throughput
12 tps
Context
131K
$/Mtok
$0.050 / $0.450
siliconflow/fp8fp8
SambaNova82.56%
Down24h 88.22%
7d
86.04%
30d
86.04%
p50
920ms
p99
8.43s
Throughput
239 tps
Context
131K
$/Mtok
$0.140 / $0.950
sambanova
Google81.87%
Down24h 90.02%
7d
89.94%
30d
89.94%
p50
440ms
p99
8.96s
Throughput
111 tps
Context
131K
$/Mtok
$0.090 / $0.360
google-vertex/global
Amazon Bedrock—
No data24h —
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
131K
$/Mtok
$0.150 / $0.600
amazon-bedrock/eu-west-1
Novita—
Degraded24h 92.25%
7d
94.56%
30d
94.56%
p50
614ms
p99
36.7s
Throughput
42 tps
Context
131K
$/Mtok
$0.050 / $0.250
novita/fp4fp4

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

Price changes

gpt-oss-120b Mancer 2mancer/fp8$0.080 / $0.500 → $0.085 / $0.5002026-08-20 23:41 UTC
gpt-oss-120b Mancer 2mancer/fp8$0.083 / $0.500 → $0.080 / $0.5002026-08-20 22:26 UTC
gpt-oss-120b Mancer 2mancer/fp8$0.085 / $0.500 → $0.083 / $0.5002026-08-20 21:56 UTC
gpt-oss-120b Mancer 2mancer/fp8$0.080 / $0.500 → $0.085 / $0.5002026-08-20 21:21 UTC
gpt-oss-120b Mancer 2mancer/fp8$0.085 / $0.500 → $0.080 / $0.5002026-08-19 19:25 UTC

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 is OpenRouter's rolling 30-minute window.

Throughput

Median tokens per second.