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%	99.25%	99.25%	488ms	2.28s	273 tps	131K	$0.150 / $0.600
Cerebrascerebras/fp16fp16	Healthy	100%	99.99%	99.99%	99.99%	187ms	1.64s	819 tps	131K	$0.350 / $0.750
Mancer 2mancer/fp8fp8	Healthy	100%	99.35%	99.75%	99.75%	656ms	4.27s	84 tps	131K	$0.085 / $0.500
Nebiusnebius/fp4fp4	Healthy	100%	99.52%	98.74%	98.74%	234ms	2.10s	234 tps	131K	$0.150 / $0.600
Parasailparasail/fp4fp4	Healthy	100%	99.66%	99.83%	99.83%	341ms	1.17s	123 tps	131K	$0.100 / $0.750
Phalaphala	Healthy	100%	97.32%	97.47%	97.47%	803ms	3.85s	67 tps	131K	$0.150 / $0.600
Groqgroq	Healthy	99.98%	99.95%	99.93%	99.93%	201ms	2.32s	376 tps	131K	$0.150 / $0.600
SiliconFlowsiliconflow/fp8fp8	Healthy	99.92%	86.36%	92.60%	92.60%	1.12s	11.8s	17 tps	131K	$0.050 / $0.450
DigitalOceandigitalocean	Healthy	99.91%	99.90%	99.90%	99.90%	943ms	3.92s	23 tps	128K	$0.055 / $0.385
AkashMLakashml/bf16bf16	Healthy	99.91%	99.24%	99.65%	99.65%	1.03s	10.7s	64 tps	131K	$0.037 / $0.490
Togethertogether	Healthy	99.66%	96.32%	97.39%	97.39%	401ms	5.16s	63 tps	131K	$0.150 / $0.600
DeepInfradeepinfra/turbobf16	Healthy	99.31%	99.72%	98.94%	98.94%	413ms	1.24s	125 tps	131K	$0.150 / $0.600
DeepInfradeepinfra/bf16bf16	Healthy	99.16%	97.44%	98.23%	98.23%	984ms	11.2s	33 tps	131K	$0.037 / $0.170
CoreWeavecoreweave/fp4fp4	Healthy	99.08%	94.92%	95.98%	95.98%	483ms	9.73s	29 tps	131K	$0.030 / $0.170
Maramara	Healthy	98.54%	97.85%	95.33%	95.33%	1.14s	12.4s	153 tps	131K	$0.150 / $0.750
Googlegoogle-vertex/global	Degraded	96.76%	89.91%	89.70%	89.70%	461ms	8.85s	94 tps	131K	$0.090 / $0.360
BaseTenbaseten/fp4fp4	Down	87.89%	99.53%	99.18%	99.18%	200ms	708ms	264 tps	128K	$0.100 / $0.500
SambaNovasambanova	Down	77.27%	88.63%	86.26%	86.26%	787ms	9.33s	377 tps	131K	$0.140 / $0.950
Amazon Bedrockamazon-bedrock/eu-west-1	No data	—	—	100%	100%	—	—	—	131K	$0.150 / $0.600
Novitanovita/fp4fp4	Degraded	—	91.05%	94.17%	94.17%	611ms	15.3s	72 tps	131K	$0.050 / $0.250

Amazon Bedrock100%
Healthy24h 99.08%
7d
99.25%
30d
99.25%
p50
488ms
p99
2.28s
Throughput
273 tps
Context
131K
$/Mtok
$0.150 / $0.600
amazon-bedrock
Cerebras100%
Healthy24h 99.99%
7d
99.99%
30d
99.99%
p50
187ms
p99
1.64s
Throughput
819 tps
Context
131K
$/Mtok
$0.350 / $0.750
cerebras/fp16fp16
Mancer 2100%
Healthy24h 99.35%
7d
99.75%
30d
99.75%
p50
656ms
p99
4.27s
Throughput
84 tps
Context
131K
$/Mtok
$0.085 / $0.500
mancer/fp8fp8
Nebius100%
Healthy24h 99.52%
7d
98.74%
30d
98.74%
p50
234ms
p99
2.10s
Throughput
234 tps
Context
131K
$/Mtok
$0.150 / $0.600
nebius/fp4fp4
Parasail100%
Healthy24h 99.66%
7d
99.83%
30d
99.83%
p50
341ms
p99
1.17s
Throughput
123 tps
Context
131K
$/Mtok
$0.100 / $0.750
parasail/fp4fp4
Phala100%
Healthy24h 97.32%
7d
97.47%
30d
97.47%
p50
803ms
p99
3.85s
Throughput
67 tps
Context
131K
$/Mtok
$0.150 / $0.600
phala
Groq99.98%
Healthy24h 99.95%
7d
99.93%
30d
99.93%
p50
201ms
p99
2.32s
Throughput
376 tps
Context
131K
$/Mtok
$0.150 / $0.600
groq
SiliconFlow99.92%
Healthy24h 86.36%
7d
92.60%
30d
92.60%
p50
1.12s
p99
11.8s
Throughput
17 tps
Context
131K
$/Mtok
$0.050 / $0.450
siliconflow/fp8fp8
DigitalOcean99.91%
Healthy24h 99.90%
7d
99.90%
30d
99.90%
p50
943ms
p99
3.92s
Throughput
23 tps
Context
128K
$/Mtok
$0.055 / $0.385
digitalocean
AkashML99.91%
Healthy24h 99.24%
7d
99.65%
30d
99.65%
p50
1.03s
p99
10.7s
Throughput
64 tps
Context
131K
$/Mtok
$0.037 / $0.490
akashml/bf16bf16
Together99.66%
Healthy24h 96.32%
7d
97.39%
30d
97.39%
p50
401ms
p99
5.16s
Throughput
63 tps
Context
131K
$/Mtok
$0.150 / $0.600
together
DeepInfra99.31%
Healthy24h 99.72%
7d
98.94%
30d
98.94%
p50
413ms
p99
1.24s
Throughput
125 tps
Context
131K
$/Mtok
$0.150 / $0.600
deepinfra/turbobf16
DeepInfra99.16%
Healthy24h 97.44%
7d
98.23%
30d
98.23%
p50
984ms
p99
11.2s
Throughput
33 tps
Context
131K
$/Mtok
$0.037 / $0.170
deepinfra/bf16bf16
CoreWeave99.08%
Healthy24h 94.92%
7d
95.98%
30d
95.98%
p50
483ms
p99
9.73s
Throughput
29 tps
Context
131K
$/Mtok
$0.030 / $0.170
coreweave/fp4fp4
Mara98.54%
Healthy24h 97.85%
7d
95.33%
30d
95.33%
p50
1.14s
p99
12.4s
Throughput
153 tps
Context
131K
$/Mtok
$0.150 / $0.750
mara
Google96.76%
Degraded24h 89.91%
7d
89.70%
30d
89.70%
p50
461ms
p99
8.85s
Throughput
94 tps
Context
131K
$/Mtok
$0.090 / $0.360
google-vertex/global
BaseTen87.89%
Down24h 99.53%
7d
99.18%
30d
99.18%
p50
200ms
p99
708ms
Throughput
264 tps
Context
128K
$/Mtok
$0.100 / $0.500
baseten/fp4fp4
SambaNova77.27%
Down24h 88.63%
7d
86.26%
30d
86.26%
p50
787ms
p99
9.33s
Throughput
377 tps
Context
131K
$/Mtok
$0.140 / $0.950
sambanova
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 91.05%
7d
94.17%
30d
94.17%
p50
611ms
p99
15.3s
Throughput
72 tps
Context
131K
$/Mtok
$0.050 / $0.250
novita/fp4fp4

Measured 1m 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.