Skip to content
ProviderBench home

Cheapest gpt-oss-120b Inference Providers

Ranks providers by estimated cost using a 1,000-input/500-output token ratio, shown per 1 million total tokens.

OpenInference currently ranks first at $0.07 / 1M tokens via open-inference/int8.

Provider options:
21
Ranked:
21
Metric:
Estimated cost / 1M tokens

Cheapest endpoint ranking

Rank providers by
Cheapest gpt-oss-120b Inference Providers
RankProvider / routeEstimated cost / 1M tokensSpeed measurementsEndpoint details
#1Provider / route
OpenInferenceopen-inference/int8
Estimated cost / 1M tokens$0.07 / 1M tokensSpeed measurements
500-token response
13.60 s
Response starts
0.44 s
Output speed
38.0 tok/s
Endpoint details
Input price
$0.03 / 1M tokens
Output price
$0.15 / 1M tokens
Uptime (30 min)
99.81%
Context
131.1K
#2Provider / route
Estimated cost / 1M tokens$0.073333 / 1M tokensSpeed measurements
500-token response
13.62 s
Response starts
0.46 s
Output speed
38.0 tok/s
Endpoint details
Input price
$0.04 / 1M tokens
Output price
$0.14 / 1M tokens
Uptime (30 min)
97.23%
Context
131.1K
#3Provider / route
DekaLLMdekallm/bf16
Estimated cost / 1M tokens$0.08 / 1M tokensSpeed measurements
500-token response
16.74 s
Response starts
1.11 s
Output speed
32.0 tok/s
Endpoint details
Input price
$0.03 / 1M tokens
Output price
$0.18 / 1M tokens
Uptime (30 min)
96.73%
Context
131.1K
#4Provider / route
DeepInfradeepinfra/bf16
Estimated cost / 1M tokens$0.081333 / 1M tokensSpeed measurements
500-token response
20.95 s
Response starts
8.13 s
Output speed
39.0 tok/s
Endpoint details
Input price
$0.037 / 1M tokens
Output price
$0.17 / 1M tokens
Uptime (30 min)
70.18%
Context
131.1K
#5Provider / route
NovitaAInovita/fp4
Estimated cost / 1M tokens$0.116667 / 1M tokensSpeed measurements
500-token response
11.78 s
Response starts
0.67 s
Output speed
45.0 tok/s
Endpoint details
Input price
$0.05 / 1M tokens
Output price
$0.25 / 1M tokens
Uptime (30 min)
80.20%
Context
131.1K
#6Provider / route
Mancermancer/fp4
Estimated cost / 1M tokens$0.155 / 1M tokensSpeed measurements
500-token response
15.08 s
Response starts
1.56 s
Output speed
37.0 tok/s
Endpoint details
Input price
$0.045 / 1M tokens
Output price
$0.375 / 1M tokens
Uptime (30 min)
88.11%
Context
131.1K
#7Provider / route
Google Vertexgoogle-vertex/global
Estimated cost / 1M tokens$0.18 / 1M tokensSpeed measurements
500-token response
3.81 s
Response starts
0.38 s
Output speed
146.0 tok/s
Endpoint details
Input price
$0.09 / 1M tokens
Output price
$0.36 / 1M tokens
Uptime (30 min)
97.58%
Context
131.1K
#8Provider / route
SiliconFlowsiliconflow/fp8
Estimated cost / 1M tokens$0.183333 / 1M tokensSpeed measurements
500-token response
22.14 s
Response starts
1.30 s
Output speed
24.0 tok/s
Endpoint details
Input price
$0.05 / 1M tokens
Output price
$0.45 / 1M tokens
Uptime (30 min)
100.00%
Context
131.1K
#9Provider / route
DigitalOceandigitalocean
Estimated cost / 1M tokens$0.21 / 1M tokensSpeed measurements
500-token response
24.25 s
Response starts
3.42 s
Output speed
24.0 tok/s
Endpoint details
Input price
$0.07 / 1M tokens
Output price
$0.49 / 1M tokens
Uptime (30 min)
98.54%
Context
128K
#10Provider / route
Basetenbaseten/fp4
Estimated cost / 1M tokens$0.233333 / 1M tokensSpeed measurements
500-token response
2.42 s
Response starts
0.24 s
Output speed
230.0 tok/s
Endpoint details
Input price
$0.1 / 1M tokens
Output price
$0.5 / 1M tokens
Uptime (30 min)
100.00%
Context
128.1K
#11Provider / route
Amazon Bedrockamazon-bedrock
Estimated cost / 1M tokens$0.3 / 1M tokensSpeed measurements
500-token response
5.32 s
Response starts
2.07 s
Output speed
154.0 tok/s
Endpoint details
Input price
$0.15 / 1M tokens
Output price
$0.6 / 1M tokens
Uptime (30 min)
100.00%
Context
131.1K
#12Provider / route
DeepInfradeepinfra/turbo
Estimated cost / 1M tokens$0.3 / 1M tokensSpeed measurements
500-token response
5.47 s
Response starts
0.62 s
Output speed
103.0 tok/s
Endpoint details
Input price
$0.15 / 1M tokens
Output price
$0.6 / 1M tokens
Uptime (30 min)
99.91%
Context
131.1K
#13Provider / route
Togethertogether
Estimated cost / 1M tokens$0.3 / 1M tokensSpeed measurements
500-token response
5.04 s
Response starts
0.23 s
Output speed
104.0 tok/s
Endpoint details
Input price
$0.15 / 1M tokens
Output price
$0.6 / 1M tokens
Uptime (30 min)
88.78%
Context
131.1K
#14Provider / route
Nebiusnebius/fp4
Estimated cost / 1M tokens$0.3 / 1M tokensSpeed measurements
500-token response
5.92 s
Response starts
0.54 s
Output speed
93.0 tok/s
Endpoint details
Input price
$0.15 / 1M tokens
Output price
$0.6 / 1M tokens
Uptime (30 min)
85.41%
Context
131.1K
#15Provider / route
Amazon Bedrockamazon-bedrock/eu-west-1
Estimated cost / 1M tokens$0.3 / 1M tokensSpeed measurements
500-token response
Insufficient recent data
Response starts
Insufficient recent data
Output speed
Insufficient recent data
Endpoint details
Input price
$0.15 / 1M tokens
Output price
$0.6 / 1M tokens
Uptime (30 min)
Insufficient recent data
Context
131.1K
#16Provider / route
Phalaphala
Estimated cost / 1M tokens$0.3 / 1M tokensSpeed measurements
500-token response
7.95 s
Response starts
0.91 s
Output speed
71.0 tok/s
Endpoint details
Input price
$0.15 / 1M tokens
Output price
$0.6 / 1M tokens
Uptime (30 min)
99.47%
Context
131.1K
#17Provider / route
Groqgroq
Estimated cost / 1M tokens$0.3 / 1M tokensSpeed measurements
500-token response
1.41 s
Response starts
0.14 s
Output speed
392.5 tok/s
Endpoint details
Input price
$0.15 / 1M tokens
Output price
$0.6 / 1M tokens
Uptime (30 min)
99.64%
Context
131.1K
#18Provider / route
Parasailparasail/fp4
Estimated cost / 1M tokens$0.316667 / 1M tokensSpeed measurements
500-token response
6.27 s
Response starts
0.39 s
Output speed
85.0 tok/s
Endpoint details
Input price
$0.1 / 1M tokens
Output price
$0.75 / 1M tokens
Uptime (30 min)
95.94%
Context
131.1K
#19Provider / route
MARAmara
Estimated cost / 1M tokens$0.35 / 1M tokensSpeed measurements
500-token response
4.09 s
Response starts
1.07 s
Output speed
166.0 tok/s
Endpoint details
Input price
$0.15 / 1M tokens
Output price
$0.75 / 1M tokens
Uptime (30 min)
91.76%
Context
131.1K
#20Provider / route
SambaNovasambanova
Estimated cost / 1M tokens$0.41 / 1M tokensSpeed measurements
500-token response
4.17 s
Response starts
0.32 s
Output speed
130.0 tok/s
Endpoint details
Input price
$0.14 / 1M tokens
Output price
$0.95 / 1M tokens
Uptime (30 min)
99.03%
Context
131.1K
#21Provider / route
Cerebrascerebras/fp16
Estimated cost / 1M tokens$0.483333 / 1M tokensSpeed measurements
500-token response
0.82 s
Response starts
0.23 s
Output speed
857.0 tok/s
Endpoint details
Input price
$0.35 / 1M tokens
Output price
$0.75 / 1M tokens
Uptime (30 min)
99.93%
Context
131.1K

Endpoint data fetched .

gpt-oss-120b endpoint guide

How to interpret the Cheapest gpt-oss-120b Inference Providers

21 of 21 gpt-oss-120b endpoints currently have the published data required for this ranking. OpenInference leads at $0.07 / 1M tokens via open-inference/int8. The table keeps unranked routes visible so missing measurements do not look like missing provider availability.

How estimated token cost is ranked

The cheapest ranking uses a 1,000-input/500-output-token ratio and reports the blended result per 1 million total tokens. Because providers can price input and output differently, a workload with a different token ratio may produce a different order.

Compare OpenInference with the next option

Weights & Biases currently ranks second at $0.073333 / 1M tokens. Compare that gap with input and output price, response-start time, output speed, 30-minute uptime, context length, and the exact route before deciding whether first place is meaningful for your workload.

Use the route, not only the provider name

gpt-oss-120b has 21 published provider options, and performance data is matched to each exact OpenRouter routing tag. Different quantization, context, regional deployment, or provider configuration can change price and behavior even when the underlying model name is identical.