•gpt-oss-120b•

Open weights model

•

Released August 2025

gpt-oss-120b (High) API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of gpt-oss-120b (High) for your use-case.

Lowest Time per Task

#1
CerebrasCerebras
1.0 min
#2
SambaNovaSambaNova
3.1 min
#3
GroqGroq
3.3 min
#4
CrusoeCrusoe
5.0 min
#5
Google VertexGoogle Vertex
5.0 min

Time per Intelligence Index task (minutes)

Total 15 providers

Lowest Cost per Task

#1
CoreWeaveCoreWeave
$0.0727
#2
DeepInfraDeepInfra
$0.0868
#3
NovitaNovita
$0.12
#4
CrusoeCrusoe
$0.12
#5
ParasailParasail
$0.17

Cost per Intelligence Index task

Total 15 providers

gpt-oss-120b (high) is available through 15 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.

  • For time per task, Cerebras (1.0 min), SambaNova (3.1 min), and Groq (3.3 min) finish an Intelligence Index task fastest.
  • For cost per task, CoreWeave ($0.0727), DeepInfra ($0.0868), and Novita ($0.12) are the cheapest per Intelligence Index task. Cost varies up to 10.5x across providers.
Inference time (minutes) per Intelligence Index task · Lower is better
Weighted average cost (USD) per Intelligence Index task · Lower is better

Endpoint Accuracy

Endpoint Accuracy Index: gpt-oss-120b (High)

v1.1 · Composite of BFCL v4-500, HLE-250 and AA-LCR-25 run against each provider endpoint · Percentage of the reference endpoint, with 95% confidence interval · Higher is better

Pricing

Cost per Intelligence Index Task: gpt-oss-120b (High)

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

Pricing: Cache Hit, Input, and Output: gpt-oss-120b (High)

Price (USD per M Tokens) · Lower is better

Output Speed vs. Cost per Task: gpt-oss-120b (High)

Output speed: output tokens divided by total request time, including time to first token · Weighted average cost (USD) per Intelligence Index task
Most attractive quadrant
Pareto line

Speed

Average of the single-request and multi-turn agentic workloads measured

Time per Intelligence Index Task: gpt-oss-120b (High)

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Lower is better

Latency

Average of the single-request and multi-turn agentic workloads measured

Time to First Answer Token: gpt-oss-120b (High)

Seconds until the first answer token after any reasoning · Average of the single-request and multi-turn agentic workloads measured · Lower is better

Reliability

Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured

Endpoint Error Rate: gpt-oss-120b (High)

Share of requests the endpoint failed with an error, a rate limit or a timeout · Across all the single-request and multi-turn agentic workloads measured · Lower is better

Caching

Cache Hit Rate: gpt-oss-120b (High)

Median across multi-turn agentic session runs in the last four weeks, updated Oct 26, 2026 · Higher is better

Cost per Task vs. Cache Hit Rate: gpt-oss-120b (High)

Weighted average cost (USD) per Intelligence Index task · Cache hit rate: median of the last four weeks, updated Oct 26, 2026
Most attractive quadrant
Pareto line

Key Comparison Metrics & API Features

Amazon Bedrock logoAmazon Bedrock
$0.35
11.1
104%
22.47
3.4%
131k
Open
Baseten logoBaseten
$0.24
5.6
100%
9.39
0.0%
128k
Open
Cerebras logoCerebras
$0.76
1.0
92%
2.47
0.0%
131k
Open
CoreWeave logoCoreWeave
$0.0727
9.5
100%
21.01
7.9%
131k
Open
Crusoe logoCrusoe
$0.12
5.0
100%
8.20
0.0%
131k
Open
DeepInfra logoDeepInfra
$0.0868
73.2
98%
83.85
23.8%
131k
Open
Google Vertex logoGoogle Vertex
$0.21
5.0
78%
9.18
0.0%
131k
Open
Groq logoGroq
$0.32
3.3
90%
5.75
4.2%
131k
Open
Microsoft Azure logoMicrosoft Azure
$0.35
5.2
97%
11.01
17.5%
131k
Open
Nebius (Base) logoNebius (Base)
$0.35
5.7
102%
7.51
8.2%
128k
Open
Novita logoNovita
$0.12
6.7
93%
9.07
0.9%
131k
Open
Parasail logoParasail
$0.17
8.1
97%
12.43
9.6%
131k
Open
SambaNova logoSambaNova
$0.49
3.1
99%
7.88
4.2%
131k
Open
Scaleway logoScaleway
$0.39
9.3
98%
15.04
0.0%
128k
Open
Together AI logoTogether AI
$0.35
18.4
81%
31.99
8.2%
131k
Open

Frequently Asked Questions

Common questions about gpt-oss-120b (High) providers