gpt-oss-120B (high): API Provider Benchmarking & Analysis

Analysis of API providers for gpt-oss-120B across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Microsoft Azure, Amazon Bedrock, Groq, Together.ai, Google, Fireworks, Cerebras, Deepinfra, Nebius, Parasail, GMI, CompactifAI, vLLM, Cloudflare, and Novita.

Owner:

OpenAI

License:

Open

Context window:

131k

Link:

Visit

Comparison Summary

Output Speed (tokens/s):

gpt-oss-120B (high): API Provider Performance Benchmarking & Price Analysis | Artificial Analysis

Intelligence

Artificial Analysis Intelligence Index; Higher is better

Speed

Output Tokens per Second; Higher is better

Price

USD per 1M Tokens; Lower is better

Navigation

Summary Analysis Pricing Speed Latency End-to-End Response Time

Endpoint Evaluations

Back to Navigation

GPQAx16 Performance: gpt-oss-120B

GPQA Diamond N=16 Runs: Minimum, 25th Percentile, Median, 75th Percentile, Maximum (Higher is Better)

Median; other points represent Min, 25th, 75th percentiles and Max respectively

GPQAx16: Results on the GPQA Diamond benchmark, which tests scientific knowledge and reasoning. Each provider endpoint is evaluated in 16 independent runs.

Boxplot points: Min (whisker bottom), 25th percentile (box lower edge), Median (line in box), 75th percentile (box upper edge), Max (whisker top).

Notes: gpt-oss-120B (high), Parasail: 131k context, gpt-oss-120B (high) Base, Nebius: 128k context, gpt-oss-120B (high), Fireworks: 131k context, gpt-oss-120B (high), Deepinfra: 131k context, gpt-oss-120B (high), Novita: 131k context, gpt-oss-120B (high), GMI: 131k context, gpt-oss-120B (high), Groq: 131k context, gpt-oss-120B (high), Together.ai: 131k context, gpt-oss-120B (high), Cloudflare: 128k context

AIME25x32 Performance: gpt-oss-120B

AIME 2025 N=32 Runs: Minimum, 25th Percentile, Median, 75th Percentile, Maximum (Higher is Better)

Median; other points represent Min, 25th, 75th percentiles and Max respectively

AIME25x32: Results on the AIME 2025 benchmark, which tests advanced mathematical problem-solving capabilities. Each provider endpoint is evaluated in 32 independent runs.

Boxplot points: Min (whisker bottom), 25th percentile (box lower edge), Median (line in box), 75th percentile (box upper edge), Max (whisker top).

Summary Table of Key Comparison Metrics

Back to Navigation

	Features	Model Intelligence	Price	Output tokens/s	Latency	End-to-End Response Time

gpt-oss-120B (high)	131k	61	$0.26	172.1	0.45	14.98	11.62
gpt-oss-120B (high)	131k	61	$0.36	3,111.2	0.27	1.08	0.64
gpt-oss-120B (high)	131k	61	$0.26	224.3	0.37	11.52	8.92
gpt-oss-120B (high) Base	128k	61	$0.26	193.2	0.52	13.46	10.35
gpt-oss-120B (high) Vertex	131k	61	$0.26	230.8	0.18	11.01	8.67
gpt-oss-120B (high)	131k	61	$0.10	193.1	0.25	13.20	10.36
gpt-oss-120B (high)	131k	61	$0.26	271.8	43.43	52.63	7.36
gpt-oss-120B (high)	131k	61	$0.26	301.6	0.45	8.74	6.63
gpt-oss-120B (high)	131k	61	$0.18	225.3	0.20	11.30	8.88
gpt-oss-120B (high)	131k	61	$0.20	208.9	0.76	12.73	9.58
gpt-oss-120B (high)	131k	61	$0.26	236.9	30.64	41.19	8.44
gpt-oss-120B (high)	131k	61	$0.30	499.3	0.19	5.20	4.01
gpt-oss-120B (high)	131k	61	$0.26	334.4	35.26	42.73	5.98
gpt-oss-120B (high)	128k	61	$0.45	126.3	124.49	144.28	15.84

	Features	Model Intelligence	Price	Output tokens/s	Latency	End-to-End Response Time
gpt-oss-120B (high)	131k	61	$0.26	172.1	0.45	14.98	11.62
gpt-oss-120B (high)	131k	61	$0.36	3,111.2	0.27	1.08	0.64
gpt-oss-120B (high)	131k	61	$0.26	224.3	0.37	11.52	8.92
gpt-oss-120B (high) Base	128k	61	$0.26	193.2	0.52	13.46	10.35
gpt-oss-120B (high) Vertex	131k	61	$0.26	230.8	0.18	11.01	8.67
gpt-oss-120B (high)	131k	61	$0.10	193.1	0.25	13.20	10.36
gpt-oss-120B (high)	131k	61	$0.26	271.8	43.43	52.63	7.36
gpt-oss-120B (high)	131k	61	$0.26	301.6	0.45	8.74	6.63
gpt-oss-120B (high)	131k	61	$0.18	225.3	0.20	11.30	8.88
gpt-oss-120B (high)	131k	61	$0.20	208.9	0.76	12.73	9.58
gpt-oss-120B (high)	131k	61	$0.26	236.9	30.64	41.19	8.44
gpt-oss-120B (high)	131k	61	$0.30	499.3	0.19	5.20	4.01
gpt-oss-120B (high)	131k	61	$0.26	334.4	35.26	42.73	5.98
gpt-oss-120B (high)	128k	61	$0.45	126.3	124.49	144.28	15.84

Summary Analysis

Back to Navigation

Output Speed vs. Price: gpt-oss-120B (high) Providers

Output Speed: Output Tokens per Second; Price: USD per 1M Tokens

Most attractive quadrant

Amazon

Azure

Cerebras

Cloudflare

CompactifAI

Deepinfra

Fireworks

GMI

Google Vertex

Groq

Nebius Base

Novita

Parasail

Together.ai

Output Speed: Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Price: Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).

Median: Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

Latency vs. Output Speed: gpt-oss-120B (high) Providers

Latency: Seconds to First Token Received; Output Speed: Output Tokens per Second; 1,000 Input Tokens

Most attractive quadrant

Size represents Price (USD per M Tokens)

Amazon

Azure

Cerebras

Cloudflare

CompactifAI

Deepinfra

Fireworks

GMI

Google Vertex

Groq

Nebius Base

Novita

Parasail

Together.ai

Output Speed: Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Latency (Time to First Token): Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Price: Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).

Median: Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

Context Window: gpt-oss-120B (high) Providers

Context Window: Tokens Limit; Higher is better

Context window: Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Variance between providers: While models have their own context window, in cases this is limited by providers.

Pricing

Back to Navigation

Pricing: Input and Output Prices: gpt-oss-120B (high) Providers

USD per 1M Tokens; Lower is better

Input price

Output price

Input Price: Price per token included in the request/message sent to the API, represented as USD per million Tokens.

Output Price: Price per token generated by the model (received from the API), represented as USD per million Tokens.

Speed

Measured by Output Speed (tokens per second)

Back to Navigation

Output Speed: gpt-oss-120B (high) Providers

Output Tokens per Second; Higher is better

Output Speed: Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Median: Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

Output Speed Variance: gpt-oss-120B (high) Providers

Output Tokens per Second; Results by percentile; Higher is better; 1,000 Input Tokens

Median; other points represent Min, 25th, 75th percentiles and Max respectively

Output Speed: Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Boxplot: Shows variance of measurements

Output Speed by Input Token Count (Context Length): gpt-oss-120B (high) Providers

Output Tokens per Second; Higher is better

100 input tokens

1k input tokens

10k input tokens

100k input tokens

Input Tokens Length: Length of tokens provided in the request. See Prompt Options above to see benchmarks of different input prompt lengths across other charts.

Output Speed: Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Median: Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

Latency

Measured by Time (seconds) to First Token

Back to Navigation

Time to First Answer Token

Seconds to First Token Received; Lower is better

'Thinking' time (reasoning models, where applicable)

Input processing time

Time To First Answer Token: Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

Median: Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

Time to First Token: gpt-oss-120B (high) Providers

Seconds to First Token Received; Lower is better; 1,000 Input Tokens

Median: Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

Time to First Token Variance: gpt-oss-120B (high) Providers

Seconds to First Token Received; Results by percentile; Lower median is better; 1,000 Input Tokens

Median; other points represent Min, 25th, 75th percentiles and Max respectively

Boxplot: Shows variance of measurements

Latency by Input Token Count (Context Length): gpt-oss-120B (high) Providers

Seconds to First Token Received; Lower is better

100 input tokens

1k input tokens

10k input tokens

100k input tokens

Input Tokens Length: Length of tokens provided in the request. See Prompt Options above to see benchmarks of different input prompt lengths across other charts.

Median: Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

End-to-End Response Time

Seconds to output 500 Tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

Back to Navigation

End-to-End Response Time vs. Price: gpt-oss-120B (high) Providers

End-to-End Response Time: End-to-End Seconds to Output 500 Tokens; Price: USD per 1M Tokens

Most attractive quadrant

Amazon

Azure

Cerebras

Cloudflare

CompactifAI

Deepinfra

Fireworks

GMI

Google Vertex

Groq

Nebius Base

Novita

Parasail

Together.ai

Price: Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).

End-to-End Response Time: Seconds to receive a 500 token response considering input processing time, 'thinking' time of reasoning models, and output speed.

Median: Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

End-to-End Response Time: gpt-oss-120B (high) Providers

Seconds to Output 500 Tokens, including reasoning model 'thinking' time; Lower is better; 1,000 Input Tokens

'Thinking' time (reasoning models)

Input processing time

Outputting time

End-to-End Response Time: Seconds to receive a 500 token response. Key components:

Input time: Time to receive the first response token
Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
Answer time: Time to generate 500 output tokens, based on output speed

Standardized Reasoning Tokens: For fair comparison, the number of reasoning tokens is standardized across all providers for each model based on the model's representative query token counts.

Median: Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

End-to-End Response Time by Input Token Count (Context Length): gpt-oss-120B (high) Providers

Seconds to Output 500 Tokens, including reasoning model 'thinking' time; Lower is better

100 input tokens

1k input tokens

10k input tokens

100k input tokens

Input Tokens Length: Length of tokens provided in the request. See Prompt Options above to see benchmarks of different input prompt lengths across other charts.

End-to-End Response Time: Seconds to receive a 500 token response considering input processing time, 'thinking' time of reasoning models, and output speed.

Median: Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

API Features

Back to Navigation

Function (Tool) Calling & JSON Mode: gpt-oss-120B (high) Providers

Models	Function calling	JSON Mode
Parasail
Cerebras
Amazon
Nebius Base
Google Vertex
CompactifAI
Azure
Fireworks
Deepinfra
Novita
GMI
Groq
Together.ai
Cloudflare

Function (Tool) Calling: Indicates whether the provider supports function calling in their API. Function calling is also known as 'Tool Calling'.

JSON Mode: Indicates whether the provider supports JSON mode in their API. When JSON mode is enabled, the models will always return a valid JSON object.

gpt-oss-120B (high): API Provider Benchmarking & Analysis

gpt-oss-120B (high): API Provider Benchmarking & Analysis

Highlights

Navigation

Endpoint Evaluations

GPQAx16 Performance: gpt-oss-120B

AIME25x32 Performance: gpt-oss-120B

Summary Table of Key Comparison Metrics

Summary Analysis

Output Speed vs. Price: gpt-oss-120B (high) Providers

Latency vs. Output Speed: gpt-oss-120B (high) Providers

Context Window: gpt-oss-120B (high) Providers

Pricing

Pricing: Input and Output Prices: gpt-oss-120B (high) Providers

Speed

Output Speed: gpt-oss-120B (high) Providers

Output Speed Variance: gpt-oss-120B (high) Providers

Output Speed by Input Token Count (Context Length): gpt-oss-120B (high) Providers

Latency

Time to First Answer Token

Time to First Token: gpt-oss-120B (high) Providers

Time to First Token Variance: gpt-oss-120B (high) Providers

Latency by Input Token Count (Context Length): gpt-oss-120B (high) Providers

End-to-End Response Time

End-to-End Response Time vs. Price: gpt-oss-120B (high) Providers

End-to-End Response Time: gpt-oss-120B (high) Providers

End-to-End Response Time by Input Token Count (Context Length): gpt-oss-120B (high) Providers

API Features

Function (Tool) Calling & JSON Mode: gpt-oss-120B (high) Providers

IFBenchx8 Performance: gpt-oss-120B