Stay connected with us on X, Discord, and LinkedIn to stay up to date with future analysis
Log in
gpt-oss-120B (high) logo

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

OpenAI

Open weights model

Released August 2025

Analysis of API providers for gpt-oss-120B (high) across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Cerebras, Parasail, Databricks, Cloudflare, Microsoft Azure, Baseten, SambaNova, Hyperbolic, Amazon Bedrock, Together.ai, Lightning AI, DeepInfra (Turbo), Google Vertex, Snowflake, Groq, Clarifai, DeepInfra, Weights & Biases, Novita, Fireworks, Scaleway, Nebius Base, Eigen AI.

Fastest

#1
CerebrasCerebras
2,288.4 t/s
#2
Eigen AIEigen AI
1,099.3 t/s
#3
FireworksFireworks
800.9 t/s
#4
SambaNovaSambaNova
773.3 t/s
#5
HyperbolicHyperbolic
738.7 t/s

Output speed

Total 23 providers

Lowest Latency

#1
BasetenBaseten
0.13 s
#2
GroqGroq
0.19 s
#3
CerebrasCerebras
0.23 s
#4
ClarifaiClarifai
0.24 s
#5
Google VertexGoogle Vertex
0.27 s

Time to first token

Total 23 providers

Lowest Price

#1
DeepInfraDeepInfra
$0.08
#2
NovitaNovita
$0.10
#3
Google VertexGoogle Vertex
$0.16
#4
ClarifaiClarifai
$0.16
#5
Lightning AILightning AI
$0.17

Blended price (per 1M tokens)

Total 23 providers

gpt-oss-120B (high) is available through 23 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.

  • For output speed, the top providers are Cerebras (2,288.4 t/s), Eigen AI (1,099.3 t/s), Fireworks (800.9 t/s). Speed varies significantly across providers, with a 210% difference between the fastest and slowest.
  • For latency, Baseten (0.13s), Groq (0.19s), Cerebras (0.23s) offer the lowest time to first token.
  • For pricing, DeepInfra (0.08), Novita (0.10), Google Vertex (0.16) offer the lowest blended prices per 1M tokens. Prices vary up to 2.3x across providers.
Speed
Output Tokens per Second; Higher is better
End-to-End Response Time
Seconds; Lower is better
Price
USD per 1M Tokens; Lower is better

Navigation

PricingSpeedLatencyEnd-to-End Response TimeAPI FeaturesSummary Table of Key Comparison MetricsEndpoint Evaluations
Parallel Queries:
Prompt Length:

Update: Default performance benchmarking workload has updated to 10k input tokens to better reflect production use cases. You can still select different workloads above!

Pricing

Pricing: Input and Output Prices

USD per 1M Tokens; Lower is better
Input price
Output price

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

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

Speed vs. Price

Output Speed: Output Tokens per Second; Price: USD per 1M Tokens
Most attractive quadrant
Amazon
Azure
Baseten
Cerebras
Clarifai
Cloudflare
Databricks
DeepInfra
DeepInfra (Turbo)
Eigen AI
Fireworks
Google Vertex
Groq
Hyperbolic
Lightning AI
Nebius Base
Novita
Parasail
SambaNova
Scaleway
Snowflake
Together.ai
Weights & Biases

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

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

Speed

Measured by Output Speed (tokens per second)

Output Speed

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

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).

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

Latency vs. Output Speed

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
Baseten
Cerebras
Clarifai
Cloudflare
Databricks
DeepInfra
DeepInfra (Turbo)
Eigen AI
Fireworks
Google Vertex
Groq
Hyperbolic
Lightning AI
Nebius Base
Novita
Parasail
SambaNova
Scaleway
Snowflake
Together.ai
Weights & Biases

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).

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

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

Latency

Measured by Time (seconds) to First Token

Time to First Answer Token

Seconds to First Token Received; Lower is better; 1,000 Input Tokens
Input processing time
'Thinking' time (reasoning models, where applicable)

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.

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

End-to-End Response Time

Seconds to Output 500 Tokens, including reasoning model 'thinking' time; Lower is better; 1,000 Input Tokens
Input processing time
'Thinking' time (reasoning models)
Outputting 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

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.

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

API Features

Function (Tool) Calling & JSON Mode

ModelsFunction callingJSON Mode
Cerebras logoCerebras
Parasail logoParasail
Databricks logoDatabricks
Cloudflare logoCloudflare
Azure logoAzure
Baseten logoBaseten
SambaNova logoSambaNova
Hyperbolic logoHyperbolic
Amazon logoAmazon
Together.ai logoTogether.ai
Lightning AI logoLightning AI
DeepInfra (Turbo) logoDeepInfra (Turbo)
Google Vertex logoGoogle Vertex
Snowflake logoSnowflake
Groq logoGroq
Clarifai logoClarifai
DeepInfra logoDeepInfra
Weights & Biases logoWeights & Biases
Novita logoNovita
Fireworks logoFireworks
Scaleway logoScaleway
Nebius Base logoNebius Base
Eigen AI logoEigen AI

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

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

Context Window

Context Window: Tokens Limit; Higher is better

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

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

Endpoint Evaluations

GPQAx16 Performance: gpt-oss-120B (high)

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
Reasoning models are indicated by a lightbulb icon.

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

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

AIME25x32 Performance: gpt-oss-120B (high)

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
Reasoning models are indicated by a lightbulb icon.

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

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

IFBenchx8 Performance: gpt-oss-120B (high)

IFBench N=8 Runs: Minimum, 25th Percentile, Median, 75th Percentile, Maximum (Higher is Better)
Median; other points represent Min, 25th, 75th percentiles and Max respectively
Reasoning models are indicated by a lightbulb icon.

Results on the IFBench benchmark, which evaluates instruction-following capabilities. Each provider endpoint is evaluated in 8 independent runs.

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

Frequently Asked Questions

Common questions about gpt-oss-120B (high) providers

gpt-oss-120B (high) is available through 23 API providers: Cerebras, Parasail, Databricks, Cloudflare, Azure, Baseten, SambaNova, Hyperbolic, Amazon, Together.ai, Lightning AI, DeepInfra (Turbo), Google Vertex, Snowflake, Groq, Clarifai, DeepInfra, Weights & Biases, Novita, Fireworks, Scaleway, Nebius Base, and Eigen AI. Each provider offers different performance characteristics and pricing.

gpt-oss-120B (high) is currently available through 23 API providers that we benchmark and track.

The fastest providers for gpt-oss-120B (high) by output speed are Cerebras (2,288.4 t/s), Eigen AI (1,099.3 t/s), and Fireworks (800.9 t/s). Output speed measures how quickly tokens are generated after the model starts responding.

The providers with the lowest time to first token for gpt-oss-120B (high) are Baseten (0.13s), Groq (0.19s), and Cerebras (0.23s). Lower latency means faster initial response time.

The most affordable providers for gpt-oss-120B (high) by blended price are DeepInfra ($0.08 per 1M tokens), Novita ($0.10 per 1M tokens), and Google Vertex ($0.16 per 1M tokens). Blended price uses a 3:1 input to output token ratio.

The providers with the lowest input token pricing for gpt-oss-120B (high) are DeepInfra ($0.04 per 1M input tokens), Novita ($0.05 per 1M input tokens), and Google Vertex ($0.09 per 1M input tokens).

The providers with the lowest output token pricing for gpt-oss-120B (high) are DeepInfra ($0.19 per 1M output tokens), Snowflake ($0.22 per 1M output tokens), and Novita ($0.25 per 1M output tokens).

Prices for gpt-oss-120B (high) vary up to 5.9x across providers. The most affordable is DeepInfra at $0.08 per 1M tokens, while Cerebras charges $0.45 per 1M tokens.

Output speed for gpt-oss-120B (high) varies significantly across providers. Cerebras is the fastest at 2,288.4 t/s, which is 34.5x faster than Novita at 66.4 t/s.

17 of 23 providers support JSON mode for gpt-oss-120B (high): Parasail, Azure, SambaNova, Hyperbolic, Amazon, Together.ai, Lightning AI, Google Vertex, Snowflake, Groq, Clarifai, DeepInfra, Weights & Biases, Novita, Scaleway, Nebius Base, and Eigen AI.

16 of 23 providers support function calling for gpt-oss-120B (high): Cerebras, Databricks, Azure, Baseten, SambaNova, Hyperbolic, Amazon, Together.ai, Lightning AI, Google Vertex, Groq, Clarifai, DeepInfra, Novita, Fireworks, and Eigen AI.

The best provider for gpt-oss-120B (high) depends on your priorities: Cerebras offers the highest output speed, Baseten has the lowest latency, and DeepInfra provides the most competitive pricing.

When choosing a provider for gpt-oss-120B (high), consider: output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.

Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.

For information about gpt-oss-120B (high)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview