Menu

logo
Artificial Analysis
HOME
logo

QwQ-32B: API Provider Benchmarking & Analysis

Analysis of API providers for QwQ 32B across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Hyperbolic, Groq, Together.ai, Fireworks, Deepinfra, Nebius, CentML, SambaNova, and Novita.
Owner:
Alibaba
License:
Open
Context window:
131k
Link:

Comparison Summary

Output Speed (tokens/s):QwQ-32B, SambaNova logo SambaNova (434 t/s) and  QwQ-32B, Groq logo Groq (404 t/s) are the fastest providers of QwQ-32B, followed by  QwQ-32B, Fireworks logo QwQ-32B, Fireworks,  QwQ-32B, Together.ai logo QwQ-32B, Together.ai &  QwQ-32B, CentML logo QwQ-32B, CentML.Latency (TTFT):QwQ-32B, Groq logo Groq (0.25s) and  QwQ-32B, CentML logo CentML (0.33s) have the lowest latency for QwQ-32B, followed by  QwQ-32B, SambaNova logo QwQ-32B, SambaNova,  QwQ-32B, Together.ai logo QwQ-32B, Together.ai &  QwQ-32B, Fireworks logo QwQ-32B, Fireworks.Blended Price ($/M tokens):QwQ-32B, Deepinfra logo Deepinfra ($0.14) and  QwQ-32B, Hyperbolic logo Hyperbolic ($0.20) are the most cost-effective providers for QwQ-32B, followed by  QwQ-32B Base, Nebius logo QwQ-32B Base, Nebius,  QwQ-32B, Groq logo QwQ-32B, Groq &  QwQ-32B, SambaNova logo QwQ-32B, SambaNova.Input Token Price:QwQ-32B, Deepinfra logo Deepinfra ($0.12) and  QwQ-32B Base, Nebius logo Nebius Base ($0.15) offer the lowest input token prices for QwQ-32B, followed by  QwQ-32B, Hyperbolic logo QwQ-32B, Hyperbolic,  QwQ-32B, Groq logo QwQ-32B, Groq &  QwQ-32B, SambaNova logo QwQ-32B, SambaNova.Output Token Price:QwQ-32B, Deepinfra logo Deepinfra ($0.18) and  QwQ-32B, Hyperbolic logo Hyperbolic ($0.20) offer the lowest output token prices for QwQ-32B, followed by  QwQ-32B, Groq logo QwQ-32B, Groq,  QwQ-32B Base, Nebius logo QwQ-32B Base, Nebius &  QwQ-32B, CentML logo QwQ-32B, CentML.

Highlights

Intelligence
Artificial Analysis Intelligence Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:

Summary Analysis

Output Speed vs. Price

Output Speed: Output Tokens per Second; Price: USD per 1M Tokens
Most attractive quadrant
Hyperbolic
Nebius Base
CentML
Fireworks
Deepinfra
Groq
SambaNova
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.
Notes: QwQ-32B, SambaNova: 16k context

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)
Hyperbolic
Nebius Base
CentML
Fireworks
Deepinfra
Groq
SambaNova
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.
Notes: QwQ-32B, SambaNova: 16k context

Context Window

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: Input and Output Prices

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.
Notes: QwQ-32B, SambaNova: 16k context

Speed

Measured by Output Speed (tokens per second)

Output Speed

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.
Notes: QwQ-32B, SambaNova: 16k context

Output Speed Variance

Output Tokens per Second; Results by percentile; Higher is better; 1,000 Input Tokens
Median, Other points represent 5th, 25th, 75th, 95th Percentiles 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
Picture of the author
Notes: QwQ-32B, SambaNova: 16k context

Output Speed by Input Token Count (Context Length)

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.
Notes: QwQ-32B, SambaNova: 16k context

Latency

Measured by Time (seconds) to First Token

Time to First Answer Token

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

Seconds to First Token Received; Lower is better; 1,000 Input Tokens
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.
Median: Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

Time to First Token Variance

Seconds to First Token Received; Results by percentile; Lower median is better; 1,000 Input Tokens
Median, Other points represent 5th, 25th, 75th, 95th Percentiles respectively
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.
Boxplot: Shows variance of measurements
Picture of the author

Latency by Input Token Count (Context Length)

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.
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.
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

End-to-End Response Time vs. Price

End-to-End Response Time: End-to-End Seconds to Output 500 Tokens; Price: USD per 1M Tokens
Most attractive quadrant
Hyperbolic
Nebius Base
CentML
Fireworks
Deepinfra
Groq
SambaNova
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

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
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)

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.
Notes: QwQ-32B, SambaNova: 16k context

API Features

Function (Tool) Calling & JSON Mode

ModelsFunction callingJSON Mode
Hyperbolic logoHyperbolic
Nebius Base logoNebius Base
CentML logoCentML
Fireworks logoFireworks
Deepinfra logoDeepinfra
Groq logoGroq
SambaNova logoSambaNova
Together.ai logoTogether.ai
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.

Summary Table of Key Comparison Metrics

Features
Model Intelligence
Price
Output tokens/s
Latency
End-to-End Response Time
Hyperbolic logo
Alibaba logo
QwQ-32B
131k
58
$0.20
46.4
1.05
65.49
53.67
Nebius Base logo
Alibaba logo
QwQ-32B Base
131k
58
$0.23
20.7
3.58
148.33
120.55
CentML logo
Alibaba logo
QwQ-32B
131k
58
$0.65
85.2
0.33
35.44
29.24
Fireworks logo
Alibaba logo
QwQ-32B
131k
58
$0.90
137.8
0.52
22.23
18.07
Deepinfra logo
Alibaba logo
QwQ-32B
131k
58
$0.14
34.8
0.57
86.40
71.48
Groq logo
Alibaba logo
QwQ-32B
131k
58
$0.32
403.6
0.25
7.66
6.17
SambaNova logo
Alibaba logo
QwQ-32B
16k
58
$0.63
433.7
0.40
7.29
5.74
Together.ai logo
Alibaba logo
QwQ-32B
131k
58
$1.20
89.0
0.51
34.11
27.98