This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.

Alibaba has launched a newer release, Qwen3 30B A3B 2507 (Reasoning). We suggest considering it instead.

•
Qwen3 14B
•

Open weights model

•

Released April 2025

Qwen3 14B (Non-reasoning) API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of Qwen3 14B (Non-reasoning) for your use-case.

Fastest

#1
Alibaba CloudAlibaba Cloud
63.6 t/s
#2
DeepInfra (FP8)DeepInfra (FP8)
24.8 t/s

Output speed

Total 2 providers

Lowest Latency

#1
DeepInfra (FP8)DeepInfra (FP8)
1.99 s
#2
Alibaba CloudAlibaba Cloud
2.65 s

Time to first token

Total 2 providers

Lowest Price

#1
DeepInfra (FP8)DeepInfra (FP8)
$0.13
#2
Alibaba CloudAlibaba Cloud
$0.45

Blended price (per 1M tokens)

Total 2 providers

Qwen3 14B (non-reasoning) is available through 2 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 Alibaba Cloud (63.6 t/s) and DeepInfra (FP8) (24.8 t/s).
  • For latency, DeepInfra (FP8) (1.99s) and Alibaba Cloud (2.65s) offer the lowest time to first token.
  • For pricing, DeepInfra (FP8) (0.13) and Alibaba Cloud (0.45) offer the lowest blended prices per 1M tokens.
  • DeepInfra (FP8) offers both the lowest latency and best pricing, making it attractive for cost-conscious applications. Alibaba Cloud is the fastest option for throughput-intensive workloads.
Output tokens per second · Higher is better
Seconds to first answer token received · Lower is better
USD per 1M tokens (blended) · Lower is better

Pricing

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens) · Lower is better · 10,000 input tokens

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type · Lower is better
No data available

Output Speed vs. Price

Blended at 7:2:1 (cache-input-output) · Output speed: output tokens per second · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

Speed

Measured by Output Speed (tokens per second)

Output Speed: Qwen3 14B (Non-reasoning)

Output speed: output tokens per second · 10,000 input tokens

Time per Intelligence Index Task

Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better
No data available

Cost per Task vs. Time per Task

Weighted average cost (USD) per Intelligence Index task · Weighted average decode time (minutes) per Intelligence Index task
Most attractive quadrant
No data available

Latency

Measured by Time (seconds) to First Token

Time to First Token

Seconds to first token received · Lower is better · 10,000 input tokens

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 · 10,000 input tokens

Key Comparison Metrics & API Features

DeepInfra logoDeepInfra
41k
Open
--
25
1.99
22.18
--
Alibaba Cloud logoAlibaba Cloud
131k
Open
--
64
2.65
10.52
--

Frequently Asked Questions

Common questions about Qwen3 14B (Non-reasoning) providers