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 Results for other workloads are historical and no longer updated.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 model, Qwen3.5 35B A3B (Non-reasoning). We suggest considering it instead.

For more information, see comparison of Qwen3.5 35B A3B (Non-reasoning) to other models and API provider benchmarks for Qwen3.5 35B A3B (Non-reasoning).

Qwen3 30B A3B 2507

Open weights model

Released July 2025

Qwen3 30B A3B 2507 Instruct API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of Qwen3 30B A3B 2507 Instruct for your use-case.

Fastest

#1
CoreWeaveCoreWeave
167.1 t/s
#2
Alibaba CloudAlibaba Cloud
137.0 t/s
#3
NebiusNebius
30.9 t/s

Output speed

Total 3 providers

Lowest Latency

#1
CoreWeaveCoreWeave
0.68 s
#2
NebiusNebius
1.18 s
#3
Alibaba CloudAlibaba Cloud
1.85 s

Time to first token

Total 3 providers

Lowest Price

#1
NebiusNebius
$0.12
#2
CoreWeaveCoreWeave
$0.12
#3
Alibaba CloudAlibaba Cloud
$0.26

Blended price (per 1M tokens)

Total 3 providers

Qwen3 30B A3B 2507 (Non-reasoning) is available through 3 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 CoreWeave (167.1 t/s), Alibaba Cloud (137.0 t/s), and Nebius (30.9 t/s).
  • For latency, CoreWeave (0.68s), Nebius (1.18s), and Alibaba Cloud (1.85s) offer the lowest time to first token.
  • For pricing, Nebius (0.12), CoreWeave (0.12), and Alibaba Cloud (0.26) offer the lowest blended prices per 1M tokens.
  • CoreWeave offers the best performance with both the highest speed and lowest latency. For cost optimization, Nebius provides the most competitive pricing.

Highlights

Output tokens per second · Higher is better
Seconds · 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

Pricing: Blended Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended) · Lower is better

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

Speed

Measured by Output Speed (tokens per second)

Output Speed: Qwen3 30B A3B 2507 Instruct

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

Latency vs. Output Speed

Latency: seconds to first token received · Output speed: output tokens per second · 10,000 input tokens
Most attractive quadrant

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

Nebius logoNebius
262k
Open
--
33
1.18
16.39
--
Alibaba Cloud logoAlibaba Cloud
262k
Open
--
139
1.89
5.50
--
CoreWeave logoCoreWeave
262k
Open
--
167
0.69
3.69
--

Frequently Asked Questions

Common questions about Qwen3 30B A3B 2507 Instruct providers