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 Results for other workloads are historical and no longer updated.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 Coder Next. We suggest considering it instead.

For more information, see comparison of Qwen3 Coder Next to other models and API provider benchmarks for Qwen3 Coder Next.

Open weights model

Released July 2025

Qwen3 Coder 480B A35B Instruct API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of Qwen3 Coder 480B A35B Instruct for your use-case.

Fastest

#1
Google VertexGoogle Vertex
156.8 t/s
#2
DeepInfra (Turbo, FP4)DeepInfra (Turbo, FP4)
104.7 t/s
#3
AmazonAmazon
102.2 t/s
#4
NovitaNovita
48.2 t/s
#5
Alibaba CloudAlibaba Cloud
47.6 t/s

Output speed

Total 5 providers

Lowest Latency

#1
Google VertexGoogle Vertex
0.76 s
#2
DeepInfra (Turbo, FP4)DeepInfra (Turbo, FP4)
0.80 s
#3
AmazonAmazon
1.23 s
#4
NovitaNovita
2.34 s
#5
Alibaba CloudAlibaba Cloud
2.97 s

Time to first token

Total 5 providers

Lowest Price

#1
DeepInfra (Turbo, FP4)DeepInfra (Turbo, FP4)
$0.23
#2
Google VertexGoogle Vertex
$0.38
#3
NovitaNovita
$0.50
#4
AmazonAmazon
$0.58
#5
Alibaba CloudAlibaba Cloud
$2.10

Blended price (per 1M tokens)

Total 5 providers

Qwen3 Coder 480B is available through 5 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 Google Vertex (156.8 t/s), DeepInfra (Turbo, FP4) (104.7 t/s), and Amazon (102.2 t/s). Speed varies significantly across providers, with a 229% difference between the fastest and slowest.
  • For latency, Google Vertex (0.76s), DeepInfra (Turbo, FP4) (0.80s), and Amazon (1.23s) offer the lowest time to first token.
  • For pricing, DeepInfra (Turbo, FP4) (0.23), Google Vertex (0.38), and Novita (0.50) offer the lowest blended prices per 1M tokens. Prices vary up to 9.1x across providers.
  • Google Vertex offers the best performance with both the highest speed and lowest latency. For cost optimization, DeepInfra (Turbo, FP4) 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

Pricing: Cache Discount

1 - (cache hit price / input price) · Higher 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
Pareto line

Speed

Measured by Output Speed (tokens per second)

Output Speed: Qwen3 Coder 480B A35B 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

Google logoGoogle
262k
Open
--
157
0.77
3.96
--
Alibaba Cloud logoAlibaba Cloud
262k
Open
--
49
3.03
13.19
--
DeepInfra logoDeepInfra
262k
Open
--
94
0.76
6.10
--
Amazon Bedrock logoAmazon Bedrock
262k
Open
--
117
1.25
5.51
--
Novita logoNovita
262k
Open
--
48
2.27
12.64
--

Frequently Asked Questions

Common questions about Qwen3 Coder 480B A35B Instruct providers