Stay connected with us on X, Discord, and LinkedIn to stay up to date with future analysis
Qwen3 Coder 480B A35B Instruct logo

Qwen3 Coder 480B A35B Instruct API Provider Benchmarking & Analysis

Open weights model

Released July 2025

Analysis of API providers for Qwen3 Coder 480B A35B Instruct across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include DeepInfra (FP8), Hyperbolic (FP8), Baseten (FP8), Together.ai (FP8), Alibaba Cloud, Nebius, Amazon Bedrock, Google Vertex, DeepInfra (Turbo, FP4), Novita, Eigen AI.

Fastest

#1
Google VertexGoogle Vertex
164.3 t/s
#2
Together.ai (FP8)Together.ai (FP8)
155.6 t/s
#3
Baseten (FP8)Baseten (FP8)
75.2 t/s
#4
Eigen AIEigen AI
72.7 t/s
#5
Hyperbolic (FP8)Hyperbolic (FP8)
64.0 t/s

Output speed

Total 11 providers

Lowest Latency

#1
DeepInfra (Turbo, FP4)DeepInfra (Turbo, FP4)
0.26 s
#2
Google VertexGoogle Vertex
0.32 s
#3
DeepInfra (FP8)DeepInfra (FP8)
0.37 s
#4
Together.ai (FP8)Together.ai (FP8)
0.41 s
#5
NebiusNebius
0.62 s

Time to first token

Total 11 providers

Lowest Price

#1
DeepInfra (Turbo, FP4)DeepInfra (Turbo, FP4)
$0.51
#2
NovitaNovita
$0.55
#3
AmazonAmazon
$0.61
#4
Google VertexGoogle Vertex
$0.61
#5
Eigen AIEigen AI
$0.61

Blended price (per 1M tokens)

Total 11 providers

Qwen3 Coder 480B is available through 11 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 (164.3 t/s), Together.ai (FP8) (155.6 t/s), Baseten (FP8) (75.2 t/s). Speed varies significantly across providers, with a 157% difference between the fastest and slowest.
  • For latency, DeepInfra (Turbo, FP4) (0.26s), Google Vertex (0.32s), DeepInfra (FP8) (0.37s) offer the lowest time to first token.
  • For pricing, DeepInfra (Turbo, FP4) (0.51), Novita (0.55), Amazon (0.61) offer the lowest blended prices per 1M tokens.
  • DeepInfra (Turbo, FP4) offers both the lowest latency and best pricing, making it attractive for cost-conscious applications. Google Vertex is the fastest option for throughput-intensive workloads.
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:

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
Alibaba Cloud
Amazon
Baseten (FP8)
DeepInfra (FP8)
DeepInfra (Turbo, FP4)
Eigen AI
Google Vertex
Hyperbolic (FP8)
Nebius
Novita
Together.ai (FP8)

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)
Alibaba Cloud
Amazon
Baseten (FP8)
DeepInfra (FP8)
DeepInfra (Turbo, FP4)
Eigen AI
Google Vertex
Hyperbolic (FP8)
Nebius
Novita
Together.ai (FP8)

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 Token

Seconds to First Token Received; Lower is better; 1,000 Input Tokens

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.

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
'Thinking' time (reasoning models)
Input processing time
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
DeepInfra (FP8) logoDeepInfra (FP8)
Hyperbolic (FP8) logoHyperbolic (FP8)
Baseten (FP8) logoBaseten (FP8)
Together.ai (FP8) logoTogether.ai (FP8)
Alibaba Cloud logoAlibaba Cloud
Nebius logoNebius
Amazon logoAmazon
Google Vertex logoGoogle Vertex
DeepInfra (Turbo, FP4) logoDeepInfra (Turbo, FP4)
Novita logoNovita
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.

Summary Table of Key Comparison Metrics