Qwen: Qwen3 Coder

Qwen3

Code

Paid

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts). Pricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.

Parameters

Context Window

262,144

tokens

Input Price

$0.2

per 1M tokens

Output Price

$0.8

per 1M tokens

Capabilities

Model capabilities and supported modalities

Performance

Reasoning

Excellent reasoning capabilities with strong logical analysis

Math

Coding

Specialized in code generation with excellent programming capabilities

Knowledge

Modalities

Input Modalities

text

Output Modalities

text

LLM Price Calculator

Calculate the cost of using this model

Input Tokens (0.00000020/token)$0.000300

Output Tokens (0.00000080/token)$0.002400

Common Scenarios:

Input Cost:$0.000300

Output Cost:$0.002400

Total Cost:$0.002700

Estimated usage: 4,500 tokens

Monthly Cost Estimator

Based on different usage levels

Light Usage

$0.0100

~10 requests

Moderate Usage

$0.1000

~100 requests

Heavy Usage

$1.0000

~1000 requests

Enterprise

$10.0000

~10,000 requests

Note: Estimates based on current token count settings per request.

Last Updated: 1970/01/21