Qwen3 Coder 480B A35B Check detailed information and pricing for AI models
Context Length 262,144 tokens, qwen from provided
262,144
Context Tokens
$0.20
Prompt Price
$0.80
Output Price
12/16
Feature Support
Overall #6
legal #3
technology #3
marketing #3
translation #3
programming #3
academia #3
trivia #3
roleplay #3
finance #3
science #3
health #3
seo #3
Efficiency #4
Model Overview
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.
Basic Information
Developer
qwen
Model Series
Qwen3
Release Date
2025-07-23
Context Length
262,144 tokens
Variant
standard
Pricing Information
Prompt Tokens
$0.20 / 1M tokens
Completion Tokens
$0.80 / 1M tokens
Data Policy
Terms of Service
학습 정책
1
Supported Features
Supported (12)
Top K
Seed
Frequency Penalty
Presence Penalty
Repetition Penalty
Response Format
Min P
Logit Bias
Tool Usage
Logprobs
Top Logprobs
Structured Outputs
Unsupported (4)
Image Input
Reasoning
Web Search Options
Top A
Other Variants
Actual Usage Statistics
#8
Out of 353 total models
486.9B
Total Tokens Last 30 Days
16.8B
Daily Average Usage
0%
Weekly Usage Change