Loading...
Loading...
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.
Preço/1M
$0.42
370th mais barato
34% acima da mediana
Top 54%
Janela de Contexto
262K
61st maior
Top 25%
Entrada
$0.22
por 1M tokens
Saída
$1.00
por 1M tokens
Combinado
$0.42
por 1M tokens
Mais barato que 46% dos modelos. Preço mediano é $0.31/1M tokens.
Diário
$0.42
Mensal
$12.45
Janela de Contexto
262K
tokens
Maior que 75% dos modelos
Comparação de Janela de Contexto