Loading...
Loading...
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per token, delivering performance comparable to models with 10 to 20x higher active compute, which makes it well suited for cost-sensitive, always-on agent deployment. The model is trained with a strong agentic focus and performs reliably on long-horizon coding tasks, complex tool usage, and recovery from execution failures. With a native 256k context window, it integrates cleanly into real-world CLI and IDE environments and adapts well to common agent scaffolds used by modern coding tools. The model operates exclusively in non-thinking mode and does not emit <think> blocks, simplifying integration for production coding agents.
Índice de Qualidade
28.3
112th de 442
Top 26%
Índice de Código
22.9
126th de 352
Top 36%
Preço/1M
$0.60
404th mais barato
94% acima da mediana
Top 59%
Velocidade
164 tok/s
Top 10%
TTFT
0.91s
Janela de Contexto
262K
61st maior
Top 25%
Entrada
$0.35
por 1M tokens
Saída
$1.20
por 1M tokens
Combinado
$0.60
por 1M tokens
Mais barato que 41% dos modelos. Preço mediano é $0.31/1M tokens.
Diário
$0.60
Mensal
$18.00
164
tokens/seg
Mais rápido que 90% dos modelos
0.91
segundos
Mais rápido que 33% dos modelos
0.91
segundos
Mais rápido que 40% dos modelos
Mediana do Mercado
46 tok/s
260% mais rápido
TTFT Mediano
0.42s
117% mais lento
Vazão/Dólar
273
tok/s por $/1M
Comparação de Velocidade
Janela de Contexto
262K
tokens
Maior que 75% dos modelos
Saída Máxima
66K
tokens
25% do contexto