Qwen 3.5 35B A3B · deepinfra

Qwen3.5-35B-A3B is an efficient Mixture-of-Experts model from Alibaba's Qwen3.5 series with 35B total parameters and only 3B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling, and support for 201 languages. Delivers strong performance on reasoning, coding, and vision-language tasks at a fraction of the compute cost.

Modelo baseTodos os modelos desta baseTodos os modelos do provedorao provedor

Leia também: Preços da API do Qwen: Qwen3.8 Max, Plus, Flash, 27B e os modelos abertos em todos os provedores

Todos os modelos Qwen em todos os provedores

Entrada, $/1M $0.14

Saída, $/1M $1.00

Contexto 262 144

Saída máx. 81 920

Aceita imagens, texto, vídeo

Última verificação 04.11.2026 12:00:14 UTC

Fonte —