Qwen3.5 122B-A10B · deepinfra
Qwen3.5-122B-A10B is a large Mixture-of-Experts model from Alibaba's Qwen3.5 series with 122B total parameters and 10B 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. Excels at complex reasoning, coding, multimodal understanding, and agentic tasks with the efficiency of sparse activation.
Entrada, $/1M $0.29
Salida, $/1M $2.40
Contexto 262 144
Salida máx. 65 536
Acepta audio, imágenes, texto, vídeo
Última comprobación 04.11.2026 12:00:14 UTC
Fuente —
Alertas de precio
API
Este tipo de modelo no tiene un formato de solicitud común: consulta la documentación del proveedor.
Source: AI Rate Card, https://airatecard.com/es/c/offer%3Adeepinfra%7CQwen/Qwen3.5-122B-A10B, prices checked 2026-11-04
Datos técnicos
ID: offer:deepinfra|Qwen/Qwen3.5-122B-A10B