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.

Base modelAll models on this baseAll models of the providerto the provider

Read also: Qwen API pricing: Qwen3.8 Max, Plus, Flash, 27B and the open models at every provider

All Qwen models at every provider

Input, $/1M $0.29

Output, $/1M $2.40

Context 262 144

Max output 65 536

Accepts audio, images, text, video

Last checked 04.11.2026 12:00:14 UTC

Source —