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.
Modalities
In / out price
$0.29 / $2.40per 1M
Context
262K
Max output
82K
Updated
Sep 6, 2026
Providers
1 routeCompare providers by price, privacy, and speed.
| Private | $0.29 | $2.40 | — | 262K | 82K | — | — |
Privacy
2 / 4Private routing
Private tier
- Anonymous
- Private
- TEE
- E2EE
Prompt and response content is not retained after the request. Request content is visible to the inference runtime while it is being processed. Learn more
Features
5Uptime
FAQ
Common questions about Qwen3.5 122B A10B.