Qwen3.5-122B-A10B
Review Qwen3.5-122B-A10B on key metrics including price, context length, throughput, and model features.
AuthorQwen
Context Length262.1k
Supports Tools
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.
Activity
Last 14 daysPrompt
288Completion
3KTotal
3KStartup
Startup
Latency (p50)-
Throughput (p50)99.5 tok/s
Pricing
Input$0.13/M tokens
Output$1.04/M tokens
Features
Input Modalitiestext, image
Output Modalitiestext
Supported EndpointsChat Completions
Vision
Supports Tools