Qwen3.5-122B-A10B
Qwen· released 25 Feb 2026
qwen/qwen3.5-122b-a10b- Input / 1M tokens
- $0.26
- Output / 1M tokens
- $2.08
Longest answer: 66K tokens
About
Qwen3.5-122B-A10B is Qwen’s native vision-language model, built with a hybrid architecture combining linear attention and a sparse mixture-of-experts design. The listed summary says this architecture targets higher inference efficiency. The model accepts text, images, and video, and outputs text. It supports tools, vision, and reasoning, with a 262,144-token context window and a maximum output of 65,536 tokens. Qwen lists the model as open weights, with the Hugging Face identifier Qwen/Qwen3.5-122B-A10B. Its model ID is qwen/qwen3.5-122b-a10b, and its official page is on OpenRouter. Released and created on February 25, 2026, it costs $0.26 per 1 million input tokens and $2.08 per 1 million output tokens.
Who it is for
It suits builders seeking open weights for vision-language workloads involving text, images, and video. Tool and reasoning support add options for multimodal applications with large contexts.
What is good
- Open weights available
- Native vision-language model
- Accepts text, image, and video
- 262,144-token context window
- Tool, vision, and reasoning support
What to know first
- Output costs $2.08 per 1M tokens
- Maximum output is 65,536 tokens
- Produces text only
Verdict
Qwen3.5-122B-A10B pairs open weights with multimodal inputs, tools, vision, and reasoning. Its hybrid architecture and large context window suit teams evaluating broad input workloads.
Details
- Lab
- Qwenopenrouter.ai · 3 Oct 2026
- Context
- 262Kopenrouter.ai · 3 Oct 2026
- Input price
- $0.26 / 1Mopenrouter.ai · 3 Oct 2026
- Output price
- $2.08 / 1Mopenrouter.ai · 3 Oct 2026
- Max output
- 65,536 tokensopenrouter.ai · 3 Oct 2026
- Inputs
- text, image, videoopenrouter.ai · 3 Oct 2026
- Open weights
- Yesopenrouter.ai · 3 Oct 2026
More newest models
See the list
Listed on Inferse
- Newest Models in 2026466 listed
- Longest-Context Models in 2026466 listed
- Cheapest Language Models in 2026437 listed
- Models with Tool Calling in 2026395 listed
- Reasoning Models in 2026332 listed
- Vision Language Models in 2026295 listed
- Open-Weight Models in 2026178 listed
- Qwen Models: Pricing per 1M Tokens and Context (2026)52 listed
Sources
- openrouter.ai/qwen/qwen3.5-122b-a10b· checked 3 Oct 2026