A
Qwen3.5-122B-A10BOPEN
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.
Prices update automatically — checked daily against provider list prices.
- $0.72 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 27% of the 191 open-weight models tracked here
- 34 of 51 Alibaba models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Qwen3.5-122B-A10B, measured by Artificial Analysis. Higher is better. Measurement mode: Reasoning.
For the same budget, Qwen3.5-122B-A10B delivers 4.7 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $0.69 per 1M tokens (median of 23) — this one costs $0.72.
Cheaper and better on this index: GLM 5.3 Flash · Gemini 3.7 Flash (batch) · GPT-5.6 Luna and 24 more
About this model
Qwen3.5-122B-A10B is an open-weight AI model by Alibaba. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B is an AI language model from Alibaba. It is open-weight: you can download it and run it on your own hardware, for free. It scores 32.8 on the Artificial Analysis intelligence index.
Is Qwen3.5-122B-A10B free?
The weights are free and open — you can self-host Qwen3.5-122B-A10B and pay nothing per token. If you prefer a hosted API, list prices are $0.26 per million input tokens and $2.08 per million output tokens.
What is Qwen3.5-122B-A10B good at?
Independent benchmarks from Artificial Analysis give it GPQA 85.7%, Humanity's Last Exam 25.2%, Long Context Reasoning 70.3%, SciCode 42%, IFBench 75.7%, τ²-Bench 93.6%, τ-Bench Banking 15.3%, Terminal-Bench 47.6%, Terminal-Bench Hard 31.1%. It is particularly used for code generation.
How fast is Qwen3.5-122B-A10B?
It generates about 138.8 tokens per second, with a median 1.01s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host Qwen3.5-122B-A10B?
Yes. Qwen3.5-122B-A10B has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.