Qwen3.5 122B A10B
StandardRun locallyQwen's second-strongest model — text capabilities exceeding Qwen3 235B, vision surpassing Qwen3 VL 235B.
Hybrid linear attention + sparse MoE architecture with 10B active parameters. Excellent multimodal reasoning across text, image, and video inputs.
▼
Qwen3.5 122B A10B is somewhat expensive at $0.26/M tokens input and $2.08/M tokens output. The model supports vision/image input, extended reasoning, a 262K context window.
Benchmarks
This model hasn't been evaluated by Artificial Analysis yet. Benchmark scores will appear once they're published.
Specifications
Performance
Providers
Run locally
Run Qwen3.5 122B A10B on your own computer with the Local AI Engine for free, with no rate limits and no third-party AI provider involved. idapt installs it and routes chat to your hardware automatically.
ollama pull qwen3.5:122b
Misc
Compare with
GPT 5.6 Solvs Qwen3.5 122B A10BGPT 5.6 Lunavs Qwen3.5 122B A10B
Claude Fable 5vs Qwen3.5 122B A10BClaude Opus 4.8vs Qwen3.5 122B A10BClaude Sonnet 5vs Qwen3.5 122B A10BClaude Haiku 4.5vs Qwen3.5 122B A10B
Gemini 3.6 Flashvs Qwen3.5 122B A10BGemini 3.5 Flashvs Qwen3.5 122B A10BGemini 3.5 Flash-Litevs Qwen3.5 122B A10BGemma 4 31Bvs Qwen3.5 122B A10B
Grok 4.5vs Qwen3.5 122B A10BGrok Build 0.1vs Qwen3.5 122B A10BGrok 4.1 Fastvs Qwen3.5 122B A10B
Muse Spark 1.1vs Qwen3.5 122B A10B
DeepSeek V4 Provs Qwen3.5 122B A10BDeepSeek V4 Flashvs Qwen3.5 122B A10B
MiniMax M3vs Qwen3.5 122B A10B
GLM 5.2vs Qwen3.5 122B A10B
Qwen3.7 Maxvs Qwen3.5 122B A10BQwen3.7 Plusvs Qwen3.5 122B A10BQwen3 Coder Nextvs Qwen3.5 122B A10B
Nemotron 3 Ultravs Qwen3.5 122B A10B
Mistral Small 4vs Qwen3.5 122B A10BFrequently Asked Questions about Qwen3.5 122B A10B▼
When was Qwen3.5 122B A10B released?
▼
Qwen3.5 122B A10B was released on February 25, 2026.
Who created Qwen3.5 122B A10B?
▼
Qwen3.5 122B A10B was created by Qwen.
How much does Qwen3.5 122B A10B cost?
▼
Qwen3.5 122B A10B costs $0.26/M input tokens and $2.08/M output tokens.
What is Qwen3.5 122B A10B API pricing?
▼
The Qwen3.5 122B A10B API is priced at $0.26 per million input tokens and $2.08 per million output tokens. You can access Qwen3.5 122B A10B through idapt.app alongside 200+ other AI models in one workspace.
Is Qwen3.5 122B A10B a reasoning model?
▼
Yes, Qwen3.5 122B A10B is a reasoning model. It can think step-by-step through complex problems before providing an answer, often yielding better results on difficult tasks like math, coding, and multi-step logic.
Does Qwen3.5 122B A10B support image or vision input?
▼
Yes, Qwen3.5 122B A10B supports vision/image input. You can share images in your conversation and the model will analyze and respond based on their content.
Does Qwen3.5 122B A10B support audio?
▼
No, Qwen3.5 122B A10B does not support audio input.
What is the context window of Qwen3.5 122B A10B?
▼
Qwen3.5 122B A10B has a context window of 262K tokens, meaning it can process approximately 196,608 words of context at once.
Is Qwen3.5 122B A10B open source?
▼
Qwen3.5 122B A10B is a proprietary model developed by Qwen. The model weights and training data are not publicly available.
What is Qwen3.5 122B A10B good at?
▼
Based on benchmark data, Qwen3.5 122B A10B excels at: visual analysis and image understanding. It is Qwen's capable model suitable for a wide range of tasks.
Where can I use Qwen3.5 122B A10B?
▼
You can chat with Qwen3.5 122B A10B on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access Qwen3.5 122B A10B through Qwen's own API or platform.