Qwen: Qwen3.5-122B-A10B
Qwen3.5-122B-A10B from qwen is designed to handle text, images, and videos with a context length of 262,144 tokens and supports tools and reasoning capabilities. This model can generate structured output, making it versatile for various applications. This model should be considered by those who need a robust tool for handling multiple modalities and require the ability to reason effectively. Given its benchmark blended score of 54.4 across three independent benchmarks, it performs well in general AI tasks. While not free, with pricing at $0.4 per million input tokens and $3.2 per million output tokens, Qwen offers a competitive cost for its capabilities.
Benchmark results
Independent, published benchmarks. Blended score 54.4 across 3 benchmarks, last refreshed 2026-08-03. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 53.3 |
| AI Index Coding | software engineering tasks | 75.4 |
| AI Index Agentic | multi-step tool-using tasks | 34.2 |
- Model ID
- qwen/qwen3.5-122b-a10b
- Vendor
- qwen
- Released
- February 2026
- Tokenizer
- Qwen3
- Input Modalities
- text, image, video
- Output Modalities
- text
- Max Output
- 65,536 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.40/M input and $3.20/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.02 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.36 |
| A month of a busy support chatbot | 5M in / 2M out | $8.40 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-17.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-08-03 | $0.40 | $3.20 | 262,144 |
| 2026-07-17 | $0.26 | $2.08 | 262,144 |
Category rankings
Where Qwen: Qwen3.5-122B-A10B places across the 7 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #16 | Image CaptioningVision · of 25 ranked | 120 |
| #17 | Video SummarizationVideo · of 25 ranked | 146 |
| #18 | JSON ExtractionData · of 25 ranked | 143 |
| #20 | Dataset AnnotationResearch · of 25 ranked | 141 |
| #21 | Customer SupportBusiness · of 25 ranked | 131 |
| #23 | Bulk Data LabelingData · of 25 ranked | 133 |
| #23 | Video Auto-TaggingVideo · of 25 ranked | 123 |
Similar models
Qwen: Qwen3.7 Flash
Qwen: Qwen3.7 Plus
Qwen: Qwen3.5 Plus 2026-04-20
Qwen: Qwen3.6 Flash
Qwen: Qwen3.6 35B A3B
Qwen: Qwen3.6 27B
Quick answers
- How much does Qwen: Qwen3.5-122B-A10B cost?
- $0.40 per million input tokens and $3.20 per million output tokens.
- What is Qwen: Qwen3.5-122B-A10B's context window?
- 262,144 tokens, roughly 393 pages of text in a single request.
- Does Qwen: Qwen3.5-122B-A10B support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Qwen: Qwen3.5-122B-A10B process images?
- Yes, it accepts image input.