Qwen: Qwen3.5 397B A17B
Qwen3.5 397B A17B is a model from Qwen that accepts text, image, and video input and returns text. It offers a 262,144-token context window with up to 235,929 completion tokens, which suits long documents, large codebases, and extended outputs. It supports tool calling and a reasoning mode; structured output support is not specified in the available data, so verify it before relying on schema-constrained responses. Pricing is $0.50 per million input tokens and $3.60 per million output tokens, so input-heavy workloads stay cheap while long generations cost noticeably more. Across four independent benchmarks it posts a blended score of 60.1. Its coding index of 79.5 is its strongest result, while its agentic score of 32.7 is markedly weaker. Teams focused on coding or multimodal analysis over long context should shortlist it; those building autonomous multi-step agents should test it against alternatives first.
Benchmark results
Independent, published benchmarks. Blended score 60.1 across 4 benchmarks, last refreshed 2026-11-08. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 55.6 |
| AI Index Coding | software engineering tasks | 79.5 |
| AI Index Agentic | multi-step tool-using tasks | 32.7 |
| EQ-Bench | emotional understanding in dialogue | 58.0 |
- Model ID
- qwen/qwen3.5-397b-a17b
- Vendor
- qwen
- Released
- February 2026
- Tokenizer
- Qwen3
- Input Modalities
- text, image, video
- Output Modalities
- text
- Max Output
- 235,929 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 $0.50/M input and $3.60/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 | $0.43 |
| A month of a busy support chatbot | 5M in / 2M out | $9.70 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-17.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-10-22 | $0.50 | $3.60 | 262,144 |
| 2026-10-20 | $0.39 | $2.34 | 262,144 |
| 2026-10-14 | $0.50 | $3.60 | 262,144 |
| 2026-10-09 | $0.55 | $3.50 | 262,144 |
| 2026-10-06 | $0.45 | $3.00 | 262,144 |
| 2026-09-09 | $0.55 | $3.50 | 262,144 |
| 2026-09-07 | $0.39 | $2.34 | 262,144 |
| 2026-09-03 | $0.55 | $3.50 | 262,144 |
| 2026-08-26 | $0.39 | $2.34 | 262,144 |
| 2026-08-24 | $0.50 | $3.60 | 262,144 |
| 2026-08-15 | $0.39 | $2.34 | 262,144 |
| 2026-08-14 | $0.50 | $3.60 | 262,144 |
| 2026-08-13 | $0.45 | $3.00 | 262,144 |
| 2026-08-11 | $0.50 | $3.60 | 262,144 |
| 2026-07-17 | $0.39 | $2.34 | 262,144 |
Category rankings
Where Qwen: Qwen3.5 397B A17B places across the 9 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #9 | Video SummarizationVideo · of 25 ranked | 152 |
| #18 | Short-Form SummarizationWriting · of 25 ranked | 129 |
| #18 | Chat CompanionPersonal · of 25 ranked | 129 |
| #18 | Trivia & General KnowledgePersonal · of 25 ranked | 120 |
| #20 | Email DraftingWriting · of 25 ranked | 125 |
| #20 | Language LearningEducation · of 25 ranked | 125 |
| #20 | Image CaptioningVision · of 25 ranked | 120 |
| #24 | Dataset AnnotationResearch · of 25 ranked | 141 |
| #25 | JSON ExtractionData · of 25 ranked | 144 |
Similar models
Qwen: Qwen3.8 Max Prime
Qwen: Qwen3.8 Omni Flash
Qwen: Qwen3.8 Max (0902)
Qwen: Qwen3.8 Flash
Qwen: Qwen3.8 27B
Qwen: Qwen3.8 27B (batch)
Quick answers
- How much does Qwen: Qwen3.5 397B A17B cost?
- $0.50 per million input tokens and $3.60 per million output tokens.
- What is Qwen: Qwen3.5 397B A17B's context window?
- 262,144 tokens, roughly 393 pages of text in a single request.
- Does Qwen: Qwen3.5 397B A17B support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Qwen: Qwen3.5 397B A17B process images?
- Yes, it accepts image input.