Qwen3.5-397B-A17B
Last refreshed 2026-05-22. Next refresh: weekly.
Qwen3.5-397B-A17B is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.
Decision context: Coding task fit, 4 tracked provider routes, and research from 2026-05-05.
Use it for
- Teams evaluating coding, rag, and agents
- Workloads that can use a 262k context window
- Buyers comparing 4 tracked provider routes
Do not use it for
- Workloads where another current model has stronger sourced task evidence
Featured in Picks
Cheapest output
$2.34
Alibaba Cloud PAI-EAS per 1M tokens
Provider routes
4
Tracked API hosts
Quality / dollar
Grade C
Ranked by benchmark score divided by cheapest output price
Freshness
2026-05-05
Researched 28d ago
Top use-case fit
Coding
Q/$ C1 relevant benchmark in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
Q/$ B1 relevant benchmark in the decision map.
Provider price ladder
Compare all 4| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Alibaba Cloud PAI-EAS | $0.390 | $2.34 | Serverless |
| OpenRouter | $0.390 | $2.34 | Serverless |
| Novita AI | $0.600 | $3.60 | Serverless |
| Together AI | $0.600 | $3.60 | Serverless |
Benchmark peer barsfor Coding
Migration checks
No linked migration route is available for this model yet.
About
Alibaba's largest Qwen3.5 model, featuring a Mixture-of-Experts architecture with 397B total parameters and 17B active per token (using 512 total experts with 10 routed + 1 shared active). Supports 201 languages with a native 262K token context window extensible to 1M tokens via YaRN. Includes a thinking/reasoning mode, tool calling with MCP integration, and unified vision-language capabilities through early fusion training.
Qwen3.5-397B-A17B is an open-source model in the Qwen3.5 family. The structured metadata tracks a 262k-token context window, multimodal input, reasoning, function calling, tool use, and structured outputs. This page tracks provider routes through OpenRouter, Together AI, Alibaba Cloud PAI-EAS, and 1 more, with the cheapest tracked route listed at $0.39 input and $2.34 output per 1M tokens. Headline tracked benchmarks include Google-Proof Q&A 89.3, MMLU PRO 87.8, and Massive Multi-discipline Multimodal Understanding 85.0.
Capabilities
Benchmark Scores(6)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Google-Proof Q&A | 89.3 | diamond | Artificial Analysis |
| MMLU PRO | 87.8 | — | https://huggingface.co/Qwen/Qwen3.5-397B-A17B |
| Massive Multi-discipline Multimodal Understanding | 85.0 | — | https://huggingface.co/Qwen/Qwen3.5-397B-A17B |
| Instruction-Following Evaluation | 92.6 | — | https://huggingface.co/Qwen/Qwen3.5-397B-A17B |
| BFCL | 72.9 | v4 | https://huggingface.co/Qwen/Qwen3.5-397B-A17B |
| SWE-bench Verified | 76.2 | SWE-bench Verified | https://benchlm.ai/benchmarks/sweVerified |
