Qwen3.5-397B-A17B is Alibaba's most capable Qwen3.5 model, a Mixture-of-Experts architecture with 397B total parameters and 17B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling with MCP integration, and support for 201 languages. Sets state-of-the-art results on reasoning, coding, math, and multimodal benchmarks.
Modalities
In / out price
$0.45 / $3.00
per 1M
Cached price
$0.22
per 1M
Context
262K
Max output
82K
Released
–
Providers
2 routesThe same model can have different pricing and privacy guarantees depending on who serves it. Only routes currently callable through AnonRouter are shown.
Privacy
2 / 4Private routing
Private tier
- Anonymous
- Private
- TEE
- E2EE
Prompt and response content is not retained after the request. Request content is visible to the inference runtime while it is being processed. Learn more