All AI models · LLM benchmarks · Methodology

Alibaba

Qwen3.5 397B A17B Thinking

Large open Qwen multimodal MoE for visual agents and long technical tasks

Model facts

Context window
258K tokens
Maximum output
66K tokens
Cheapest paid input
$0.6 per 1M tokens
Cheapest paid output
$3.6 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

reasoning, tool calling, attachments, temperature control, open weights, text, image, video.

Observed price history

  • 2026-08-24: $0.6 input / $3.6 output per 1M tokens

API providers

  • NanoGPT — model id qwen/qwen3.5-397b-a17b-thinking; $0.6 input / $3.6 output per 1M tokens; provider documentation