All AI models · LLM benchmarks · Methodology

Qwen 3.5 397B

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

Model facts

Context window
262K tokens
Maximum output
66K tokens
Cheapest paid input
$0.75 per 1M tokens
Cheapest paid output
$4.5 per 1M tokens
Open weights
yes
Providers
2

Capabilities and modalities

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

Observed price history

  • 2026-08-24: $0.75 input / $4.5 output per 1M tokens

API providers

  • Venice AI — model id qwen3-5-397b-a17b; $0.75 input / $4.5 output per 1M tokens; provider documentation
  • Ollama Cloud — model id qwen3.5:397b; not published input / not published output per 1M tokens; provider documentation