All AI models · LLM benchmarks · Methodology

Alibaba

Qwen3.5 397B-A17B

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
$0.172 per 1M tokens
Cheapest paid output
$1.03 per 1M tokens
Open weights
yes
Providers
33

Capabilities and modalities

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

Local hardware estimate

At 4K context: Q4_K_M 214.5 GiB, Q8_0 402.3 GiB, F16 754.6 GiB working memory.

Parameters
403.4 billion
Architecture
qwen3_5moe
Model license
apache-2.0

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
Reasoning34.348.2not measured92.0
Non-reasoning32.7not measurednot measured86.8

Observed price history

  • 2026-08-24: $0.172 input / $1.03 output per 1M tokens

API providers

  • Nvidia — model id qwen/qwen3.5-397b-a17b; free input / free output per 1M tokens; provider documentation
  • UnoRouter — model id qwen3.5-397b-a17b:free; free input / free output per 1M tokens; provider documentation
  • Alibaba (China) — model id qwen3.5-397b-a17b; $0.172 input / $1.03 output per 1M tokens; provider documentation
  • EmpirioLabs AI — model id qwen3-5-397b-a17b; $0.172 input / $1.03 output per 1M tokens; provider documentation
  • Merge Gateway — model id qwen/qwen3.5-397b-a17b; $0.172 input / $1.03 output per 1M tokens; provider documentation
  • OrcaRouter — model id qwen/qwen3.5-397b-a17b; $0.172 input / $1.03 output per 1M tokens; provider documentation
  • CrofAI — model id qwen3.5-397b-a17b; $0.35 input / $1.75 output per 1M tokens; provider documentation
  • Vultr — model id Qwen/Qwen3.5-397B-A17B; $0.3 input / $2 output per 1M tokens; provider documentation
  • Kilo Gateway — model id qwen/qwen3.5-397b-a17b; $0.39 input / $2.34 output per 1M tokens; provider documentation
  • SiliconFlow — model id Qwen/Qwen3.5-397B-A17B; $0.39 input / $2.34 output per 1M tokens; provider documentation
  • TokenGo — model id qwen/qwen3.5-397b-a17b; $0.4 input / $2.65 output per 1M tokens; provider documentation
  • Deep Infra — model id Qwen/Qwen3.5-397B-A17B; $0.45 input / $3 output per 1M tokens; provider documentation
  • DigitalOcean — model id qwen3.5-397b-a17b; $0.55 input / $3.5 output per 1M tokens; provider documentation
  • Ofox — model id bailian/qwen3.5-397b-a17b; $0.55 input / $3.5 output per 1M tokens; provider documentation
  • OpenRouter — model id qwen/qwen3.5-397b-a17b; $0.55 input / $3.5 output per 1M tokens; provider documentation
  • Alibaba — model id qwen3.5-397b-a17b; $0.6 input / $3.6 output per 1M tokens; provider documentation
  • Cloudflare AI Gateway — model id alibaba/qwen3.5-397b-a17b; $0.6 input / $3.6 output per 1M tokens; provider documentation
  • DevPass (LLM Gateway) — model id qwen35-397b-a17b; $0.6 input / $3.6 output per 1M tokens; provider documentation
  • Hugging Face — model id Qwen/Qwen3.5-397B-A17B; $0.6 input / $3.6 output per 1M tokens; provider documentation
  • Jalapeno Cloud — model id Qwen3.5-397B-A17B; $0.6 input / $3.6 output per 1M tokens; provider documentation
  • LLM Gateway — model id novita/qwen35-397b-a17b; $0.6 input / $3.6 output per 1M tokens; provider documentation
  • LLMTR — model id qwen/qwen3.5-397b-a17b; $0.6 input / $3.6 output per 1M tokens; provider documentation
  • Mixlayer — model id qwen/qwen3.5-397b-a17b; $0.6 input / $3.6 output per 1M tokens; provider documentation
  • NanoGPT — model id qwen/qwen3.5-397b-a17b; $0.6 input / $3.6 output per 1M tokens; provider documentation
  • Nebius Token Factory — model id Qwen/Qwen3.5-397B-A17B; $0.6 input / $3.6 output per 1M tokens; provider documentation
  • NovitaAI — model id qwen/qwen3.5-397b-a17b; $0.6 input / $3.6 output per 1M tokens; provider documentation
  • Scaleway — model id qwen3.5-397b-a17b; $0.6 input / $3.6 output per 1M tokens; provider documentation
  • Together AI — model id Qwen/Qwen3.5-397B-A17B; $0.6 input / $3.6 output per 1M tokens; provider documentation
  • Cortecs — model id qwen3.5-397b-a17b; $0.668 input / $4.01 output per 1M tokens; provider documentation
  • OVHcloud AI Endpoints — model id qwen3.5-397b-a17b; $0.71 input / $4.25 output per 1M tokens; provider documentation
  • GreenPT — model id qwen3.5-397b-a17b; $0.798 input / $4.96 output per 1M tokens; provider documentation
  • Arena — model id qwen3.5-397b-a17b; not published input / not published output per 1M tokens; provider documentation
  • Qiniu — model id qwen3.5-397b-a17b; not published input / not published output per 1M tokens; provider documentation