qwen3-vl-235b · Qwen · vision
Qwen3 VL 235B is the open-weight multimodal model with 128K context and strong image, document and OCR understanding.
128K context; vision; document understanding; OCR; multimodal reasoning.
Image understanding; document parsing; OCR; multimodal reasoning.
128K context; open-weight; no image generation.
Anthropic公式のCLIコーディングエージェント。複数ファイル編集、ツール利用、長文脈推論。
export ANTHROPIC_AUTH_TOKEN="YOUR_API_KEY"
export ANTHROPIC_BASE_URL="https://api.robovai.com"
export ANTHROPIC_MODEL="qwen3-vl-235b"
claude --dangerously-skip-permissions