Qwen-QwQ-32B-fast
Qwen/QwQ-32B is a 32.5B parameter reasoning-focused large language model developed by the Qwen team. Based on the Qwen2.5 architecture, it combines pretraining, supervised finetuning, and reinforcement learning to enhance logical reasoning and problem-solving capabilities. With support for up to 131,072 tokens via YaRN, QwQ-32B delivers strong performance on complex tasks, rivaling models like DeepSeek-R1 and o1-mini. It uses advanced components like RoPE, SwiGLU, RMSNorm, and gated attention for high efficiency and accuracy in long-context text generation.
- Large Language Models (LLMs)
Price: $7.00 per hour of run time, billed per second.
Run Qwen-QwQ-32B-fast via API
curl -X POST https://api.flymy.ai/api/v1/flymyai/Qwen-QwQ-32B-fast/predict \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{}'API documentation · Create a free account · Pricing