← Back to all models

Qwq 32b

qwq-32b

Provider: Nvidia, Context: 128000, Output Limit: 4096

Available at 12 Providers

Provider Source Input Price ($/1M) Output Price ($/1M) Description Free
nvidia models-dev Input: $0.00 Output: $0.00 Provider: Nvidia, Context: 128000, Output Limit: 4096
alibabacn models-dev Input: $0.29 Output: $0.86 Provider: Alibaba (China), Context: 131072, Output Limit: 8192
siliconflowcn models-dev Input: $0.15 Output: $0.58 Provider: SiliconFlow (China), Context: 131000, Output Limit: 131000
siliconflow models-dev Input: $0.15 Output: $0.58 Provider: SiliconFlow, Context: 131000, Output Limit: 131000
cloudflareworkersai models-dev Input: $0.66 Output: $1.00 Provider: Cloudflare Workers AI, Context: 24000, Output Limit: 24000
cloudflareaigateway models-dev Input: $0.66 Output: $1.00 Provider: Cloudflare AI Gateway, Context: 128000, Output Limit: 16384
deepinfra litellm Input: $0.15 Output: $0.40 Source: deepinfra, Context: 131072
hyperbolic litellm Input: $0.20 Output: $0.20 Source: hyperbolic, Context: 131072
nscale litellm Input: $0.18 Output: $0.20 Source: nscale, Context: N/A
sambanova litellm Input: $0.50 Output: $1.00 Source: sambanova, Context: 16384
fireworksai litellm Input: $0.90 Output: $0.90 Source: fireworks_ai, Context: 131072
openrouter openrouter Input: $0.15 Output: $0.40 QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini. Context: 32768