← Back to all models

Qwen3 235B-A22B

qwen3-235b-a22b

Provider: Alibaba, Context: 131072, Output Limit: 16384

Available at 10 Providers

Provider Source Input Price ($/1M) Output Price ($/1M) Description Free
alibaba models-dev Input: $0.70 Output: $2.80 Provider: Alibaba, Context: 131072, Output Limit: 16384
nvidia models-dev Input: $0.00 Output: $0.00 Provider: Nvidia, Context: 131072, Output Limit: 8192
alibabacn models-dev Input: $0.29 Output: $1.15 Provider: Alibaba (China), Context: 131072, Output Limit: 16384
siliconflowcn models-dev Input: $0.35 Output: $1.42 Provider: SiliconFlow (China), Context: 131000, Output Limit: 131000
chutes models-dev Input: $0.30 Output: $1.20 Provider: Chutes, Context: 40960, Output Limit: 40960
siliconflow models-dev Input: $0.35 Output: $1.42 Provider: SiliconFlow, Context: 131000, Output Limit: 131000
fireworksai models-dev Input: $0.22 Output: $0.88 Provider: Fireworks AI, Context: 128000, Output Limit: 16384
deepinfra litellm Input: $0.18 Output: $0.54 Source: deepinfra, Context: 40960
hyperbolic litellm Input: $2.00 Output: $2.00 Source: hyperbolic, Context: 131072
openrouter openrouter Input: $0.18 Output: $0.54 Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and code tasks, and a "non-thinking" mode for general conversational efficiency. The model demonstrates strong reasoning ability, multilingual support (100+ languages and dialects), advanced instruction-following, and agent tool-calling capabilities. It natively handles a 32K token context window and extends up to 131K tokens using YaRN-based scaling. Context: 40960