← Back to all models

Qwen3-Coder 30B-A3B Instruct

qwen3-coder-30b-a3b-instruct

Provider: Alibaba, Context: 262144, Output Limit: 65536

Available at 10 Providers

Provider Source Input Price ($/1M) Output Price ($/1M) Description Free
alibaba models-dev Input: $0.45 Output: $2.25 Provider: Alibaba, Context: 262144, Output Limit: 65536
alibabacn models-dev Input: $0.22 Output: $0.86 Provider: Alibaba (China), Context: 262144, Output Limit: 65536
siliconflowcn models-dev Input: $0.07 Output: $0.28 Provider: SiliconFlow (China), Context: 262000, Output Limit: 262000
siliconflow models-dev Input: $0.07 Output: $0.28 Provider: SiliconFlow, Context: 262000, Output Limit: 262000
helicone models-dev Input: $0.10 Output: $0.30 Provider: Helicone, Context: 262144, Output Limit: 262144
ovhcloud models-dev Input: $0.07 Output: $0.26 Provider: OVHcloud AI Endpoints, Context: 256000, Output Limit: 256000
modelscope models-dev Input: $0.00 Output: $0.00 Provider: ModelScope, Context: 262144, Output Limit: 65536
scaleway models-dev Input: $0.20 Output: $0.80 Provider: Scaleway, Context: 128000, Output Limit: 8192
fireworksai litellm Input: $0.15 Output: $0.60 Source: fireworks_ai, Context: 262144
openrouter openrouter Input: $0.07 Output: $0.27 Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the Qwen3 architecture, it supports a native context length of 256K tokens (extendable to 1M with Yarn) and performs strongly in tasks involving function calls, browser use, and structured code completion. This model is optimized for instruction-following without “thinking mode”, and integrates well with OpenAI-compatible tool-use formats. Context: 160000