qwentext → text
Qwen: Qwen3 Coder 30B A3B Instruct
Canonical ID: qwen/qwen3-coder-30b-a3b-instruct
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...
Artificial Analysis Benchmarks
VerifiedNo standardized Artificial Analysis benchmark scores recorded for this variant yet.
Token Pricing & Economics
Prompt Input (1M Tokens)
Input$0.07
Completion Output (1M Tokens)
Output$0.28
Prompt KV-Cache Read (1M Tokens)
Cached$0.00
Context Window Capacity
Context256k tokens
Supported Parameters & Features
frequency_penaltymax_tokensresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p