Hub/Models/qwen/qwen3-coder-30b-a3b-instruct
qwentext → text

Qwen: Qwen3 Coder 30B A3B Instruct

Canonical ID: qwen/qwen3-coder-30b-a3b-instruct

Compare ModelOpen on OpenRouter →

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

Verified
No standardized Artificial Analysis benchmark scores recorded for this variant yet.

Token Pricing & Economics

Prompt Input (1M Tokens)
$0.07
Input
Completion Output (1M Tokens)
$0.28
Output
Prompt KV-Cache Read (1M Tokens)
$0.00
Cached
Context Window Capacity
256k tokens
Context

Supported Parameters & Features

frequency_penaltymax_tokensresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p