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...

LLM & Generative AI 1 model 2 listings snapshot Oct 14, 2026, 12:53 AM

Platforms

click a card to open the detail table

Cheapest Together no official benchmark Input$0 Output$0 per 1M tokens Fastest OpenRouter lowest p50 latency on this board 128.1 ms p50 Most free quota Together · Qwen/Qwen3-Coder-30B-A3B-Instruct free listing ($0 per 1M) $0 free tier

Model variants

W3r9 dedup — same model + identical tags merge; prices are listed per billing form

Model	Provider	Tags	Input /1M	Output /1M
qwen/qwen3-coder-30b-a3b-instruct	OpenRouter	30b256k context	$0.070	$0.280
Qwen/Qwen3-Coder-30B-A3B-Instruct	Together	30b256k context	$0	$0

Capabilities

official design_arena & architecture metadata

Design Arena Elo official design_arena benchmark (OpenRouter)

website 1090 · 57.1% wr
dataviz 1085 · 54.7% wr
uicomponent 1048 · 54.1% wr

Input / Output modalities modality: text->text

text in+out

Platform details

per provider

provider	model	Input /1M	Output /1M	Latency ?	Official $/1M	Availability	Data time
OpenRouter	qwen/qwen3-coder-30b-a3b-instruct	$0.070	$0.280	128.1 ms	—	100% available	2026-10-14 00:43:21
Together	Qwen/Qwen3-Coder-30B-A3B-Instruct	$0	$0	—	—	—	2026-10-14 00:53:13

2 rows · snapshot 2026-10-14 00:53:13 · from data/public/prices.json + measurements.json