Qwen

Qwen3-Coder 30B-A3B Instruct

CTX262K

Tools

Input$0.45/M

Output$2.25/M

Smaller Qwen coder for efficient local agents and repo-level fixes

Open weightsApache 2.0527/1040

Drag to turn

QwenTextUncommon

Qwen3-Coder 30B-A3B Instruct

Smaller Qwen coder for efficient local agents and repo-level fixes

qwen3-coder-30b-a3b-instruct

Type: Text
Quality: Not rated yet
Context window: 262,144 tokens
Max output: 65,536 tokens
Input price: $0.45 / 1M tokens
Output price: $2.25 / 1M tokens
Cache read: —
Cache write: —
Parameters: 31B (30,532,122,624)
Downloads: 490K in the last 30 days
Likes: 1.3K
Access to weights: Open download
Released: Apr 1, 2025
Knowledge cutoff: Apr 2025
Takes in: Text
Puts out: Text
Reasoning: No
Tool calling: Yes
Structured output: No
File attachments: No
Access: Open weights
License: Apache 2.0
Rarity: Uncommon
Set number: 527/1040

Open Qwen docs Weights on Hugging Face Where to run it 21 Evolution 2/2 Race it 149 tok/s Meet its creature Battle Seed 2.1 Turbo

License read from the model’s Hugging Face card. Specs from models.dev, downloads from Hugging Face, last changed Oct 18, 2026. Official source: www.alibabacloud.com.

How good is it?

Public leaderboard scores for Qwen3-Coder 30B-A3B Instruct, refreshed daily from Epoch AI and LMArena.

No public leaderboard lists Qwen3-Coder 30B-A3B Instruct yet. Epoch AI and LMArena cover most chat, image, and video models from the big labs; embeddings, speech, and small open models mostly go unrated.

Where to run it

19 providers sell Qwen3-Coder 30B-A3B Instruct through an API, and 2 Hugging Face hosts serve it. Prices are per million tokens, cheapest first.

CheapestDevPass (LLM Gateway)$0.07 in · $0.27 out
Free to try2 providersModelScope, Pendra
From the labAlibaba$0.45 in · $2.25 out
Fastest on Hugging FaceScaleway149 tokens/s

API providers

Provider	Input	Output	Context
ModelScopeFree`Qwen/Qwen3-Coder-30B-A3B-Instruct`	Free	Free	262K
PendraFree`qwen3-coder:30b`	Free	Free	262K
DevPass (LLM Gateway)Cheapest paid`qwen3-coder-30b-a3b-instruct`	$0.07	$0.27	262K
LLM Gateway`novita/qwen3-coder-30b-a3b-instruct`	$0.07	$0.27	160K
Kilo Gateway`qwen/qwen3-coder-30b-a3b-instruct`	$0.07	$0.28	262K
OpenRouter`qwen/qwen3-coder-30b-a3b-instruct`	$0.07	$0.28	262K
SiliconFlow`Qwen/Qwen3-Coder-30B-A3B-Instruct`	$0.07	$0.28	262K
SiliconFlow (China)`Qwen/Qwen3-Coder-30B-A3B-Instruct`	$0.07	$0.28	262K
Helicone`qwen3-coder-30b-a3b-instruct`	$0.10	$0.30	262K
NanoGPT`qwen/qwen3-coder-30b-a3b-instruct`	$0.10	$0.40	128K

Show 9 more providers

Provider	Input	Output	Context
Amazon Bedrock`qwen.qwen3-coder-30b-a3b-v1:0`	$0.15	$0.60	262K
Vercel AI Gateway`alibaba/qwen3-coder-30b-a3b`	$0.15	$0.60	262K
Cortecs`qwen3-coder-30b-a3b-instruct`	$0.18	$0.70	262K
Clarifai`qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct`	$0.11	$0.75	262K
Scaleway`qwen3-coder-30b-a3b-instruct`	$0.20	$0.80	128K
Alibaba (China)`qwen3-coder-30b-a3b-instruct`	$0.22	$0.86	262K
Eden AI`scaleway/qwen3-coder-30b-a3b-instruct`	$0.23	$0.90	128K
GreenPT`qwen3-coder-30b-a3b-instruct`	$0.28	$1.08	128K
AlibabaOfficial`qwen3-coder-30b-a3b-instruct`	$0.45	$2.25	262K

Hugging Face Inference Providers

Host	Input	Output	Context	Speed	First token
ScalewayFastestTools	$0.23	$0.91	—	149 tok/s	0.4s
Featherless	—	—	—	—	—

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.