Qwen3 Coder 30B A3B Instruct as a coding agent in your terminal
Qwen3 Coder 30B A3B Instruct by Qwen (Alibaba), one of 250+ models you can use in Darce, the open source AI coding agent you can undo.
| Model | Qwen3 Coder 30B A3B Instruct |
|---|---|
| Vendor | Qwen (Alibaba) |
| Model id | qwen/qwen3-coder-30b-a3b-instruct |
| Context window | 262k tokens |
| Price per 1M tokens | $0.070 input · $0.28 output (OpenRouter) |
| Can do | tool calling |
| Category | Open weights and budget |
Strengths
A small Qwen3 Coder (30B, 3B active). Extremely cheap; good for simple edits and experiments.
OpenRouter's description:
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...
Use Qwen3 Coder 30B A3B Instruct as a coding agent in your terminal
Start Darce in your project with Qwen3 Coder 30B A3B Instruct:
npm install -g darce-cli
darce --model qwen/qwen3-coder-30b-a3b-instructAlready in a session? Type /model qwen/qwen3-coder-30b-a3b-instruct, or open the picker with Ctrl+P. Darce then reads your code, edits files and runs commands with Qwen3 Coder 30B A3B Instruct; risky commands ask first, and /undo reverses any change, including what shell commands did. No account yet? npx darce-cli lets you try it free. Which plan includes which models is on the pricing page.
Make it your default or a gear
In ~/.darcerc, set it as the starting model or add it to the gears you move between with Shift+↑ / Shift+↓ (see configuration):
{
"router": { "default": "qwen/qwen3-coder-30b-a3b-instruct" },
"gears": ["qwen/qwen3-coder", "qwen/qwen3-coder-30b-a3b-instruct"]
}Compare it on your own code
Benchmarks rarely match your repository. Race Qwen3 Coder 30B A3B Instruct against two other models on a real task and keep the best diff:
/derby --models qwen/qwen3-coder-30b-a3b-instruct,qwen/qwen3-coder,qwen/qwen3-coder-next fix the failing testRead more about /derby and /swarm.
Related models
- Qwen3 Coder 480B A35B (Qwen (Alibaba)): 262k tokens, $0.30 / $1.00 per 1M tokens
- Qwen3 Coder Next (Qwen (Alibaba)): 262k tokens, $0.12 / $0.80 per 1M tokens
- Qwen3 Coder Plus (Qwen (Alibaba)): 1M tokens, $0.65 / $3.25 per 1M tokens
- Qwen3 Coder Flash (Qwen (Alibaba)): 1M tokens, $0.20 / $0.97 per 1M tokens
- gpt-oss-120b (OpenAI): 131k tokens, $0.037 / $0.17 per 1M tokens
- Gemma 4 31B (Google): 262k tokens, $0.090 / $0.34 per 1M tokens
- DeepSeek V3.2 (DeepSeek): 164k tokens, $0.26 / $0.80 per 1M tokens
- Kimi K2.6 (Moonshot AI): 262k tokens, $0.47 / $2.45 per 1M tokens
All models · Getting started · Claude Code alternative
Model data from OpenRouter, refreshed daily. Prices are OpenRouter's list rates and show relative cost; your Darce allowance is used in proportion to them.