---
last_updated: 2026-11-20
source_url: https://opper.ai/alibaba/qwen3-30b-a3b
title: "Qwen3 30B A3B by Alibaba"
description: "Qwen3 30B A3B by Alibaba, an efficient MoE model with 3B active parameters and switchable thinking and non-thinking modes."
---

# Qwen3 30B A3B

By [Alibaba](https://opper.ai/alibaba).

Released 29 Apr 2025 · [Announcement](https://github.com/QwenLM/Qwen3) · [All Alibaba releases](https://opper.ai/model-releases/alibaba)

Qwen3-30B-A3B is Alibaba's efficient MoE model released in April 2025, with 30.5 billion total parameters and only 3.3 billion activated per token through 128 experts (8 selected). This sparse design delivers low inference cost while keeping broad capability across reasoning, coding, and general tasks.

The model supports switching between a step-by-step reasoning mode for complex problems and direct generation for straightforward queries within a single architecture. Native context covers around 40K tokens, extending to 131K via YaRN, and it handles mathematical reasoning, code generation, and instruction following across 100+ languages, drawing on roughly 36 trillion tokens of pretraining data.

Both thinking and non-thinking modes let users match computational depth to task complexity. MoE sparse activation means the inference cost reflects only a fraction of the full 30.5 billion parameters. Open-weight under Apache 2.0.

## Available routes

Qwen3 30B A3B runs on 2 different routes through the Opper gateway. Prices are per 1M tokens. In the EU it is served by Greenference. [See every Qwen model hosted in the EU](https://opper.ai/models/eu/qwen). One route also sells flex and priority processing: the same model at another price, picked per request with service_tier. [How service tiers work](https://docs.opper.ai/build/gateway/service-tiers). Its routes and prices, live from the catalogue, are public JSON with no API key needed at https://api.opper.ai/v3/models?q=deepinfra%2FQwen%2FQwen3-30B-A3B.

| Provider | Model id | Region | Zero data retention | Training | Input | Output | Cache read |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [DeepInfra](https://opper.ai/provider/deepinfra) | `deepinfra/Qwen/Qwen3-30B-A3B` | US (United States) | Yes | No | $0.12 | $0.50 | Input price |
| [DeepInfra](https://opper.ai/provider/deepinfra), Flex | `deepinfra:flex/Qwen/Qwen3-30B-A3B` | US (United States) | Yes | No | $0.10 | $0.40 | $0.10 |
| [DeepInfra](https://opper.ai/provider/deepinfra), Priority | `deepinfra:priority/Qwen/Qwen3-30B-A3B` | US (United States) | Yes | No | $0.18 | $0.75 | $0.18 |
| [Greenference](https://opper.ai/provider/greenference) | `greenference/qwen3-30b-a3b` | EU | Yes | No | $0.10 | $0.28 | $0.05 |

## Key info

- Model id: `deepinfra/Qwen/Qwen3-30B-A3B`
- Input: Text
- Output: Text
- Features: Reasoning, Tools
- Context window: 41K
- Max output: 41K
- Input price: $0.12 per 1M tokens
- Output price: $0.50 per 1M tokens
- Released: 29 Apr 2025
- EU residency available on Greenference
- US residency available on DeepInfra
- Zero data retention on pay-as-you-go
- No training by default

## Data handling per route

Each route hosting Qwen3 30B A3B has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

### DeepInfra — United States

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs.

- Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: No classifier
- Transfer mechanism: SCCs

Verified by Opper on 2026-10-19.

### Greenference — EU

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU.

- Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: No classifier
- Caching: Content cached for replay
- Subprocessor access: Subprocessors may read content
- Transfer mechanism: Not applicable — data stays in EU

Verified by Opper on 2026-09-21.

## Benchmarks

Independent benchmark scores via [Artificial Analysis](https://artificialanalysis.ai) ([view on AA](https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning)). Indices and domain scores are out of 100, Omniscience runs from −100 to 100, Briefcase is an Elo rating, and the other evaluation scores are the share of tasks solved.

- Global rank: #279 of 520 LLMs on the [LLM leaderboard](https://opper.ai/llm-leaderboard)
- Tier: Efficient
- Intelligence Index (previous version): 9.8
- Agentic: 0.4

### Coding

- Terminal-Bench 4.0: 0%
- SciCode: 33%
- LiveCodeBench: 71%

### Agentic & knowledge work

- AutomationBench: 1%
- GDPval: 0%
- GDP.pdf: 0%
- Briefcase (Elo): 6
- Terminal-Bench Hard: 6%
- τ²-Bench Telecom: 28%

### Science & reasoning

- Humanity's Last Exam: 10%
- GPQA Diamond: 71%
- Long-context reasoning: 61%

### Knowledge

- MMLU-Pro: 81%

### Math & instruction following

- AIME 2025: 66%
- IFBench: 51%

## Get started

Call Qwen3 30B A3B through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Qwen3 30B A3B is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

### Set it up with your agent

Paste this into a coding agent like Claude Code, Cursor or Codex and it will wire up Opper for you:

```text
Use curl to download, read and follow: https://skills.opper.ai Call Qwen3 30B A3B
```

### Or call it directly

OpenAI:

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const completion = await client.chat.completions.create({
  model: "deepinfra/Qwen/Qwen3-30B-A3B",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);
```

Anthropic:

```javascript
import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const message = await client.messages.create({
  model: "deepinfra/Qwen/Qwen3-30B-A3B",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello" }],
});
console.log(message.content);
```

Gemini:

```javascript
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: process.env.OPPER_API_KEY,
  httpOptions: { baseUrl: "https://api.opper.ai/v3/compat" },
});

const response = await ai.models.generateContent({
  model: "deepinfra/Qwen/Qwen3-30B-A3B",
  contents: "Hello",
});
console.log(response.text);
```

cURL:

```bash
curl https://api.opper.ai/v3/compat/chat/completions \
  -H "Authorization: Bearer $OPPER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepinfra/Qwen/Qwen3-30B-A3B",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'
```

## Use Qwen3 30B A3B in your apps

Pick your tool to see how to run it on Qwen3 30B A3B through Opper.

- [Claude Code](https://opper.ai/apps/claude-code/qwen3-30b-a3b)
- [Claude Cowork](https://opper.ai/apps/claude-cowork/qwen3-30b-a3b)
- [Codex](https://opper.ai/apps/codex/qwen3-30b-a3b)
- [DeepSeek Harness](https://opper.ai/apps/deepseek-harness/qwen3-30b-a3b)
- [GitHub Copilot CLI](https://opper.ai/apps/github-copilot-cli/qwen3-30b-a3b)
- [Aider](https://opper.ai/apps/aider/qwen3-30b-a3b)
- [Goose](https://opper.ai/apps/goose/qwen3-30b-a3b)
- [Droid](https://opper.ai/apps/droid/qwen3-30b-a3b)
- [OpenCode](https://opper.ai/apps/opencode/qwen3-30b-a3b)
- [Pi](https://opper.ai/apps/pi/qwen3-30b-a3b)
- [OpenClaw](https://opper.ai/apps/openclaw/qwen3-30b-a3b)
- [Hermes](https://opper.ai/apps/hermes/qwen3-30b-a3b)
- [Copilot for Obsidian](https://opper.ai/apps/obsidian-copilot/qwen3-30b-a3b)
- [OmniRoute](https://opper.ai/apps/omniroute/qwen3-30b-a3b)
- [Cursor](https://opper.ai/apps/cursor/qwen3-30b-a3b)
- [Cline](https://opper.ai/apps/cline/qwen3-30b-a3b)
- [Continue](https://opper.ai/apps/continue/qwen3-30b-a3b)
- [Kilo Code](https://opper.ai/apps/kilo-code/qwen3-30b-a3b)
- [GitHub Copilot](https://opper.ai/apps/github-copilot/qwen3-30b-a3b)
- [Zed](https://opper.ai/apps/zed/qwen3-30b-a3b)
- [JetBrains AI Assistant](https://opper.ai/apps/jetbrains-ai-assistant/qwen3-30b-a3b)
- [Voidleap Code](https://opper.ai/apps/voidleap-code/qwen3-30b-a3b)
- [n8n](https://opper.ai/apps/n8n/qwen3-30b-a3b)
- [LibreChat](https://opper.ai/apps/librechat/qwen3-30b-a3b)
- [Open WebUI](https://opper.ai/apps/open-webui/qwen3-30b-a3b)
- [See all apps](https://opper.ai/apps)

## Other models from Alibaba

- [Qwen4-Max](https://opper.ai/alibaba/qwen4-max)
- [Qwen3.8 Max](https://opper.ai/alibaba/qwen3-8-max)
- [Qwen3.8 27B](https://opper.ai/alibaba/qwen3-8-27b)
- [Qwen3.8-2.4T-A95B](https://opper.ai/alibaba/qwen3-8-2-4t-a95b)
- [Qwen3.8 Flash-Next](https://opper.ai/alibaba/qwen3-8-flash-next)
- [Qwen3.7-Max](https://opper.ai/alibaba/qwen3-7-max)
