Qwen3-30B-A3B-Instruct-2507 is the instruction-tuned variant of the 30B MoE model, tuned for following user queries and tasks with strong results across reasoning, coding, mathematics, and general knowledge. It has 30.5 billion total parameters and 3.3 billion activated through 128 experts, balancing efficiency with broad capability. The model supports a 262K context window for extended document understanding and long-context work, and it operates in non-thinking mode. It posts solid scores on mathematics (AIME25 61.3), coding (LiveCodeBench 43.2), and creative writing (Creative Writing v3 86.0), while handling 100+ languages. Tool calling enables agentic workflows. As an instruction-tuned model, it is optimized for user preference alignment and subjective task quality. The sparse MoE design keeps inference efficient, activating only 3.3 billion parameters despite the 30.5 billion total. Open-weight under Apache 2.0.
Qwen 3 30B runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance โ full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| Nebius | EU | Enterprise | No | $0.10 | $0.30 |
Training posture across routes: No training on prompts by default.
Each route hosting Qwen 3 30B has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is available via Opper Enterprise contract. No training on customer data. EU; DPA available.
Independent benchmark scores โ composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call Qwen 3 30B through the Opper gateway with one API key. Let your coding agent set it up, or call it directly โ Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into your coding agent โ Claude Code, Cursor, Codex, and more โ and it'll wire up Opper for you.
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: "nebius/qwen3-30b-a3b-instruct",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
