Qwen3-235B-A22B-Instruct-2507 is the July 2025 instruction-tuned update of the flagship 235B model, with 22 billion active parameters drawn from a 235 billion total pool. Released on July 21, 2025, it emphasizes stronger instruction following, mathematical reasoning, code generation, and long-context understanding up to 262K tokens. Tuned for general-purpose tasks rather than long reasoning chains, this variant operates in non-thinking mode and posts solid results on knowledge (MMLU-Pro 83.0), reasoning (AIME25 70.3), coding (LiveCodeBench 51.8), and multilingual benchmarks across 100+ languages. The MoE architecture activates only 22 billion of its 235 billion parameters per forward pass for efficient inference. It supports tool calling for agentic workflows and is optimized for instruction following across diverse domains. Open-weight under Apache 2.0.
Qwen3 235B A22B Instruct runs on 3 different routes through the Opper gateway. Compare residency, ZDR, and training posture at a glance โ full data-handling detail per route below.
Training posture across routes: No training on prompts by default.
Each route hosting Qwen3 235B A22B Instruct 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. US; unknown.
Zero data retention is available via Opper Enterprise contract. No training on customer data. EU; DPA available.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Independent benchmark scores โ composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call Qwen3 235B A22B Instruct 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: "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
