Released 13 days after Qwen 3 Coder Next · All Alibaba releases
Qwen3.5 397B A17B is Alibaba's large sparse Mixture-of-Experts model with 397 billion total parameters and 17 billion activated per token, built for frontier-class reasoning and coding. It is multimodal across text, image, and video, with a 262,144 token native context window extensible toward roughly one million tokens with YaRN scaling. Reported scores include MMLU-Pro 87.8, MMMU-Pro 79.0, and SWE-bench Verified 76.4. The model runs in thinking mode by default, generating reasoning tokens before its response, and supports recommended output lengths up to 81,920 tokens for hard problems. It targets demanding agentic workflows, repository-level code reasoning, structured outputs, and tool calling across more than 200 languages.
Qwen 3.5 397B runs on 5 different routes through the qynio gateway. Compare residency, zero retention, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| US | Zero data retention | No | $0.45 | $3.00 | |
| US | Not by default | No | $0.55 | $3.50 | |
| US | Not by default | No | $0.50 | $3.50 | |
| US | Not by default | No | $0.60 | $3.60 | |
| US | Zero data retention | No | $0.60 | $3.60 |
Qwen 3.5 397B runs on 3 independently monitored routes through the qynio gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 2 further routes for this model are not on the board yet and are not counted above. See uptime for every provider qynio monitors.
Each route hosting Qwen 3.5 397B has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; unknown; deposit available.
Zero data retention is not on by default — a moderation hold applies. No training on customer data. US; dpf sccs; deposit available.
Zero data retention is not on by default — abuse monitoring, 30-day retention. No training on customer data. US; wallets; deposit available.
Zero data retention is not on by default — abuse monitoring. No training on customer data. US; wallets; deposit available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; wallets; deposit available.
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call Qwen 3.5 397B through the qynio gateway with one API key. Let your coding agent set it up, or call it directly — qynio is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.QYN_API_KEY,baseURL: "https://api.qyn.io/v3/compat",});const completion = await client.chat.completions.create({model: "deepinfra/Qwen/Qwen3.5-397B-A17B",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, crypto rails, pricing, and benchmarks.
