DeepSeek-V3.2, released December 2025, is DeepSeek's first model to integrate thinking directly into tool-use, supporting tool calls in both thinking and non-thinking modes. The 671-billion-parameter sparse MoE activates 37 billion per token and uses DeepSeek Sparse Attention to cut long-context compute while preserving quality. DeepSeek positions it as a daily driver at GPT-5-level performance, with strong agentic results including 73.1% on SWE-bench Verified and 93.1% on AIME 2025. A higher-compute variant, V3.2-Speciale, pushes reasoning further and attained gold-level results at the 2025 IMO, CMO, ICPC World Finals, and IOI. Released open-weight under an MIT license with Hugging Face weights, V3.2 targets teams building reasoning-first agent architectures that need capable long-context tool-use without proprietary lock-in.
DeepSeek V3.2 runs on 4 different routes through the Opper gateway. Compare residency, ZDR, and training posture at a glance β full data-handling detail per route below.
Training posture across routes: No training on prompts by default.
Each route hosting DeepSeek V3.2 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 on by default on Pay-as-you-go β no action required. No training on customer data. US; dpf sccs; DPA available.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Independent benchmark scores β composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call DeepSeek V3.2 through the Opper gateway with one API key. Let your coding agent set it up, or call it directly β Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into your coding agent β Claude Code, Cursor, Codex, and more β 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/deepseek-ai/DeepSeek-V3.2",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
