When was DeepSeek V3.2 released?

DeepSeek released DeepSeek V3.2 on 1 Dec 2025. It is available through the Opper gateway.

Does DeepSeek V3.2 support zero data retention?

Yes. DeepSeek V3.2 is available with zero data retention on DeepInfra, Infercom, Novita, TensorX through the Opper gateway. Other routes carry zero data retention with abuse monitoring; see each route's window in the data-handling section.

Where is DeepSeek V3.2 hosted?

DeepSeek V3.2 runs on both EU and US hosting routes through the Opper gateway. Pick the route that matches your residency requirement.

Is DeepSeek V3.2 trained on prompts and outputs?

No. Every hosting route for DeepSeek V3.2 is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for DeepSeek V3.2?

Yes. A GDPR Data Processing Agreement is available on at least one route serving DeepSeek V3.2. Contact hello@opper.ai to receive it.

DeepSeek V3.2

by DeepSeek

Released 70 days after DeepSeek V3.1 Terminus · All DeepSeek releases

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.

Call DeepSeek V3.2 on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

131K

Max output

33K

Input price

$0.28 /1M$0.06 cache read

Output price

$0.42 /1M

Released

1 Dec 2025

EU residency available
US residency available
Zero data retention on pay-as-you-go
No training by default
GDPR DPA available

Available routes

DeepSeek V3.2 runs on 6 different routes through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Provider	Region	Training	Input	Output	Cache read
BytePlus	Multi	No	$0.28	$0.42	$0.06
DeepInfra	US	No	$0.26	$0.38	$0.13
DigitalOcean	US	No	$0.25	$0.80	$0.07
Infercom	US	No	$3.42	$5.13	Input price
Novita	US	No	$0.27	$0.40	$0.13
TensorX	EU	No	$0.30	$0.50	$0.08

Uptime and availability

DeepSeek V3.2 runs on 2 independently monitored routes through the Opper gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.

100%effective uptime, last 30 days

Averaged across these routes on their own, a single provider reached 100% over the same window.

Daily status through the gateway, which serves each request from whichever route is healthy.

2 monitored providers serve DeepSeek V3.2.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 4 further routes for this model are not on the board yet and are not counted above. See uptime for every provider Opper monitors.

Data handling per route

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.

BytePlus — Multi-region

Zero data retention with abuse monitoring: prompts and outputs are kept for up to 180 days for abuse monitoring only, and are not used for training. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention: With abuse monitoring, 180-day window.
Training: No training on customer data.
Logging: Abuse monitoring (180-day retention)
Abuse monitoring: On by default, holds flagged content, 180 days, stored in Malaysia, a person can view samples
Caching: Content cached for replay
GDPR DPA: DPA available
Transfer mechanism: SCCs

DeepInfra — United States🇺🇸

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

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
GDPR DPA: DPA available
Transfer mechanism: unknown

DigitalOcean — United States🇺🇸

Zero data retention with abuse monitoring: nothing is logged or used for training; content flagged by abuse monitoring is held for review. No training on customer data. US; dpf sccs; DPA available.

Zero data retention: With abuse monitoring, flagged content held.
Training: No training on customer data.
Logging: None
Abuse monitoring: Always on, holds flagged content, stored in United States
Caching: Content cached for replay
Subprocessor access: No subprocessor reads content
GDPR DPA: DPA available
Transfer mechanism: dpf sccs

Infercom — United States🇺🇸

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

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
Subprocessor access: Subprocessors may read content
GDPR DPA: DPA available
Transfer mechanism: SCCs

Novita — United States🇺🇸

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

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: On by default, keeps nothing
GDPR DPA: DPA available
Transfer mechanism: SCCs

TensorX — European Union🇪🇺

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

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
GDPR DPA: DPA available
Transfer mechanism: Not applicable — data stays in EU

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#257 of 665 LLMs

TierEfficient

Intelligence Index16.0

Math Index59.0

Reasoning & knowledge

MMLU-Pro

84%

GPQA Diamond

75%

Humanity's Last Exam

11%

Long-context reasoning

46%

Coding

LiveCodeBench

59%

Agentic & tool use

Terminal-Bench Hard

33%

τ²-Bench Telecom

79%

Math & instruction following

AIME 2025

59%

IFBench

49%

See full leaderboard →Benchmarks via Artificial Analysis · View on AA

Get started

Call DeepSeek V3.2 through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

DeepSeek V3.2 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

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "deepseek-v3.2",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);