Deepseek V3.2 by NovitaAI | AI model information

Loading catalog

Loading catalog

Subscribe

Follow catalog updates and new guides

RSS feedOpen RSS feed

MediumMedium guides

skills.shskills.sh

CodexBank a free Codex reset

01 / 02Open RSS feed and Medium guides

RSS covers catalog changes. Medium has guides. Skills.sh has reusable agent playbooks. Codex reset is for new accounts.

Model explorer

Models

Deepseek V3.2 by NovitaAI | AI model information

Use Kimi K3 in OpenCode Go. Get $5 off your first month.

The fastest GLM 5.2, Kimi K2.7 and MiniMax M3The fastest GLM 5.2, Kimi K2.7 and MiniMax M3

Get a Codex banked reset for new accounts

Model details

Deepseek V3.2

Loading model overview

NovitaAIdeepseek/deepseek-v3.2deepseek

Open provider page Provider docs

Quick Info

Provider: NovitaAI
Model key: deepseek/deepseek-v3.2
Release date: Dec 1, 2025

Cost

Input token cost: $0.269
Output token cost: $0.40

Limits

Output tokens: 65,536 tokens
Context window

Latest news about Deepseek V3.2

No articles yet. Fetch the latest news to show it here.

Videos about Deepseek V3.2

Recent tweets and retweets from NovitaAI

More models around Deepseek V3.2

Also served by

This exact model name is also listed by 21 other providers.

Abacus Alibaba Token Plan Alibaba Token Plan (China)Amazon Bedrock Azure Azure Cognitive Services Cortecs CrofAI DigitalOcean Friendli Helicone Hugging Face LLM Gateway Meganova NanoGPT OpenRouter Venice AI Vercel AI Gateway Vertex Vivgrid Vultr

16 providers

Currently listed through these providers:

NovitaAI Abacus Alibaba (China)Amazon Bedrock Azure +11 more

10 providers

DeepSeek V3 0324

Currently listed through these providers:

NovitaAI Azure Azure Cognitive Services Cortecs GitHub Models +5 more

6 providers

Deepseek V3.1 Terminus

Currently listed through these providers:

NovitaAI Abacus Helicone NanoGPT OpenRouter +1 more

5 providers

DeepSeek V4 Pro

Currently listed through these providers:

FrogBot Together AI Venice AI Vercel AI Gateway Weights & Biases

5 providers

DeepSeek V3.2 Exp

Currently listed through these providers:

Alibaba (China)iFlow Meganova NanoGPT OpenRouter

4 providers

Deepseek V4 Flash

Currently listed through these providers:

DigitalOcean Venice AI Vercel AI Gateway Weights & Biases

4 providers

Currently listed through these providers:

AnyAPI DeepSeek OpenRouter OrcaRouter

3 providers

DeepSeek V3.2 Speciale

Currently listed through these providers:

Azure Azure Cognitive Services NanoGPT

3 providers

Currently listed through these providers:

D.Run (China)DigitalOcean Helicone

2 providers

deepseek-ai/DeepSeek-V3.2

Currently listed through these providers:

SiliconFlow SiliconFlow (China)

2 providers

DeepSeek V3.2 TEE

Currently listed through these providers:

2 providers

deepseek-ai/DeepSeek-V3.1-Terminus

Currently listed through these providers:

SiliconFlow SiliconFlow (China)

Discuss this model

Powered byHyvor Talk

Add corrections, implementation notes, pricing changes, or usage caveats for other readers.

Last updated

Dec 1, 2025

Input modalities

Output modalities

Capabilities

163,840 tokens

Recent tweets and retweets from NovitaAI

Jul 15, 2026, 2:57 AMUTC

That Hy3 test from Jen @jenzhuscott was really impressive. Thank you. 🥰

Jul 14, 2026, 9:01 PMUTC

We are officially hosting the Last Mile Hackathon in SF! 🌉 @ActionLayer_io and @novita_labs are teaming up to help you build AI agents that actually execute real-world tasks, not just plan them. BYOA (Bring Your Own Agent) and give it the infrastructure to handle payments,…

Jul 13, 2026, 8:18 PMUTC

K2.7 Code +136% with DSpark! Thanks Novita AI 🙏

Jul 13, 2026, 9:14 PMUTC

Break My AI returns this Wednesday!

Jul 13, 2026, 5:04 PMUTC

🚀 New record: 1.5T daily tokens on OpenRouter. From 1.3T → 1.4T → 1.5T. Excited to see Tencent Hy3 by @TencentHunyuan claim the #1 spot on OpenRouter. Huge thanks to every developer, partner, and the OpenRouter team for supporting Novita.