DeepSeek-V3.2 by Deep Infra | AI model information

$10 off Synthetic - fastest OpenCode provider$10 off Synthetic - the fastest Kimi K2.6 and GLM 5.1 provider Discuss

Model details

DeepSeek-V3.2

Deep Infradeepseek-ai/DeepSeek-V3.2

Open provider page Provider docs

Quick Info

Provider: Deep Infra
Model key: deepseek-ai/DeepSeek-V3.2
Release date: Dec 2, 2025
Last updated: Dec 2, 2025

Cost

Input token cost: $0.26
Output token cost: $0.38

Limits

Output tokens: 64,000 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 Deep Infra

May 30, 2026, 12:41 PMUTC

Entire world: We need more GPUs Meanwhile, Jensen Huang: Video

Jun 1, 2026, 1:59 AMUTC

Introducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities - Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas - MiniMax Sparse Attention scales context to…

Jun 1, 2026, 9:23 AMUTC

We are really excited about Nemotron 3 Ultra.

May 16, 2026, 12:32 AMUTC

CEO Charles Liang Keynote @ Supermicro Innovate!/COMPUTEX

Jun 1, 2026, 4:35 AMUTC

Nemotron 3 Ultra is coming this week. ⌛️ Video

Recent tweets and retweets from Deep Infra

Discuss this model

Powered byHyvor Talk

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