19
2w
4

Deepseek-v3.2Speciale, built for agentic work, just released

Just saw the news on twitter - and this is my own screenshot of their API pricing taken just now.

V3 has received an update and is moving to 3.2 - including on the web interface. They posted all these nice benchmarks which I guess means something? Lol tbh I'm not sure how much you can trust these benchmarks.

What does this mean? Well, I gave the twitter thread announcement to Crush (and the new deepseek-v3.2, which you are automatically upgraded to both on API and web interface) and this is what it made of the news:

Quick Summary

DeepSeek has released V3.2, replacing the experimental version. There are two main models:

  • V3.2: General-purpose, balanced performance (GPT‑5 level)
  • V3.2‑Speciale: Specialized for complex reasoning (Gemini‑3.0‑Pro level)

Both are open‑source and available via API.

What's New & Why It Matters

1. Thinking Integrated with Tool‑Use

V3.2 can now "think" while using tools (like searching the web, running code, or calling APIs). This makes AI assistants more transparent and better at multi‑step tasks. You can choose thinking mode (slower but more thorough) or non‑thinking mode (faster for simple tasks).

2. Two Models for Different Needs

  • V3.2: Use this for most agentic work—chatbots, coding assistants, general automation. It's cost‑effective and reliable.
  • V3.2‑Speciale: Use this only when you need top‑tier reasoning—complex math, competitive programming, advanced planning. It uses more tokens (costs more) but solves harder problems.

3. Open‑Source & API Options

  • API: Available immediately. V3.2‑Speciale has a temporary endpoint until Dec 15, 2025.
  • Self‑hosting: Download from Hugging Face and run locally for privacy or cost savings.
  • Pricing: Same for both models [crush made a mistake in pricing here, not sure why. See my screenshot for current pricing or check on https://api-docs.deepseek.com/quick_start/pricing]

Practical Advice for Agent Builders

Which Model Should You Use?

  • Start with V3.2—it handles 90% of agentic tasks well.
  • Switch to V3.2‑Speciale only for tasks that require deep, step‑by‑step reasoning.
  • Monitor token costs—V3.2‑Speciale uses more tokens, so watch your API bill.

Key Improvements for Agentic Interfaces

  1. Better reasoning transparency—you can see the model's thought process when using tools.
  2. Mode flexibility—toggle thinking on/off based on task complexity.
  3. Stronger performance on benchmarks (math Olympiads, programming contests).

Timeline & Availability

  • Now: V3.2 on DeepSeek App, Web, and API
  • Until Dec 15: V3.2‑Speciale via temporary API (same price)
  • Always: Both models open‑source on Hugging Face
小莱卡 - 2w

❤️ deepseek

8
CriticalResist8 - 2w

no matter what one may think they have to admit deepseek is pretty much destroying the western AI ecosystem. On par with GPT5 on the free/cheap version is pretty big, considering how much fanfare there was around GPT5

7
Obama's Perfidy - 2w

V3.2 can now “think” while using tools (like searching the web, running code, or calling APIs). This makes AI assistants more transparent and better at multi‑step tasks. You can choose thinking mode (slower but more thorough) or non‑thinking mode (faster for simple tasks).

I fucking love deepseek

7
CriticalResist8 - 2w

it was pretty funny that deepseek gave me its own rundown technically lol, but its report on the official twitter thread is more in-depth than I gleaned from my own reading so

9