DeepSeek: DeepSeek V3.2 Speciale
deepseek/deepseek-v3.2-speciale
Access DeepSeek V3.2 Speciale from DeepSeek using Puter.js AI API.
Get Started// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "deepseek/deepseek-v3.2-speciale"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "deepseek/deepseek-v3.2-speciale"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.puter.com/puterai/openai/v1/",
api_key="YOUR_PUTER_AUTH_TOKEN",
)
response = client.chat.completions.create(
model="deepseek/deepseek-v3.2-speciale",
messages=[
{"role": "user", "content": "Explain quantum computing in simple terms"}
],
)
print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
-d '{
"model": "deepseek/deepseek-v3.2-speciale",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
Model Card
DeepSeek V3.2-Speciale is a high-compute variant designed exclusively for maximum reasoning accuracy, achieving gold-medal performance in IMO 2025, IOI 2025, and ICPC World Finals. It rivals Gemini 3.0 Pro but requires higher token usage and doesn't support tool calling.
Context Window 164K
tokens
Max Output 164K
tokens
Input Cost $0.4
per million tokens
Output Cost $1.2
per million tokens
Release Date Dec 1, 2025
Model Playground
Try DeepSeek V3.2 Speciale instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How DeepSeek V3.2 Speciale performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 87.1% |
| Humanity's Last Exam Cross-domain reasoning | 26.1% |
| LiveCodeBench Recent coding problems | 89.6% |
| SciCode Scientific programming | 44.0% |
| AIME 2025 Advanced math exam | 96.7% |
| IFBench Instruction following | 63.9% |
| LCR Long-context reasoning | 59.3% |
| Terminal-Bench Hard Agentic terminal tasks | 34.8% |
| τ²-Bench Tool use / agents | 0.0% |
Scores sourced from Artificial Analysis.
Find other DeepSeek models →
DeepSeek V3.2
DeepSeek V3.2 is the December 2025 flagship model featuring DeepSeek Sparse Attention for efficiency and massive reinforcement learning post-training, achieving GPT-5-level performance. It's the first DeepSeek model to integrate thinking directly into tool-use and excels at agentic AI tasks.
ChatDeepSeek V3.2 Exp
DeepSeek V3.2-Exp is the September 2025 experimental predecessor to V3.2, introducing DeepSeek Sparse Attention architecture through continued training on V3.1-Terminus. It served as a testing ground for the sparse attention innovations later refined in V3.2.
ChatDeepSeek V3.1 Terminus
DeepSeek V3.1-Terminus is the September 2025 refined update to V3.1, addressing user-reported issues like language mixing and improving Code Agent and Search Agent capabilities. It represents the final, most stable version of the V3 architecture before V3.2.
Frequently Asked Questions
You can access DeepSeek V3.2 Speciale by DeepSeek through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add DeepSeek V3.2 Speciale to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.
| Price per 1M tokens | |
|---|---|
| Input | $0.4 |
| Output | $1.2 |
DeepSeek V3.2 Speciale was created by DeepSeek and released on Dec 1, 2025.
DeepSeek V3.2 Speciale supports a context window of 164K tokens. For reference, that is roughly equivalent to 328 pages of text.
DeepSeek V3.2 Speciale can generate up to 164K tokens in a single response.
Yes — the DeepSeek V3.2 Speciale API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Get started with Puter.js
Add DeepSeek V3.2 Speciale to your app without worrying about API keys or setup.
Read the Docs View Tutorials