DeepSeek V3.2

About DeepSeek V3.2

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

DeepSeek Model Lineup

Compare all models from DeepSeek to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Qwen3 VL 30B A3B Instruct

Alibaba Qwen

Input: $0.13

Output: $0.52

Context: 262k

Qwen3 VL 30B A3B Instruct

Alibaba Qwen

Input: $0.13

Output: $0.52

Context: 262k

Qwen3 30B A3B Instruct 2507

Alibaba Qwen

Input: $0.13

Output: $0.52

Context: 262k

Olmo 3.1 32B Think

Allen AI

Input: $0.15

Output: $0.50

Context: 66k

💡 Cheaper Alternatives

Same Brand (DeepSeek)

Cross Brand

🚀 Quick Start

Get started with DeepSeek V3.2 API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v3.2-20251201",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision