DeepSeek-V3.2 is a large language model optimized for high computational efficiency and strong tool-use reasoning. It features DeepSeek Sparse Attention (DSA), a mechanism that lowers training and inference costs while maintaining quality in long-context tasks. A scalable reinforcement learning post-training framework further enhances reasoning, achieving performance comparable to GPT-5 and earning top results on the 2025 IMO and IOI. V3.2 also leverages large-scale agentic task synthesis to improve reasoning in practical tool-use scenarios, boosting its generalization and compliance in interactive environments.
Pricing
Pay-as-you-go rates for this model. More details can be found here.
Input Tokens (1M)
$0.14
Cached Input Tokens (1M)
$0.01
Output Tokens (1M)
$0.21
Capabilities
Input Modalities
Output Modalities
Supported Parameters
Available parameters for API requests
Usage Analytics
Token usage of this model on our platform
Throughput
Time-To-First-Token (TTFT)
Code Example
Example code for using this model through our API with Python (OpenAI SDK) or cURL. Replace placeholders with your API key and model ID.
Basic request example. Ensure API key permissions. For more details, see our documentation.
from openai import OpenAI
client = OpenAI(
base_url="https://api.naga.ac/v1",
api_key="YOUR_API_KEY",
)
resp = client.chat.completions.create(
model="deepseek-v3.2",
messages=[
{{"role": "user", "content": "What's 2+2?"}}
],
temperature=0.2,
)
print(resp.choices[0].message.content)