DeepSeek V3.2
Model Information
Display Name: DeepSeek V3.2
API Model ID: deepseek-ai/deepseek-v3.2
Category: Text To Text
Description: DeepSeek V3.2 is an advanced large language model with exceptional reasoning capabilities and cost efficiency. **Key Features:** - 163K+ token context window - Function calling and tool use - Structured outputs (JSON) - Reasoning mode (can be toggled) - Prompt caching for cost savings - FP4 quantization for efficiency **Capabilities:** - Advanced reasoning and math - Code generation and debugging - Function/tool calling - JSON mode for structured outputs - Multi-turn conversations **Best For:** - Complex reasoning tasks - Code assistance - Cost-effective high-volume use - Tasks requiring long context **Technical Specs:** - Quantization: FP4 - Caching: 50% discount on cached inputs
Context Window: 163,840 tokens
Max Output: 8,192 tokens
How to Use This Model
To use DeepSeek V3.2 via the HInow.ai API, use the model ID: deepseek-ai/deepseek-v3.2
API Request Example (Chat/Text)
POST https://api.hinow.ai/v1/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
{
"model": "deepseek-ai/deepseek-v3.2",
"messages": [
{"role": "user", "content": "Your message here"}
]
}
Pricing
- input: $0.37
- output: $0.75
Available Parameters
- temperature: Controls randomness (0-2). Default: 0.7 (Options: 0, 0.3, 0.5, 0.7, 1.0, 1.5, 2.0)
- top_p: Nucleus sampling (0-1). Default: 0.9 (Options: 0.1, 0.5, 0.7, 0.9, 0.95, 1.0)
- max_tokens: Max tokens to generate (1-8192) (Options: 256, 512, 1024, 2048, 4096, 8192)
- repetition_penalty: Reduce repetition (0.01-5). Default: 1 (Options: 1.0, 1.1, 1.2, 1.5, 2.0)
- response_format: Output format (Options: text, json_object, json_schema)
Quick Reference
To use this model, set: "model": "deepseek-ai/deepseek-v3.2"
Featured: Yes
Documentation: https://hinow.ai/models/deepseek-ai/deepseek-v3.2
API Endpoint: https://api.hinow.ai/v1
