Model Information

Display Name: DeepSeek V3.1

API Model ID: deepseek-ai/deepseek-v3.1

Category: Text To Text

Description: DeepSeek V3.1 is a powerful reasoning model with extended training phases and excellent cost efficiency. **Key Features:** - 128K token context window - 32K max output tokens - Reasoning mode (can be toggled) - Structured outputs (JSON) - Prompt caching for cost savings - FP8 quantization **Capabilities:** - Advanced reasoning and math - Long-form content generation - Code generation - JSON mode for structured outputs - Multi-turn conversations **Best For:** - Complex reasoning tasks - Long document generation - Cost-effective inference - Tasks requiring extended outputs **Technical Specs:** - Based on DeepSeek-V3.1-Base - Extended training phases - UE8M0 FP8 scale format

Context Window: 128,000 tokens

Max Output: 32,768 tokens

How to Use This Model

To use DeepSeek V3.1 via the HInow.ai API, use the model ID: deepseek-ai/deepseek-v3.1

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-v3.1",
  "messages": [
    {"role": "user", "content": "Your message here"}
  ]
}
              

Pricing

• input: $0.28
• output: $1.07

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 (1-32768) (Options: 512, 1024, 2048, 4096, 8192, 16384, 32768)
• 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-v3.1"

Featured: Yes

Documentation: https://hinow.ai/models/deepseek-ai/deepseek-v3.1

API Endpoint: https://api.hinow.ai/v1