DeepSeek-V3.1 Available on Novita AI: Enhanced Context Window & Revolutionary Hybrid Thinking Mode

DeepSeek-V3.1 is now available on the Novita AI platform, bringing DeepSeek’s groundbreaking AI capabilities to developers and businesses through our developer-friendly infrastructure. This latest release from DeepSeek represents a significant advancement in AI model architecture, introducing a revolutionary hybrid thinking system that sets it apart from previous generations.

Whether you’re developing AI applications, building automation solutions, or exploring advanced AI capabilities, DeepSeek-V3.1 on Novita AI simplifies the development process with our optimized infrastructure and easy integration options.

Current pricing on Novita AI: 163840 Context, $0.55/1M input tokens, $1.66/1M output tokens

What is DeepSeek V3.1?

DeepSeek V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. Compared to the previous version, this upgrade brings improvements in multiple aspects:

• Hybrid thinking mode: One model supports both thinking mode and non-thinking mode by changing the chat template.
• Smarter tool calling: Through post-training optimization, the model’s performance in tool usage and agent tasks has significantly improved.
• Higher thinking efficiency: DeepSeek-V3.1-Think achieves comparable answer quality to DeepSeek-R1-0528, while responding more quickly.

DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. DeepSeek has expanded their dataset by collecting additional long documents and substantially extending both training phases. The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens. Additionally, DeepSeek-V3.1 is trained using the UE8M0 FP8 scale data format to ensure compatibility with microscaling data formats.

This 671B parameter model (with 37B activated parameters) features an enhanced 128K context window, designed to handle various tasks and deliver consistent results across different applications.

Model Specifications

• Total Parameters: 671B
• Activated Parameters: 37B
• Context Length: 128K tokens
• Training Format: UE8M0 FP8 scale data format
• License: MIT License
• Architecture: Hybrid thinking/non-thinking mode support

Performance Benchmarks

DeepSeek V3.1 demonstrates exceptional performance across multiple domains:

Getting Started with DeepSeek V3.1 on Novita AI Platform

Accessing DeepSeek V3.1 through Novita AI offers multiple pathways tailored to different technical expertise levels and use cases. Whether you’re a business user exploring AI capabilities or a developer building production applications, Novita AI provides the tools you need.

Use the Playground (Available Now – No Coding Required)

• Instant Access: Sign up and start experimenting with DeepSeek V3.1 models in seconds
• Interactive Interface: Test prompts and visualize outputs in real-time
• Model Comparison: Compare DeepSeek V3.1 with other leading models for your specific use case

The playground enables you to test various prompts and see immediate results without any technical setup. Perfect for prototyping, testing ideas, and understanding model capabilities before full implementation.

Integrate via API (Live and Ready – For Developers)

Connect DeepSeek V3.1 to your applications with Novita AI’s unified REST API.

Option 1: Direct API Integration (Python Example)

from openai import OpenAI
  
client = OpenAI(
    base_url="https://api.novita.ai/openai",
    api_key="session_nIoDgfR3KQUuYZQEy7Lkz6Tn7gGQI1XR7fWLdey7IKmv-fgHtCNRN5uc5O6t2TNjo-KXbZNR58dpuYErRi7gcg==",
)

model = "deepseek/deepseek-v3.1"
stream = True # or False
max_tokens = 81920
system_content = "Be a helpful assistant"
temperature = 1
top_p = 1
min_p = 0
top_k = 50
presence_penalty = 0
frequency_penalty = 0
repetition_penalty = 1
response_format = { "type": "text" }

chat_completion_res = client.chat.completions.create(
    model=model,
    messages=[
        {
            "role": "system",
            "content": system_content,
        },
        {
            "role": "user",
            "content": "Hi there!",
        }
    ],
    stream=stream,
    max_tokens=max_tokens,
    temperature=temperature,
    top_p=top_p,
    presence_penalty=presence_penalty,
    frequency_penalty=frequency_penalty,
    response_format=response_format,
    extra_body={
      "top_k": top_k,
      "repetition_penalty": repetition_penalty,
      "min_p": min_p
    }
  )

if stream:
    for chunk in chat_completion_res:
        print(chunk.choices[0].delta.content or "", end="")
else:
    print(chat_completion_res.choices[0].message.content)
  
  

Option 2: Multi-Agent Workflows with OpenAI Agents SDK

Build sophisticated multi-agent systems leveraging DeepSeek-V3.1’s dual-mode capabilities:

• Plug-and-Play Integration: Use DeepSeek V3.1 in any OpenAI Agents workflow
• Advanced Agent Capabilities: Support for handoffs, routing, and tool integration
• Scalable Architecture: Design agents that leverage DeepSeek V3.1’s capabilities

Connect with Third-Party Platforms

Development Tools: Seamlessly integrate with popular IDEs and development environments like Cursor, Trae, Qwen Code and Cline through OpenAI-compatible APIs and Anthropic-compatible APIs.

Orchestration Frameworks: Connect with LangChain, Dify, CrewAI, Langflow, and other AI orchestration platforms using official connectors.

Hugging Face Integration: Novita AI serves as an official inference provider of Hugging Face, ensuring broad ecosystem compatibility.

Conclusion

DeepSeek-V3.1 on Novita AI provides developers and organizations with access to DeepSeek’s most advanced AI capabilities through our reliable, scalable platform. The revolutionary hybrid thinking system, combined with enhanced tool calling and superior performance benchmarks, makes this the most advanced AI model available for practical applications.

Start exploring DeepSeek-V3.1‘s groundbreaking dual-mode capabilities on our platform today and discover how next-generation AI can transform your projects with both lightning-fast responses and deep, thoughtful reasoning when you need it most.

Novita AI is an AI cloud platform that offers developers an easy way to deploy AI models using our simple API, while also providing the affordable and reliable GPU cloud for building and scaling.