Doubleword
    DeepSeek
    New
    Open weights

    DeepSeek V4.1 Flash 1017

    DeepSeek V4.1 Flash 1017 is a multimodal model for coding, reasoning, tool use, and long-context analysis. It accepts text and image inputs and generates text, with thinking and non-thinking modes, tool calling, and structured outputs. It supports a context window of up to 1,048,576 tokens across input and output.

    deepseek-ai/DeepSeek-V4.1-Flash-1017

    Context window

    1M

    1,048,576 tokens across input and output

    Intelligence

    45

    Artificial Analysis Intelligence Index v4.3

    Input

    Text + Image

    Text output on Doubleword

    Released

    Oct 2026

    DeepSeek · Generation

    Coding
    Thinking & non-thinking
    Tool calling
    Structured outputs
    Vision

    API pricing

    USD per 1M tokens.

    TierInput / 1MOutput / 1M
    Batch (24 hours)$0.08$0.30
    Async$0.12$0.48
    Realtime$0.15$0.60

    Run with the OpenAI SDK

    Async inference through the OpenAI-compatible API.

    Python
    from openai import OpenAI
    
    client = OpenAI(
        api_key="your-api-key-here",
        base_url="https://api.doubleword.ai/v1",
    )
    
    response = client.chat.completions.create(
        model="deepseek-ai/DeepSeek-V4.1-Flash-1017",
        messages=[{"role": "user", "content": "Analyze this repository and propose a refactor plan."}],
        extra_body={"service_tier": "flex"},
    )
    
    print(response.choices[0].message.content)
    Read documentation