Skip to content

    DeepSeek V4 Flash

    Chat

    DeepSeek-V4-Flash

    Get an API key Try it

    DeepSeek V4 Flash on FlexAI: DeepSeek LLM, MIT license, served via the OpenAI-compatible Token Factory at the live market-tracked rate.

    Recommended for

    Research agents · as Summarize

    Pricing

    Input

    $0.082 / M tokens

    Output

    $0.164 / M tokens

    Pricing source

    Context

    1.0M tokens

    API endpoint

    /v1/chat/completions

    Compatibility

    OpenAI

    Parameters

    284B MoE (13B active)

    License

    MIT

    Hardware

    8× H100

    Quantization

    FP8

    Estimate your monthly cost

    M tokens
    M tokens
    10M × $0.082/M input$0.82
    2M × $0.164/M output$0.33
    Estimated monthly cost$1.15

    Estimate only, at the current market-tracked rate. Usage-based; no minimums.

    Get an API key

    Quick Start

    from openai import OpenAI

client = OpenAI(
    base_url="https://tokens.flex.ai/v1",
    api_key="your-api-key",
)

response = client.chat.completions.create(
    model="DeepSeek-V4-Flash",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(response.choices[0].message.content)
    Get an API key Run this model on a dedicated endpoint