Skip to content

DeepSeek V3.1

deepseek/deepseek-chat-v3.1

context
164K
modalities
text → text
capabilities
Tool use, Reasoning, Structured output, Low cost

Overview

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

Providers

Access method depends on provider and account setup.

Pricing

  • AtlasCloud

    input / 1M
    $0.30
    output / 1M
    $1.00
  • CoreWeave

    input / 1M
    $0.55
    output / 1M
    $1.65
  • DeepInfra

    input / 1M
    $0.25
    output / 1M
    $0.95
  • Google

    input / 1M
    $0.60
    output / 1M
    $1.70
  • Mara

    input / 1M
    $0.60
    output / 1M
    $1.70
  • Novita

    input / 1M
    $0.27
    output / 1M
    $1.00
  • SambaNova

    input / 1M
    $0.65
    output / 1M
    $1.50
  • SiliconFlow

    input / 1M
    $0.27
    output / 1M
    $1.00

Use this model through Nautili

Route requests to DeepSeek V3.1 through your Nautili gateway using a supported SDK or the Nautili SDK.

Connect your stack to Nautili

Route across supported providers through one control layer.