Skip to content

DeepSeek · Chat

community

DeepSeek 🇨🇳ChatDeepSeek family
Market median price
$0.475 blended / 1M
Max context
64K
Listings
2
Providers
2

Evidence and sources

Source: LiteLLM dataPrimary data from LiteLLM

Advantages and trade-offs

Compared with 10 representative chat models
We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 6 maker's prices; 1 market median price.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

Function calling

Listings

 302aideepseek/deepseek-v3/communitySource: 302.ai data64K$0.30$1.00
 Novita AInovita/deepseek/deepseek-v3/communitySource: LiteLLM data64K$0.89$0.89

Benchmarks

No benchmark scores yet.

Around the web

  • 🚀 Introducing DeepSeek-V3 | DeepSeek API Docs
    Skip to main content DeepSeek API Docs Logo DeepSeek API Docs Logo DeepSeek API Docs …Skip to main content DeepSeek API Docs Logo DeepSeek API Docs Logo DeepSeek API Docs English English 中文(中国) DeepSeek Platform News Introducing DeepSeek-V3 2024/12/26 On this page 🚀 Introducing DeepS…

    api-docs.deepseek.com

  • deepseek-ai/DeepSeek-V3 · Hugging Face
    We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B …We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, Deep…

    huggingface.co

  • DeepSeek-V3/README.md at main · deepseek-ai/DeepSeek-V3 · GitHub
    We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B …We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, Deep…

    github.com

  • DeepSeek V3 — Megatron Bridge - NVIDIA Documentation Hub
    DeepSeek-V3 is a large-scale Mixture-of-Experts (MoE) language model with 671B total parameters and 37B activated …DeepSeek-V3 is a large-scale Mixture-of-Experts (MoE) language model with 671B total parameters and 37B activated parameters per token. It features Multi-head Latent Attention (MLA), innovative load …

    docs.nvidia.com

  • GitHub - deepseek-ai/DeepSeek-V3 · GitHub
    deepseek-ai/DeepSeek-V3 Page: GitHub repository URL: https://github.com/deepseek-ai/DeepSeek-V3 Stars: 104,185 Forks: 16,725 License: MIT license Default branch: …deepseek-ai/DeepSeek-V3 Page: GitHub repository URL: https://github.com/deepseek-ai/DeepSeek-V3 Stars: 104,185 Forks: 16,725 License: MIT license Default branch: main Created: 2024-12-26T09:52:40.000…

    github.com

  • [2412.19437] DeepSeek-V3 Technical Report - arXiv.org
    To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE …To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2. Further…

    arxiv.org

  • DeepSeek-V3 Technical Report
    arXiv is now an independent nonprofit! Learn more × arXiv logo Back to arXiv Why …arXiv is now an independent nonprofit! Learn more × arXiv logo Back to arXiv Why HTML? Report Issue Back to Abstract Download PDF License: arXiv.org perpetual non-exclusive license arXiv:2412.19437v2…

    arxiv.org

  • DeepSeek-V3 Technical Report - arXiv.org
    DeepSeek-V3 Technical Report DeepSeek-AI research@deepseek.com Abstract Following DeepSeek-V2, we adopt MLA and DeepSeekMoE for efficient …DeepSeek-V3 Technical Report DeepSeek-AI research@deepseek.com Abstract Following DeepSeek-V2, we adopt MLA and DeepSeekMoE for efficient inference and economical training. strategy (Wang et al., 202…

    arxiv.org

  • DeepSeek-V3 - Hugging Face
    The DeepSeek-V3 model was proposed in DeepSeek-V3 Technical Report by DeepSeek-AI Team. The abstract from …The DeepSeek-V3 model was proposed in DeepSeek-V3 Technical Report by DeepSeek-AI Team. The abstract from the paper is the following: We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) languag…

    huggingface.co

  • DeepSeek-V3 - Hugging Face
    The DeepSeek-V3 model was proposed in DeepSeek-V3 Technical Report by DeepSeek-AI Team. The abstract from …The DeepSeek-V3 model was proposed in DeepSeek-V3 Technical Report by DeepSeek-AI Team. The abstract from the paper is the following: We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) languag…

    huggingface.co

Also known as: deepseek/deepseek-v3/community, novita/deepseek/deepseek-v3/community

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works