Skip to content
AI Atlas
ModelAnnounced

DeepSeek V3 0324

DeepSeekfamily · DeepSeek-V3huggingface.co/deepseek-ai/DeepSeek-V3-0324

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...

Open in Graph
data quality68

Updated 3 h ago · first seen 11 Sept 2026

model_01M294WWHTCRTKN8AHRV7H4SBP

Overview

Identity

Identity block not returned by the API for this entity.

Openness

Openness not classified yet — no sourced evidence to place this model in the ontology.

Key facts

Release date

Source:OpenRouter public model & pricing listingT2observed 10 h agomedium

Status

Source:DeepSeek — site & API docsT2observed 11 h agomediumLLM-extracted

Version

Source:DeepSeek — site & API docsT2observed 11 h agomediumLLM-extracted

Knowledge cutoff

Source:OpenRouter public model & pricing listingT2observed 10 h agomedium

Repository

Source:DeepSeek — site & API docsT2observed 11 h agomediumLLM-extracted

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 10 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 h agomedium

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 10 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 h agomedium

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 h agomedium

Hugging Face repo

Source:OpenRouter public model & pricing listingT2observed 10 h agomedium

Capabilities

Modalities

Modalities
text
Input
text
Output
text

Capabilities

  • Tool calling

    Yes

    OpenRouter public model & pricing listing · T2

  • Structured output

    Yes

    OpenRouter public model & pricing listing · T2

  • Reasoning

    Yes

    DeepSeek — site & API docs · T2

  • Vision

    Unavailable

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:OpenRouter public model & pricing listingT2observed 7 h agomedium

Max output

Source:OpenRouter public model & pricing listingT2observed 10 h agomedium

Knowledge cutoff

Source:OpenRouter public model & pricing listingT2observed 10 h agomedium

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 10 h agomedium

Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric

No benchmark results recorded

Results appear when a tier 1–3 source publishes them; we never copy scores without a source.
Current prices per 1M tokens
ProviderInput / 1MOutput / 1MCached inBatch in / outContextObservedSource
DeepSeek APIdeepseek/deepseek-chat-v3-0324$0.25$1163.8K2 h agoopenrouter.aiT2

USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 1 provider

Output price history of DeepSeek V3 0324$0$0.20$0.40$0.60$0.80$1$1.2Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26DeepSeek API: first observed → $1 · 11 Sept 2026
  • DeepSeek API
  • DeepSeek APIfirst observed $111 Sept 2026

Input price · USD / 1M tokens 1 provider

Input price history of DeepSeek V3 0324$0$0.10$0.20$0.30Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26DeepSeek API: first observed → $0.25 · 11 Sept 2026
  • DeepSeek API
  • DeepSeek APIfirst observed $0.2511 Sept 2026

Hardware fit37

Estimated

3 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit394.1 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit394.1 GB est.Yes
NVIDIA DGX B2004bit1,440 GB394.1 GB est.Yes
Apple M2 Ultra4bit394.1 GB est.No
Apple M1 Ultra4bit394.1 GB est.No
Apple M3 Max4bit394.1 GB est.No
Apple M4 Max4bit394.1 GB est.No
Mac Studio (Apple M5 Max)4bit394.1 GB est.No
MacBook Pro (Apple M5 Max)4bit394.1 GB est.No
Apple M2 Max4bit394.1 GB est.No
Apple M1 Max4bit394.1 GB est.No
Apple M4 Pro4bit394.1 GB est.No
Mac mini (Apple M5 Pro)4bit394.1 GB est.No
MacBook Pro (Apple M5 Pro)4bit394.1 GB est.No
Apple M3 Pro4bit394.1 GB est.No
Apple M1 Pro4bit394.1 GB est.No
Apple M2 Pro4bit394.1 GB est.No
Apple M44bit394.1 GB est.No
iMac (Apple M4)4bit394.1 GB est.No
Mac mini (Apple M6)4bit394.1 GB est.No
MacBook Air (Apple M5)4bit394.1 GB est.No
MacBook Pro (Apple M5)4bit394.1 GB est.No
Apple M24bit394.1 GB est.No
Apple M34bit394.1 GB est.No
Apple M14bit394.1 GB est.No
NVIDIA GeForce RTX 30904bit24 GB394.1 GB est.No
NVIDIA GeForce RTX 40904bit24 GB394.1 GB est.No
NVIDIA GeForce RTX 50904bit32 GB394.1 GB est.No
NVIDIA A100 80GB4bit80 GB394.1 GB est.No
NVIDIA H100 SXM4bit80 GB394.1 GB est.No
NVIDIA H100 NVL4bit94 GB394.1 GB est.No
NVIDIA DGX Spark4bit128 GB394.1 GB est.No
NVIDIA H2004bit141 GB394.1 GB est.No
NVIDIA H200 NVL4bit141 GB394.1 GB est.No
NVIDIA B2004bit180 GB394.1 GB est.No
AMD Instinct MI300X4bit192 GB394.1 GB est.No
AMD Instinct MI325X4bit256 GB394.1 GB est.No
Assumptions (6)
  • Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead.
  • bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
  • KV cache approximated at 0.5 GB per 8 192 tokens of context, independent of architecture (GQA/MLA models need less).
  • A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
  • Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
  • Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).

Papers1

Change history

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.
1 claims · 1 propertiesShow all properties

Model typemodel_type1

Claim history for Model type
ValueValid from → toStatusSourceConfidenceExtractor
deepseek_v3currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Provenance

Attributed facts

39

Source tiers

T239

Freshest observation

3 h ago

Conflicts

None

Source documents 8

Source documents
SourceDocumentTypeTierLast observedSnapshots
DeepSeek — site & API docsapi-docs.deepseek.com/news/news250325 newsT1· Official11 h ago1
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary2 h ago6
Hugging Face Hub (public pages, model cards, papers)huggingface.co/deepseek-ai/DeepSeek-V3-0324/raw/main/README.md model_cardT2· Quality secondary4 h ago1
Hugging Face Hub (public pages, model cards, papers)huggingface.co/deepseek-ai/DeepSeek-V3-0324 model_pageT2· Quality secondary4 h ago4
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=deepseek-ai&p=0&sort=downloads listingT2· Quality secondary5 h ago6
SWE-bench leaderboardsswebench.com/ leaderboardT2· Quality secondary9 h ago1
Artificial Analysisartificialanalysis.ai/leaderboards/models leaderboardT2· Quality secondary9 h ago1
Aider polyglot leaderboard (data file on GitHub)raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml leaderboardT2· Quality secondary9 h ago1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (68/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →