ModelDeprecated

DeepSeek V3

DeepSeek huggingface.co/deepseek-ai/DeepSeek-V3

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...

Open in Graph

data quality66

Updated 5 h ago · first seen 11 Sept 2026

model_01M294WWM5FCNGG1A4WTJSEVHX

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:Hugging Face Hub (public pages, model cards, papers)T2observed 7 h agomedium
Status: Source:Artificial AnalysisT2observed 10 h agomedium
Knowledge cutoff: Source:OpenRouter public model & pricing listingT2observed 12 h agomedium
Model card: huggingface.co/deepseek-ai/DeepSeek-V3
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
Openrouter id: Source:OpenRouter public model & pricing listingT2observed 12 h agomedium

Architecture

Architecture: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
Model type: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
Parameters: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
Tokenizer: Source:OpenRouter public model & pricing listingT2observed 12 h agomedium
Weights dtype: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
File size: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
Library name: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
Pipeline tag: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
Hugging Face repo: Source:OpenRouter public model & pricing listingT2observed 12 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
No
Artificial Analysis · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable

Context window: Source:OpenRouter public model & pricing listingT2observed 9 h agomedium
Max output: Source:OpenRouter public model & pricing listingT2observed 12 h agomedium
Knowledge cutoff: Source:OpenRouter public model & pricing listingT2observed 12 h agomedium
Tokenizer: Source:OpenRouter public model & pricing listingT2observed 12 h agomedium

Benchmarks6

Compare with another model →

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.

Providers & Pricing1

All offers in the price terminal →

Current prices per 1M tokens
Provider	Input / 1M	Output / 1M	Cached in	Batch in / out	Context	Observed	Source
DeepSeek APIdeepseek/deepseek-chat	$0.257	$1.03	—	—	128K	4 h ago	openrouter.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

DeepSeek API

DeepSeek APIfirst observed $1.0311 Sept 2026

Input price · USD / 1M tokens 1 provider

DeepSeek API

DeepSeek APIfirst observed $0.25711 Sept 2026

Hardware fit37

Estimated

3 of 37 device × quantization combinations fit.

Run locally: your machine →

Estimated hardware fit
Hardware	Quantization	Device memory	Est. memory	Fits
Apple M3 Ultra	4bit	—	394.1 GB est.	Yes
Mac Studio (Apple M5 Ultra)	4bit	—	394.1 GB est.	Yes
NVIDIA DGX B200	4bit	1,440 GB	394.1 GB est.	Yes
Apple M2 Ultra	4bit	—	394.1 GB est.	No
Apple M1 Ultra	4bit	—	394.1 GB est.	No
Apple M3 Max	4bit	—	394.1 GB est.	No
Apple M4 Max	4bit	—	394.1 GB est.	No
Mac Studio (Apple M5 Max)	4bit	—	394.1 GB est.	No
MacBook Pro (Apple M5 Max)	4bit	—	394.1 GB est.	No
Apple M2 Max	4bit	—	394.1 GB est.	No
Apple M1 Max	4bit	—	394.1 GB est.	No
Apple M4 Pro	4bit	—	394.1 GB est.	No
Mac mini (Apple M5 Pro)	4bit	—	394.1 GB est.	No
MacBook Pro (Apple M5 Pro)	4bit	—	394.1 GB est.	No
Apple M3 Pro	4bit	—	394.1 GB est.	No
Apple M1 Pro	4bit	—	394.1 GB est.	No
Apple M2 Pro	4bit	—	394.1 GB est.	No
Apple M4	4bit	—	394.1 GB est.	No
iMac (Apple M4)	4bit	—	394.1 GB est.	No
Mac mini (Apple M6)	4bit	—	394.1 GB est.	No
MacBook Air (Apple M5)	4bit	—	394.1 GB est.	No
MacBook Pro (Apple M5)	4bit	—	394.1 GB est.	No
Apple M2	4bit	—	394.1 GB est.	No
Apple M3	4bit	—	394.1 GB est.	No
Apple M1	4bit	—	394.1 GB est.	No
NVIDIA GeForce RTX 3090	4bit	24 GB	394.1 GB est.	No
NVIDIA GeForce RTX 4090	4bit	24 GB	394.1 GB est.	No
NVIDIA GeForce RTX 5090	4bit	32 GB	394.1 GB est.	No
NVIDIA A100 80GB	4bit	80 GB	394.1 GB est.	No
NVIDIA H100 SXM	4bit	80 GB	394.1 GB est.	No
NVIDIA H100 NVL	4bit	94 GB	394.1 GB est.	No
NVIDIA DGX Spark	4bit	128 GB	394.1 GB est.	No
NVIDIA H200	4bit	141 GB	394.1 GB est.	No
NVIDIA H200 NVL	4bit	141 GB	394.1 GB est.	No
NVIDIA B200	4bit	180 GB	394.1 GB est.	No
AMD Instinct MI300X	4bit	192 GB	394.1 GB est.	No
AMD Instinct MI325X	4bit	256 GB	394.1 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

arXiv:2412.19437Active
35

Timeline12

Full timeline →

12 Sept 2026
Context window changedModelDeepSeek V3DeepSeek
DeepSeek V3: context length changed from 128000 to 163840
Context window128K tokens→163.8K tokensopenrouter
openrouter.ai
11 Sept 2026
Benchmark resultModelDeepSeek V3DeepSeek
DeepSeek V3 scores 32.58% on Terminal-Bench
artificial_analysis
artificialanalysis.ai
11 Sept 2026
Benchmark resultModelDeepSeek V3DeepSeek
DeepSeek V3 scores 78.95% on τ²-bench
artificial_analysis
artificialanalysis.ai
11 Sept 2026
Benchmark resultModelDeepSeek V3DeepSeek
DeepSeek V3 scores 49.05% on IFBench
artificial_analysis
artificialanalysis.ai
11 Sept 2026
Benchmark resultModelDeepSeek V3DeepSeek
DeepSeek V3 scores 11.21% on Humanity's Last Exam
artificial_analysis
artificialanalysis.ai
11 Sept 2026
Benchmark resultModelDeepSeek V3DeepSeek
DeepSeek V3 scores 75.05% on GPQA
artificial_analysis
artificialanalysis.ai
11 Sept 2026
Benchmark resultModelDeepSeek V3DeepSeek
DeepSeek V3 scores 16.04 on Artificial Analysis Intelligence Index
artificial_analysis
artificialanalysis.ai
11 Sept 2026
Context window changedModelDeepSeek V3DeepSeek
DeepSeek V3: context length changed from 163840 to 128000
Context window163.8K tokens→128K tokensartificial_analysis
artificialanalysis.ai
11 Sept 2026
Release date changedModelDeepSeek V3DeepSeek
DeepSeek V3: release date changed from 2024-12-25 to 2024-12-26
Release date25 Dec 2024→26 Dec 2024openrouter
openrouter.ai
11 Sept 2026
Release date changedModelDeepSeek V3DeepSeek
DeepSeek V3: release date changed from 2024-12-26 to 2024-12-25
Release date26 Dec 2024→25 Dec 2024huggingface
huggingface.co
26 Dec 2024
New modelModelDeepSeek V3DeepSeek
New model: DeepSeek V3 (DeepSeek)
openrouter
openrouter.ai
11 Sept 2026
Listed by providerModelDeepSeek V3DeepSeek
DeepSeek API lists DeepSeek V3 at $0.2574 in / $1.0287 out per 1M tokens
openrouter
openrouter.ai

Change history40

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

Viewing AI Atlas as of 1 Jan 2025 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

DeepSeek V3 was not yet in AI Atlas on 1 Jan 2025

First seen 11 Sept 2026. Nothing is inferred backwards: no attribute is shown for dates before the first observation.

40 claims · 34 properties

Release daterelease_date5

Claim history for Release date
Value	Valid from → to	Status	Source	Confidence	Extractor
26 Dec 2024	12 Sept 2026 00:05 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic
25 Dec 2024	11 Sept 2026 23:05 UTC → 12 Sept 2026 00:05 UTC	superseded	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic
26 Dec 2024	11 Sept 2026 22:37 UTC → 11 Sept 2026 23:05 UTC	superseded	OpenRouter public model & pricing listingT2	medium	deterministic
25 Dec 2024	11 Sept 2026 21:29 UTC → 11 Sept 2026 22:37 UTC	superseded	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic
26 Dec 2024	11 Sept 2026 21:10 UTC → 11 Sept 2026 21:29 UTC	superseded	OpenRouter public model & pricing listingT2	medium	deterministic

Statusstatus1

Claim history for Status
Value	Valid from → to	Status	Source	Confidence	Extractor
deprecated	11 Sept 2026 22:42 UTC → current	current	Artificial AnalysisT2	medium	deterministic

Opennessopenness1

Claim history for Openness
Value	Valid from → to	Status	Source	Confidence	Extractor
open-weights	11 Sept 2026 21:10 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Architecturearchitecture1

Claim history for Architecture
Value	Valid from → to	Status	Source	Confidence	Extractor
DeepseekV3ForCausalLM	11 Sept 2026 21:29 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Parametersparameter_count1

Claim history for Parameters
Value	Valid from → to	Status	Source	Confidence	Extractor
684.5B	11 Sept 2026 21:10 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Context windowcontext_length3

Claim history for Context window
Value	Valid from → to	Status	Source	Confidence	Extractor
163.8K tokens	12 Sept 2026 00:05 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic
128K tokens	11 Sept 2026 22:42 UTC → 12 Sept 2026 00:05 UTC	superseded	Artificial AnalysisT2	medium	deterministic
163.8K tokens	11 Sept 2026 21:10 UTC → 11 Sept 2026 22:42 UTC	superseded	OpenRouter public model & pricing listingT2	medium	deterministic

Max outputmax_output_tokens1

Claim history for Max output
Value	Valid from → to	Status	Source	Confidence	Extractor
16K tokens	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Knowledge cutoffknowledge_cutoff1

Claim history for Knowledge cutoff
Value	Valid from → to	Status	Source	Confidence	Extractor
Jul 2024	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Modalitiesmodalities1

Claim history for Modalities
Value	Valid from → to	Status	Source	Confidence	Extractor
text	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Input modalitiesmodalities_input1

Claim history for Input modalities
Value	Valid from → to	Status	Source	Confidence	Extractor
text	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Output modalitiesmodalities_output1

Claim history for Output modalities
Value	Valid from → to	Status	Source	Confidence	Extractor
text	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Tokenizertokenizer1

Claim history for Tokenizer
Value	Valid from → to	Status	Source	Confidence	Extractor
DeepSeek	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Quantization formatquant_format1

Claim history for Quantization format
Value	Valid from → to	Status	Source	Confidence	Extractor
fp8	11 Sept 2026 21:29 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

File sizefile_size_gb1

Claim history for File size
Value	Valid from → to	Status	Source	Confidence	Extractor
688.6 GB	11 Sept 2026 21:29 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Hugging Face repohf_repo1

Claim history for Hugging Face repo
Value	Valid from → to	Status	Source	Confidence	Extractor
deepseek-ai/DeepSeek-V3	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Pipeline tagpipeline_tag1

Claim history for Pipeline tag
Value	Valid from → to	Status	Source	Confidence	Extractor
text-generation	11 Sept 2026 21:10 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Model cardmodel_card_url1

Claim history for Model card
Value	Valid from → to	Status	Source	Confidence	Extractor
https://huggingface.co/deepseek-ai/DeepSeek-V3	11 Sept 2026 21:10 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Downloadsmetric.downloads1

Claim history for Downloads
Value	Valid from → to	Status	Source	Confidence	Extractor
1,066,832	11 Sept 2026 21:10 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Likesmetric.likes1

Claim history for Likes
Value	Valid from → to	Status	Source	Confidence	Extractor
4,182	11 Sept 2026 21:10 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Descriptiondescription1

Claim history for Description
Value	Valid from → to	Status	Source	Confidence	Extractor
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Gatedgated1

Claim history for Gated
Value	Valid from → to	Status	Source	Confidence	Extractor
No	11 Sept 2026 21:29 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Hf inference providershf_inference_providers1

Claim history for Hf inference providers
Value	Valid from → to	Status	Source	Confidence	Extractor
deepinfra, novita	11 Sept 2026 21:29 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Is quantizedis_quantized1

Claim history for Is quantized
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 21:29 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Last modifiedlast_modified1

Claim history for Last modified
Value	Valid from → to	Status	Source	Confidence	Extractor
2025-03-27T04:01:45+00:00	11 Sept 2026 21:10 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Library namelibrary_name1

Claim history for Library name
Value	Valid from → to	Status	Source	Confidence	Extractor
transformers	11 Sept 2026 21:29 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Downloads all timemetric.downloads_all_time1

Claim history for Downloads all time
Value	Valid from → to	Status	Source	Confidence	Extractor
20,549,319	11 Sept 2026 21:29 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Model typemodel_type1

Claim history for Model type
Value	Valid from → to	Status	Source	Confidence	Extractor
deepseek_v3	11 Sept 2026 21:29 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Openrouter idopenrouter_id1

Claim history for Openrouter id
Value	Valid from → to	Status	Source	Confidence	Extractor
deepseek/deepseek-chat	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Reasoningreasoning1

Claim history for Reasoning
Value	Valid from → to	Status	Source	Confidence	Extractor
No	11 Sept 2026 22:42 UTC → current	current	Artificial AnalysisT2	medium	deterministic

Structured outputstructured_output1

Claim history for Structured output
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Supported parameterssupported_parameters1

Claim history for Supported parameters
Value	Valid from → to	Status	Source	Confidence	Extractor
frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Tagstags1

Claim history for Tags
Value	Valid from → to	Status	Source	Confidence	Extractor
transformers, safetensors, deepseek_v3, text-generation, custom_code, fp8	11 Sept 2026 21:29 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Tool callingtool_calling1

Claim history for Tool calling
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Weights dtypeweights_dtype1

Claim history for Weights dtype
Value	Valid from → to	Status	Source	Confidence	Extractor
BF16, F32, F8_E4M3	11 Sept 2026 21:29 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

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

Source tiers

T235

Freshest observation

5 h ago

Conflicts

None

Source documents 5

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
OpenRouter public model & pricing listing	openrouter.ai/api/v1/models	catalogue	T2· Quality secondary	4 h ago	6
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/deepseek-ai/DeepSeek-V3/raw/main/README.md	model_card	T2· Quality secondary	5 h ago	1
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/deepseek-ai/DeepSeek-V3	model_page	T2· Quality secondary	6 h ago	4
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/models?author=deepseek-ai&p=0&sort=downloads	listing	T2· Quality secondary	6 h ago	6
Artificial Analysis	artificialanalysis.ai/leaderboards/models	leaderboard	T2· Quality secondary	10 h ago	1

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

Data quality (66/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →