DeepSeek V4 Pro 0423
DeepSeekfamily · DeepSeekhuggingface.co/deepseek-ai/DeepSeek-V4-Pro
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
Updated 1 h ago · first seen 11 Sept 2026
model_01M294WW0GPKNDS16RSPXC5YCE
Overview
Identity
- Canonical model
- Yesidentity confidence: mediumOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
- Official checkpoints
- official_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
- Artifacts
- None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
- Provider deployments
- 2
- API aliases
- deepseek/deepseek-v4-proIdentifiers under which providers and evaluators refer to this model.
- Folded evaluation variants
- 0Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.
Openness
Open weights— weights downloadable under MIT; commercial use allowed; redistribution allowed; derivatives allowed; 4 dimensions unknown.
Weights downloadable under a permissive or Creative Commons licence allowing commercial use; code or data may be missing.
Weights
Yes
Inference code
—
Training code
—
Training data
—
Dataset
—
Commercial use
Yes
Redistribution
Yes
Derivatives
Yes
Licence: MIT License (permissive · SPDX MIT · stated as “mit”)
dimensions marked null are unknown, not false
Key facts
- Release date
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Openrouter id
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
Architecture
- Architecture
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Model type
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Parameters
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Tokenizer
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
- Weights dtype
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- File size
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Library name
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Pipeline tag
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Hugging Face repo
Source:OpenRouter public model & pricing listingT2observed 5 d 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
OpenRouter public model & pricing listing · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
- Max output
Source:OpenRouter public model & pricing listingT2observed 4 d agomedium
- Tokenizer
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
Providers & Pricing2
All offers in the price terminal →USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →
Price history
Output price · USD / 1M tokens 2 providers
- DeepSeek API
- OpenRouter
- OpenRouter$1.46 → $3.212 Sept 2026
- OpenRouter$1.52 → $1.4612 Sept 2026
- OpenRouter$1.54 → $1.5212 Sept 2026
- OpenRouter$1.56 → $1.5412 Sept 2026
- OpenRouter$1.6 → $1.5612 Sept 2026
- OpenRouter$1.62 → $1.612 Sept 2026
- OpenRouter$1.6 → $1.6212 Sept 2026
- OpenRouter$1.62 → $1.612 Sept 2026
- OpenRouterfirst observed $1.6212 Sept 2026
- DeepSeek API$1.66 → $1.6412 Sept 2026
- DeepSeek API$1.7 → $1.6612 Sept 2026
- DeepSeek API$1.68 → $1.712 Sept 2026
Input price · USD / 1M tokens 2 providers
- DeepSeek API
- OpenRouter
- OpenRouter$0.728 → $1.612 Sept 2026
- OpenRouter$0.759 → $0.72812 Sept 2026
- OpenRouter$0.769 → $0.75912 Sept 2026
- OpenRouter$0.779 → $0.76912 Sept 2026
- OpenRouter$0.799 → $0.77912 Sept 2026
- OpenRouter$0.809 → $0.79912 Sept 2026
- OpenRouter$0.799 → $0.80912 Sept 2026
- OpenRouter$0.809 → $0.79912 Sept 2026
- OpenRouterfirst observed $0.80912 Sept 2026
- DeepSeek API$0.829 → $0.81912 Sept 2026
- DeepSeek API$0.85 → $0.82912 Sept 2026
- DeepSeek API$0.84 → $0.8512 Sept 2026
Hardware fit37
Assumptions (7)
- Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead (or the observed artifact file size when one is recorded).
- bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
- KV cache: 2 × layers × kv_heads × head_dim × 2 bytes × context × batch when the architecture is known; otherwise 0.5 GB per 8 192 tokens (× batch), 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).
- Multi-GPU: device memories are summed; interconnect bandwidth, tensor-parallel replication and pipeline bubbles are not modelled.
Versions & Artifacts0
Version history
Max output1 change
11 Sept 2026→12 Sept 2026current
Context windowfirst observation only
11 Sept 2026current
Licensefirst observation only
11 Sept 2026current
Opennessfirst observation only
11 Sept 2026current
Parametersfirst observation only
11 Sept 2026current
Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.
Artifacts 0
No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.
Papers1
- arXiv:2606.19348Active35
Timeline16
Full timeline →OpenRouter changed pricing for DeepSeek V4 Pro 0423: $0.72819 in / $1.45638 out per 1M tokens → $1.6 in / $3.2 out per 1M tokens
$0.728 in / $1.46 out→$1.6 in / $3.2 outopenrouterDeepSeek V4 Pro 0423: max output tokens changed from 384000 to 393216
Max output384K tokens→393.2K tokensopenrouterOpenRouter changed pricing for DeepSeek V4 Pro 0423: $0.75864 in / $1.51728 out per 1M tokens → $0.72819 in / $1.45638 out per 1M tokens
$0.759 in / $1.52 out→$0.728 in / $1.46 outopenrouterOpenRouter changed pricing for DeepSeek V4 Pro 0423: $0.768732 in / $1.53746 out per 1M tokens → $0.75864 in / $1.51728 out per 1M tokens
$0.769 in / $1.54 out→$0.759 in / $1.52 outopenrouterOpenRouter changed pricing for DeepSeek V4 Pro 0423: $0.778824 in / $1.55765 out per 1M tokens → $0.768732 in / $1.53746 out per 1M tokens
$0.779 in / $1.56 out→$0.769 in / $1.54 outopenrouterOpenRouter changed pricing for DeepSeek V4 Pro 0423: $0.799182 in / $1.59836 out per 1M tokens → $0.778824 in / $1.55765 out per 1M tokens
$0.799 in / $1.6 out→$0.779 in / $1.56 outopenrouterOpenRouter changed pricing for DeepSeek V4 Pro 0423: $0.799182 in / $1.59836 out per 1M tokens → $0.809274 in / $1.61855 out per 1M tokens
$0.799 in / $1.6 out→$0.809 in / $1.62 outopenrouterOpenRouter changed pricing for DeepSeek V4 Pro 0423: $0.809274 in / $1.61855 out per 1M tokens → $0.799182 in / $1.59836 out per 1M tokens
$0.809 in / $1.62 out→$0.799 in / $1.6 outopenrouterOpenRouter lists DeepSeek V4 Pro 0423 at $0.809274 in / $1.61855 out per 1M tokens
openrouterDeepSeek API changed pricing for DeepSeek V4 Pro 0423: $0.829458 in / $1.65892 out per 1M tokens → $0.819366 in / $1.63873 out per 1M tokens
$0.829 in / $1.66 out→$0.819 in / $1.64 outopenrouterDeepSeek API changed pricing for DeepSeek V4 Pro 0423: $0.849816 in / $1.69963 out per 1M tokens → $0.829458 in / $1.65892 out per 1M tokens
$0.85 in / $1.7 out→$0.829 in / $1.66 outopenrouterDeepSeek API changed pricing for DeepSeek V4 Pro 0423: $0.839724 in / $1.67945 out per 1M tokens → $0.849816 in / $1.69963 out per 1M tokens
$0.84 in / $1.68 out→$0.85 in / $1.7 outopenrouterDeepSeek API changed pricing for DeepSeek V4 Pro 0423: $0.947778 in / $1.89556 out per 1M tokens → $0.839724 in / $1.67945 out per 1M tokens
$0.948 in / $1.9 out→$0.84 in / $1.68 outopenrouterDeepSeek API changed pricing for DeepSeek V4 Pro 0423: $0.859908 in / $1.71982 out per 1M tokens → $0.947778 in / $1.89556 out per 1M tokens
$0.86 in / $1.72 out→$0.948 in / $1.9 outopenrouterDeepSeek V4 Pro 0423: release date changed from 2026-04-22 to 2026-04-24
Release date22 Apr 2026→24 Apr 2026openrouterDeepSeek V4 Pro 0423: release date changed from 2026-04-24 to 2026-04-22
Release date24 Apr 2026→22 Apr 2026huggingface
Change history79
Viewing AI Atlas as of 18 Jun 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.
Back to today →DeepSeek V4 Pro 0423 was not yet in AI Atlas on 18 Jun 2026
Release daterelease_date6
Opennessopenness1
Licenselicense1
Architecturearchitecture1
Parametersparameter_count1
Context windowcontext_length1
Max outputmax_output_tokens2
Modalitiesmodalities1
Input modalitiesmodalities_input1
Output modalitiesmodalities_output1
Tokenizertokenizer1
Quantization formatquant_format1
File sizefile_size_gb1
Hugging Face repohf_repo1
Pipeline tagpipeline_tag1
Model cardmodel_card_url1
Downloadsmetric.downloads6
Likesmetric.likes22
Accessaccess1
Artifact kindartifact_kind1
Commercial use allowedcommercial_use_allowed1
Derivatives allowedderivatives_allowed1
Descriptiondescription1
Gatedgated1
Hf inference providershf_inference_providers1
Is quantizedis_quantized1
Last modifiedlast_modified1
Library namelibrary_name1
License keylicense_key1
License rawlicense_raw1
Downloads all timemetric.downloads_all_time6
Model typemodel_type1
Openrouter idopenrouter_id1
Openrouter listed atopenrouter_listed_at1
Reasoningreasoning1
Redistribution allowedredistribution_allowed1
Structured outputstructured_output1
Supported parameterssupported_parameters1
Tool callingtool_calling1
Weights availableweights_available1
Weights dtypeweights_dtype1
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
43
Source tiers
T243
Freshest observation
2 h ago
Conflicts
None
Source documents 4
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 →