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 3 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 8 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium
- Openrouter id
Source:OpenRouter public model & pricing listingT2observed 13 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 13 h agomedium
- Tokenizer
Source:OpenRouter public model & pricing listingT2observed 13 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 13 h agomedium
- Hugging Face repo
Source:OpenRouter public model & pricing listingT2observed 13 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
OpenRouter public model & pricing listing · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
Source:OpenRouter public model & pricing listingT2observed 13 h agomedium
- Max output
Source:OpenRouter public model & pricing listingT2observed 13 h agomedium
- Tokenizer
Source:OpenRouter public model & pricing listingT2observed 13 h 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$1.62 → $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
- DeepSeek API$1.9 → $1.6812 Sept 2026
- DeepSeek API$1.72 → $1.911 Sept 2026
- DeepSeek APIfirst observed $1.7211 Sept 2026
Input price · USD / 1M tokens 2 providers
- DeepSeek API
- OpenRouter
- 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
- DeepSeek API$0.948 → $0.8412 Sept 2026
- DeepSeek API$0.86 → $0.94811 Sept 2026
- DeepSeek APIfirst observed $0.8611 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
Context windowfirst observation only
11 Sept 2026current
Licensefirst observation only
11 Sept 2026current
Max outputfirst 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
Timeline9
Full timeline →OpenRouter 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 history43
Viewing AI Atlas as of 11 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.
Back to today →Attributes as of 11 Sept 2026 33 claims in force
- Release date
- 22 Apr 2026
- Openness
- open-weights
- License
- MIT
- Architecture
- DeepseekV4ForCausalLM
- Parameters
- 1.6T
- Context window
- 1.05M tokens
- Max output
- 384K tokens
- Modalities
- text
- Input modalities
- text
- Output modalities
- text
- Tokenizer
- DeepSeek
- Quantization format
- fp8
- File size
- 864.7 GB
- Hugging Face repo
- deepseek-ai/DeepSeek-V4-Pro
- Pipeline tag
- text-generation
- Downloads
- 619,127
- Likes
- 5,523
- Gated
- No
- Hf inference providers
- baseten, deepinfra, novita, together
- Is quantized
- Yes
- Last modified
- 2026-06-22T12:12:50+00:00
- Library name
- transformers
- Downloads all time
- 10,412,271
- Model type
- deepseek_v4
- Openrouter id
- deepseek/deepseek-v4-pro
- Reasoning
- Yes
- Structured output
- Yes
- Supported parameters
- frequency_penalty, include_reasoning, logit_bias, logprobs, max_completion_tokens, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Tags
- transformers, safetensors, deepseek_v4, text-generation, 8-bit, fp8
- Tool calling
- Yes
- Weights dtype
- BF16, F32, F8_E4M3, I64, I8
Release daterelease_date6
Opennessopenness1
Licenselicense1
Architecturearchitecture1
Parametersparameter_count1
Context windowcontext_length1
Max outputmax_output_tokens1
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.downloads1
Likesmetric.likes1
Commercial use allowedcommercial_use_allowed1
Derivatives allowedderivatives_allowed1
Descriptiondescription1
Gatedgated1
Hf inference providershf_inference_providers1
Is quantizedis_quantized1
Last modifiedlast_modified1
Library namelibrary_name1
Downloads all timemetric.downloads_all_time1
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
40
Source tiers
T240
Freshest observation
3 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 →