Skip to content
AI Atlas
ModelActiveOpen weightsIdentity probable

DeepSeek V4 Flash 0423

DeepSeekfamily · DeepSeekhuggingface.co/deepseek-ai/DeepSeek-V4-Flash

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

Open in Graph
data quality68

Updated 1 h ago · first seen 11 Sept 2026

model_01M294WW0M9SRBDTMYPH56GG7K

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-flashIdentifiers 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 12 h agomedium

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 16 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 h agomedium

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 16 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 h agomedium

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 h agomedium

Hugging Face repo

Source:OpenRouter public model & pricing listingT2observed 16 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 16 h agomedium

Max output

Source:OpenRouter public model & pricing listingT2observed 16 h agomedium

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 16 h agomedium

Providers & Pricing2

All offers in the price terminal →
Provider deployments, cheapest output first
ProviderContextInput / 1MCached inOutput / 1MStatusObservedSource
DeepSeek APIcheapest outputdeepseek/deepseek-v4-flash1.02Mout 384K$0.013active7 h agosince 12 Sept 2026openrouter.aiT2
OpenRouterdeepseek/deepseek-v4-flash1.02Mout 384K$0.013active57 min agosince 12 Sept 2026openrouter.aiT2

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

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 2 providers

Output price history of DeepSeek V4 Flash 0423$0$0.05$0.10$0.15$0.20Sept 26Sept 26Sept 26Sept 26Sept 26DeepSeek API: first observed → $0.17 · 11 Sept 2026DeepSeek API: $0.17 → $0.169 · 11 Sept 2026DeepSeek API: $0.169 → $0.135 · 12 Sept 2026DeepSeek API: $0.135 → $0.135 · 12 Sept 2026DeepSeek API: $0.135 → $0.134 · 12 Sept 2026DeepSeek API: $0.134 → $0.134 · 12 Sept 2026DeepSeek API: $0.134 → $0.134 · 12 Sept 2026OpenRouter: first observed → $0.134 · 12 Sept 2026
  • DeepSeek API
  • OpenRouter
  • OpenRouterfirst observed $0.13412 Sept 2026
  • DeepSeek API$0.134 → $0.13412 Sept 2026
  • DeepSeek API$0.134 → $0.13412 Sept 2026
  • DeepSeek API$0.135 → $0.13412 Sept 2026
  • DeepSeek API$0.135 → $0.13512 Sept 2026
  • DeepSeek API$0.169 → $0.13512 Sept 2026
  • DeepSeek API$0.17 → $0.16911 Sept 2026
  • DeepSeek APIfirst observed $0.1711 Sept 2026

Input price · USD / 1M tokens 2 providers

Input price history of DeepSeek V4 Flash 0423$0$0.02$0.04$0.06$0.08$0.10Sept 26Sept 26Sept 26Sept 26Sept 26DeepSeek API: first observed → $0.085 · 11 Sept 2026DeepSeek API: $0.085 → $0.085 · 11 Sept 2026DeepSeek API: $0.085 → $0.068 · 12 Sept 2026DeepSeek API: $0.068 → $0.067 · 12 Sept 2026DeepSeek API: $0.067 → $0.067 · 12 Sept 2026DeepSeek API: $0.067 → $0.067 · 12 Sept 2026DeepSeek API: $0.067 → $0.067 · 12 Sept 2026OpenRouter: first observed → $0.067 · 12 Sept 2026
  • DeepSeek API
  • OpenRouter
  • OpenRouterfirst observed $0.06712 Sept 2026
  • DeepSeek API$0.067 → $0.06712 Sept 2026
  • DeepSeek API$0.067 → $0.06712 Sept 2026
  • DeepSeek API$0.067 → $0.06712 Sept 2026
  • DeepSeek API$0.068 → $0.06712 Sept 2026
  • DeepSeek API$0.085 → $0.06812 Sept 2026
  • DeepSeek API$0.085 → $0.08511 Sept 2026
  • DeepSeek APIfirst observed $0.08511 Sept 2026

Hardware fit37

Estimated

7 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit—167.8 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—167.8 GB est.Yes
Apple M2 Ultra4bit—167.8 GB est.Yes
NVIDIA B2004bit180 GB167.8 GB est.Yes
AMD Instinct MI300X4bit192 GB167.8 GB est.Yes
AMD Instinct MI325X4bit256 GB167.8 GB est.Yes
NVIDIA DGX B2004bit1,440 GB167.8 GB est.Yes
Apple M1 Ultra4bit—167.8 GB est.No
Apple M3 Max4bit—167.8 GB est.No
Apple M4 Max4bit—167.8 GB est.No
Mac Studio (Apple M5 Max)4bit—167.8 GB est.No
MacBook Pro (Apple M5 Max)4bit—167.8 GB est.No
Apple M2 Max4bit—167.8 GB est.No
Apple M1 Max4bit—167.8 GB est.No
Apple M4 Pro4bit—167.8 GB est.No
Mac mini (Apple M5 Pro)4bit—167.8 GB est.No
MacBook Pro (Apple M5 Pro)4bit—167.8 GB est.No
Apple M3 Pro4bit—167.8 GB est.No
Apple M1 Pro4bit—167.8 GB est.No
Apple M2 Pro4bit—167.8 GB est.No
Apple M44bit—167.8 GB est.No
iMac (Apple M4)4bit—167.8 GB est.No
Mac mini (Apple M6)4bit—167.8 GB est.No
MacBook Air (Apple M5)4bit—167.8 GB est.No
MacBook Pro (Apple M5)4bit—167.8 GB est.No
Apple M24bit—167.8 GB est.No
Apple M34bit—167.8 GB est.No
Apple M14bit—167.8 GB est.No
NVIDIA GeForce RTX 30904bit24 GB167.8 GB est.No
NVIDIA GeForce RTX 40904bit24 GB167.8 GB est.No
NVIDIA GeForce RTX 50904bit32 GB167.8 GB est.No
NVIDIA A100 80GB4bit80 GB167.8 GB est.No
NVIDIA H100 SXM4bit80 GB167.8 GB est.No
NVIDIA H100 NVL4bit94 GB167.8 GB est.No
NVIDIA DGX Spark4bit128 GB167.8 GB est.No
NVIDIA H2004bit141 GB167.8 GB est.No
NVIDIA H200 NVL4bit141 GB167.8 GB est.No
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

Timeline9

Full timeline →
  • Listed by providerModelDeepSeek V4 Flash 0423DeepSeek

    OpenRouter lists DeepSeek V4 Flash 0423 at $0.06678 in / $0.13356 out per 1M tokens

    openrouter
    openrouter.ai
  • Price changedModelDeepSeek V4 Flash 0423DeepSeek

    DeepSeek API changed pricing for DeepSeek V4 Flash 0423: $0.06706 in / $0.13412 out per 1M tokens → $0.06678 in / $0.13356 out per 1M tokens

    $0.067 in / $0.134 out→$0.067 in / $0.134 outopenrouter
    openrouter.ai
  • Price changedModelDeepSeek V4 Flash 0423DeepSeek

    DeepSeek API changed pricing for DeepSeek V4 Flash 0423: $0.06678 in / $0.13356 out per 1M tokens → $0.06706 in / $0.13412 out per 1M tokens

    $0.067 in / $0.134 out→$0.067 in / $0.134 outopenrouter
    openrouter.ai
  • Price changedModelDeepSeek V4 Flash 0423DeepSeek

    DeepSeek API changed pricing for DeepSeek V4 Flash 0423: $0.06734 in / $0.13468 out per 1M tokens → $0.06678 in / $0.13356 out per 1M tokens

    $0.067 in / $0.135 out→$0.067 in / $0.134 outopenrouter
    openrouter.ai
  • Price changedModelDeepSeek V4 Flash 0423DeepSeek

    DeepSeek API changed pricing for DeepSeek V4 Flash 0423: $0.06762 in / $0.13524 out per 1M tokens → $0.06734 in / $0.13468 out per 1M tokens

    $0.068 in / $0.135 out→$0.067 in / $0.135 outopenrouter
    openrouter.ai
  • Price changedModelDeepSeek V4 Flash 0423DeepSeek

    DeepSeek API changed pricing for DeepSeek V4 Flash 0423: $0.08456 in / $0.16912 out per 1M tokens → $0.06762 in / $0.13524 out per 1M tokens

    $0.085 in / $0.169 out→$0.068 in / $0.135 outopenrouter
    openrouter.ai
  • Price changedModelDeepSeek V4 Flash 0423DeepSeek

    DeepSeek API changed pricing for DeepSeek V4 Flash 0423: $0.08484 in / $0.16968 out per 1M tokens → $0.08456 in / $0.16912 out per 1M tokens

    $0.085 in / $0.17 out→$0.085 in / $0.169 outopenrouter
    openrouter.ai
  • Release date changedModelDeepSeek V4 Flash 0423DeepSeek

    DeepSeek V4 Flash 0423: release date changed from 2026-04-22 to 2026-04-24

    Release date22 Apr 2026→24 Apr 2026openrouter
    openrouter.ai
  • Release date changedModelDeepSeek V4 Flash 0423DeepSeek

    DeepSeek V4 Flash 0423: release date changed from 2026-04-24 to 2026-04-22

    Release date24 Apr 2026→22 Apr 2026huggingface
    huggingface.co

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

Accessaccess1

Claim history for Access
ValueValid from → toStatusSourceConfidenceExtractor
open → currentcurrentHugging 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

43

Source tiers

T243

Freshest observation

2 h ago

Conflicts

None

Source documents 4

Source documents
SourceDocumentTypeTierLast observedSnapshots
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary57 min ago12
Hugging Face Hub (public pages, model cards, papers)huggingface.co/deepseek-ai/DeepSeek-V4-Flash/raw/main/README.md model_cardT2· Quality secondary1 h ago1
Hugging Face Hub (public pages, model cards, papers)huggingface.co/deepseek-ai/DeepSeek-V4-Flash model_pageT2· Quality secondary2 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=deepseek-ai&p=0&sort=downloads listingT2· Quality secondary2 h ago8

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 →