ModelActiveOpen weightsIdentity probable

DeepSeek-V4.1-Flash

DeepSeek family · DeepSeek api-docs.deepseek.com/quick_start/pricing

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

Open in Graph

data quality77

Updated 3 h ago · first seen 11 Sept 2026

model_01M293WR6HM862PR1R3X4523QG

Overview

Identity

Canonical model: Yesidentity confidence: medium
Official checkpoints: deepseek-ai/DeepSeek-V4.1-Flash
Artifacts: None recorded
Provider deployments: 4
API aliases: deepseek-flashdeepseek-v4-1-flashdeepseek/deepseek-v4.1-flashfireworks/deepseek-v4p1-flash
Folded evaluation variants: 0

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)

dimensions marked null are unknown, not false

Key facts

Release date: Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
Official page: api-docs.deepseek.com/quick_start/pricing
Source:DeepSeek — site & API docsT1observed 5 d agohigh
Model card: huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
API model id: Source:DeepSeek — site & API docsT1observed 5 d agohigh
Openrouter id: Source:OpenRouter public model & pricing listingT2observed 5 d agomedium

Relations

Available through: OpenRouter, Together AI, DeepSeek API, Fireworks AI
Developed by: DeepSeek
Member of family: DeepSeek, DeepSeek
Published by: DeepSeek

Identifiers

artificial_analysis: deepseek-v4-1-flash
deepseek_model_id: deepseek-flash
fireworks-ai_model_id: fireworks/deepseek-v4p1-flash
hf_repo: deepseek-ai/DeepSeek-V4.1-Flash
openrouter: deepseek/deepseek-v4.1-flash
together_ai_model_slug: deepseek-v4-1-flash

Also known as: DeepSeek V4.1 Flash (max), DeepSeek V4.1 Flash Max Effort, deepseek-ai/DeepSeek-V4.1-Flash, deepseek-flash, deepseek-v4-flash, deepseek-v4-flash-vision-exp, DeepSeek-V4.1-Flash, deepseek-v4p1-flash, DeepSeek: DeepSeek V4.1 Flash, fireworks/deepseek-v4p1-flash

slug deepseek-v4.1-flash

ModelDeepSeek V4 Flash (0731)DeepSeek
ModelDeepSeek-V4-Pro-0813DeepSeek
Modeldeepseek-v4-flashDeepSeek
ModelDeepSeek V4 Flash Vision ExpDeepSeek
Modeldeepseek-v4-proDeepSeek
ModelKimi K3Moonshot AI
ModelMiniMax-M3MiniMax
ModelDeepSeek V3DeepSeek

Architecture

Architecture: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
Model type: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
Parameters: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
Tokenizer: Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
Weights dtype: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
File size: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
Library name: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
Pipeline tag: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
Hugging Face repo: Source:OpenRouter public model & pricing listingT2observed 5 d agomedium

Capabilities

Modalities

Modalities: imagetext
Input: textimage
Output: text

Capabilities

Tool calling
Yes
DeepSeek — site & API docs · T1
Structured output
Yes
DeepSeek — site & API docs · T1
Reasoning
Yes
DeepSeek — site & API docs · T1
Vision
Yes
DeepSeek — site & API docs · T1
Audio
Unavailable
Fine-tuning available
Unavailable

Context window: Source:DeepSeek — site & API docsT1observed 5 d agohigh
Max output: Source:DeepSeek — site & API docsT1observed 5 d agohigh
Tokenizer: Source:OpenRouter public model & pricing listingT2observed 5 d agomedium

Benchmarks18

Compare with another model →

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

Benchmark results grouped by comparability group
Benchmark · group	Trust	Configuration	Results	vs leader	Evaluated	Source
Terminal-Benchagentic · accuracy · variant=v4.0 · evaluator=Artificial Analysis	Independent	evaluatorArtificial Analysisvariantv4.0reasoning_effortmaxconditions differ across rows → partially comparable	2	non-primary group	obs. 15 Sept 2026	artificialanalysis.aiT2
LiveBench Agentic Codingcoding · average score · variant=Agentic Coding	Official board	variantAgentic Codingrelease2026-06-25	1	current leader	25 Jun 2026	livebench.aiT2
LiveBench Codingcoding · average score · variant=Coding	Official board	variantCodingrelease2026-06-25	1	−6.34 ptvs Claude Fable 5.1	25 Jun 2026	livebench.aiT2
SciCodecoding · accuracy · evaluator=Artificial Analysis	Independent	evaluatorArtificial Analysisreasoning_effortmaxconditions differ across rows → partially comparable	2	−11.2 ptvs Claude Fable 5.1	obs. 16 Sept 2026	artificialanalysis.aiT2
Artificial Analysis Intelligence Indexcomposite · index	Independent	reasoning_effortmaxversion4.3conditions differ across rows → partially comparable	2	−13.8vs Claude Fable 5.1	obs. 16 Sept 2026	artificialanalysis.aiT2
LiveBenchgeneral · global_average	Official board	release2026-06-25	1	−2.30 ptvs Claude Fable 5.1	25 Jun 2026	livebench.aiT2
LiveBench Data Analysisgeneral · average score · variant=Data Analysis	Official board	variantData Analysisrelease2026-06-25	1	−3.72 ptvs gpt-6-astra	25 Jun 2026	livebench.aiT2
LiveBench Languagegeneral · average score · variant=Language	Official board	variantLanguagerelease2026-06-25	1	−9.49 ptvs Claude Fable 5	25 Jun 2026	livebench.aiT2
LiveBench Instruction Followinginstruction-following · average score · variant=IF	Official board	variantIFrelease2026-06-25	1	−11.4 ptvs Gemini 3.8 Flash	25 Jun 2026	livebench.aiT2
Humanity's Last Examknowledge · accuracy · evaluator=Artificial Analysis	Independent	evaluatorArtificial Analysisreasoning_effortmaxconditions differ across rows → partially comparable	2	−19.9 ptvs Claude Fable 5.1	obs. 16 Sept 2026	artificialanalysis.aiT2
LiveBench Mathematicsmath · average score · variant=Mathematics	Official board	variantMathematicsrelease2026-06-25	1	−3.72 ptvs Claude Fable 5.1	25 Jun 2026	livebench.aiT2
MMMU-Promultimodal · accuracy · evaluator=Artificial Analysis	Independent	evaluatorArtificial Analysisreasoning_effortmaxconditions differ across rows → partially comparable	2	−9.89 ptvs gpt-6-astra	obs. 16 Sept 2026	artificialanalysis.aiT2
LiveBench Reasoningreasoning · average score · variant=Reasoning	Official board	variantReasoningrelease2026-06-25	1	−5.96 ptvs gpt-6-astra	25 Jun 2026	livebench.aiT2

Current rows only, grouped by benchmark → canonical metric → comparability group (task configuration). Effort variants folded into this model appear as rows of the same group. 18 current rows in total. “vs leader” compares with the current leader of the benchmark's primary group only; other groups are not directly comparable. Comparability rules →

Providers & Pricing5

All offers in the price terminal →

Provider deployments, cheapest output first
Provider	Context	Cached in	Batch in / out	Native units	Status	Observed	Source
DeepSeek APIcheapest outputdeepseek/deepseek-v4.1-flash	1.05Mout 384K	$0.003	—	—	active	4 d agosince 11 Sept 2026	openrouter.aiT2
OpenRouterdeepseek/deepseek-v4.1-flash	1.05Mout 384K	$0.003	—	—	active	2 h agosince 16 Sept 2026	openrouter.aiT2
Fireworks AIfireworks/deepseek-v4p1-flash	—	$0.007	—	—	active	5 d agosince 11 Sept 2026	app.fireworks.aiT1
DeepSeek APIdeepseek-flash	—	$0.006	—	off_peak_input_per_mtok=0.15off_peak_output_per_mtok=0.6off_peak_cached_input_per_mtok=0.003	active	5 d agosince 11 Sept 2026	api-docs.deepseek.comT1
Together AIdeepseek-v4-1-flash	—	$0.006	$0.30 / $1.2	—	active	6 h agosince 13 Sept 2026	together.aiT1

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 4 providers

DeepSeek API
Fireworks AI
OpenRouter
Together AI

OpenRouter$1.2 → $0.6016 Sept 2026
OpenRouter$0.60 → $1.216 Sept 2026
OpenRouter$1.2 → $0.6015 Sept 2026
OpenRouter$0.60 → $1.215 Sept 2026
OpenRouter$1.2 → $0.6015 Sept 2026
OpenRouter$0.60 → $1.215 Sept 2026
OpenRouter$1.2 → $0.6014 Sept 2026
OpenRouter$0.60 → $1.214 Sept 2026
OpenRouter$1.2 → $0.6014 Sept 2026
OpenRouter$0.60 → $1.214 Sept 2026
Together AIfirst observed $1.213 Sept 2026
OpenRouterfirst observed $0.6012 Sept 2026

Input price · USD / 1M tokens 4 providers

DeepSeek API
Fireworks AI
OpenRouter
Together AI

OpenRouter$0.30 → $0.1516 Sept 2026
OpenRouter$0.15 → $0.3016 Sept 2026
OpenRouter$0.30 → $0.1515 Sept 2026
OpenRouter$0.15 → $0.3015 Sept 2026
OpenRouter$0.30 → $0.1515 Sept 2026
OpenRouter$0.15 → $0.3015 Sept 2026
OpenRouter$0.30 → $0.1514 Sept 2026
OpenRouter$0.15 → $0.3014 Sept 2026
OpenRouter$0.30 → $0.1514 Sept 2026
OpenRouter$0.15 → $0.3014 Sept 2026
Together AIfirst observed $0.3013 Sept 2026
OpenRouterfirst observed $0.1512 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	—	439.3 GB est.	Yes
Mac Studio (Apple M5 Ultra)	4bit	—	439.3 GB est.	Yes
NVIDIA DGX B200	4bit	1,440 GB	439.3 GB est.	Yes
Apple M2 Ultra	4bit	—	439.3 GB est.	No
Apple M1 Ultra	4bit	—	439.3 GB est.	No
Apple M3 Max	4bit	—	439.3 GB est.	No
Apple M4 Max	4bit	—	439.3 GB est.	No
Mac Studio (Apple M5 Max)	4bit	—	439.3 GB est.	No
MacBook Pro (Apple M5 Max)	4bit	—	439.3 GB est.	No
Apple M2 Max	4bit	—	439.3 GB est.	No
Apple M1 Max	4bit	—	439.3 GB est.	No
Apple M4 Pro	4bit	—	439.3 GB est.	No
Mac mini (Apple M5 Pro)	4bit	—	439.3 GB est.	No
MacBook Pro (Apple M5 Pro)	4bit	—	439.3 GB est.	No
Apple M3 Pro	4bit	—	439.3 GB est.	No
Apple M1 Pro	4bit	—	439.3 GB est.	No
Apple M2 Pro	4bit	—	439.3 GB est.	No
Apple M4	4bit	—	439.3 GB est.	No
iMac (Apple M4)	4bit	—	439.3 GB est.	No
Mac mini (Apple M6)	4bit	—	439.3 GB est.	No
MacBook Air (Apple M5)	4bit	—	439.3 GB est.	No
MacBook Pro (Apple M5)	4bit	—	439.3 GB est.	No
Apple M2	4bit	—	439.3 GB est.	No
Apple M3	4bit	—	439.3 GB est.	No
Apple M1	4bit	—	439.3 GB est.	No
NVIDIA GeForce RTX 3090	4bit	24 GB	439.3 GB est.	No
NVIDIA GeForce RTX 4090	4bit	24 GB	439.3 GB est.	No
NVIDIA GeForce RTX 5090	4bit	32 GB	439.3 GB est.	No
NVIDIA A100 80GB	4bit	80 GB	439.3 GB est.	No
NVIDIA H100 SXM	4bit	80 GB	439.3 GB est.	No
NVIDIA H100 NVL	4bit	94 GB	439.3 GB est.	No
NVIDIA DGX Spark	4bit	128 GB	439.3 GB est.	No
NVIDIA H200	4bit	141 GB	439.3 GB est.	No
NVIDIA H200 NVL	4bit	141 GB	439.3 GB est.	No
NVIDIA B200	4bit	180 GB	439.3 GB est.	No
AMD Instinct MI300X	4bit	192 GB	439.3 GB est.	No
AMD Instinct MI325X	4bit	256 GB	439.3 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

16 Sept 2026current

Max outputfirst observation only

11 Sept 2026current

Opennessfirst observation only

11 Sept 2026current

Parametersfirst observation only

16 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.

Timeline9

Full timeline →

14 Sept 2026
Price changedModelDeepSeek-V4.1-FlashDeepSeek
OpenRouter changed pricing for DeepSeek-V4.1-Flash: $0.3 in / $1.2 out per 1M tokens → $0.15 in / $0.6 out per 1M tokens
$0.30 in / $1.2 out→$0.15 in / $0.60 outopenrouter
openrouter.ai
14 Sept 2026
Price changedModelDeepSeek-V4.1-FlashDeepSeek
OpenRouter changed pricing for DeepSeek-V4.1-Flash: $0.15 in / $0.6 out per 1M tokens → $0.3 in / $1.2 out per 1M tokens
$0.15 in / $0.60 out→$0.30 in / $1.2 outopenrouter
openrouter.ai
13 Sept 2026
Listed by providerModelDeepSeek-V4.1-FlashDeepSeek
Together AI lists DeepSeek-V4.1-Flash at $0.3 in / $1.2 out per 1M tokens
together_pricing
together.ai
12 Sept 2026
Listed by providerModelDeepSeek-V4.1-FlashDeepSeek
OpenRouter lists DeepSeek-V4.1-Flash at $0.15 in / $0.6 out per 1M tokens
openrouter
openrouter.ai
12 Sept 2026
Benchmark resultModelDeepSeek-V4.1-FlashDeepSeek
DeepSeek-V4.1-Flash scores 26.77% on Terminal-Bench
artificial_analysis
artificialanalysis.ai
12 Sept 2026
Benchmark resultModelDeepSeek-V4.1-FlashDeepSeek
DeepSeek-V4.1-Flash scores 76.99% on MMMU-Pro
artificial_analysis
artificialanalysis.ai
12 Sept 2026
Benchmark resultModelDeepSeek-V4.1-FlashDeepSeek
DeepSeek-V4.1-Flash scores 51.85% on SciCode
artificial_analysis
artificialanalysis.ai
12 Sept 2026
Benchmark resultModelDeepSeek-V4.1-FlashDeepSeek
DeepSeek-V4.1-Flash scores 39.25% on Humanity's Last Exam
artificial_analysis
artificialanalysis.ai
12 Sept 2026
Benchmark resultModelDeepSeek-V4.1-FlashDeepSeek
DeepSeek-V4.1-Flash scores 39.55 on Artificial Analysis Intelligence Index
artificial_analysis
artificialanalysis.ai

Change history58

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 15 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

Attributes as of 15 Sept 2026 25 claims in force

Family: DeepSeek
Release date: 10 Sept 2026
Openness: open-weights
Context window: 1M tokens
Max output: 384K tokens
Modalities: image, text
Input modalities: text, image
Output modalities: text
Tokenizer: DeepSeek
API model id: deepseek-flash
Hugging Face repo: deepseek-ai/DeepSeek-V4.1-Flash
Official page: api-docs.deepseek.com/quick_start/pricing
Aa context window: 1,000,000
Aa openness: open-weights
Livebench hf link: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash
Aa median output tokens per second: 213.2
Openrouter id: deepseek/deepseek-v4.1-flash
Openrouter listed at: 10 Sept 2026
Reasoning: Yes
Structured output: Yes
Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, 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
Tool calling: Yes
Vision: Yes
Weights available: Yes

58 claims · 46 properties11 conflicting

Familyfamily1

Claim history for Family
Value	Valid from → to	Status	Source	Confidence	Extractor
DeepSeek	11 Sept 2026 20:52 UTC → current	current	DeepSeek — site & API docsT1	high	deterministic

Release daterelease_date1

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

Opennessopenness1

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

Licenselicense1

Claim history for License
Value	Valid from → to	Status	Source	Confidence	Extractor
MIT	16 Sept 2026 13:35 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
DeepseekV41ForCausalLM	16 Sept 2026 13:35 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
763.2B	16 Sept 2026 13:21 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Context windowcontext_length8conflicting claims

Claim history for Context window
Value	Valid from → to	Status	Source	Confidence	Extractor
1.05M tokens	12 Sept 2026 06:14 UTC → current	conflicting	OpenRouter public model & pricing listingT2	medium	deterministic
1.05M tokens	12 Sept 2026 05:14 UTC → current	conflicting	OpenRouter public model & pricing listingT2	medium	deterministic
1.05M tokens	12 Sept 2026 04:10 UTC → current	conflicting	OpenRouter public model & pricing listingT2	medium	deterministic
1.05M tokens	12 Sept 2026 01:07 UTC → current	conflicting	OpenRouter public model & pricing listingT2	medium	deterministic
1.05M tokens	12 Sept 2026 00:05 UTC → current	conflicting	OpenRouter public model & pricing listingT2	medium	deterministic
1.05M tokens	11 Sept 2026 22:37 UTC → current	conflicting	OpenRouter public model & pricing listingT2	medium	deterministic
1.05M tokens	11 Sept 2026 21:10 UTC → current	conflicting	OpenRouter public model & pricing listingT2	medium	deterministic
1M tokens	11 Sept 2026 20:52 UTC → current	current	DeepSeek — site & API docsT1	conflicted	deterministic

Max outputmax_output_tokens1

Claim history for Max output
Value	Valid from → to	Status	Source	Confidence	Extractor
384K tokens	11 Sept 2026 20:52 UTC → current	current	DeepSeek — site & API docsT1	high	deterministic

Modalitiesmodalities1

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

Input modalitiesmodalities_input5conflicting claims

Claim history for Input modalities
Value	Valid from → to	Status	Source	Confidence	Extractor
image, text	12 Sept 2026 01:07 UTC → current	conflicting	OpenRouter public model & pricing listingT2	medium	deterministic
image, text	12 Sept 2026 00:05 UTC → current	conflicting	OpenRouter public model & pricing listingT2	medium	deterministic
image, text	11 Sept 2026 22:37 UTC → current	conflicting	OpenRouter public model & pricing listingT2	medium	deterministic
image, text	11 Sept 2026 21:10 UTC → current	conflicting	OpenRouter public model & pricing listingT2	medium	deterministic
text, image	11 Sept 2026 20:52 UTC → current	current	DeepSeek — site & API docsT1	conflicted	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

API model idapi_model_id1

Claim history for API model id
Value	Valid from → to	Status	Source	Confidence	Extractor
deepseek-flash	11 Sept 2026 20:52 UTC → current	current	DeepSeek — site & API docsT1	high	deterministic

Quantization formatquant_format1

Claim history for Quantization format
Value	Valid from → to	Status	Source	Confidence	Extractor
fp8	16 Sept 2026 13:35 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
510.3 GB	16 Sept 2026 13:35 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-V4.1-Flash	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
image-text-to-text	16 Sept 2026 13:21 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Official pageofficial_url1

Claim history for Official page
Value	Valid from → to	Status	Source	Confidence	Extractor
https://api-docs.deepseek.com/quick_start/pricing/	11 Sept 2026 20:52 UTC → current	current	DeepSeek — site & API docsT1	high	deterministic

Model cardmodel_card_url1

Claim history for Model card
Value	Valid from → to	Status	Source	Confidence	Extractor
https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash	16 Sept 2026 13:21 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
366,459	16 Sept 2026 13:21 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Likesmetric.likes2

Claim history for Likes
Value	Valid from → to	Status	Source	Confidence	Extractor
2,790	16 Sept 2026 13:35 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic
2,786	16 Sept 2026 13:21 UTC → 16 Sept 2026 13:35 UTC	superseded	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Aa context windowaa_context_window1

Claim history for Aa context window
Value	Valid from → to	Status	Source	Confidence	Extractor
1,000,000 tokens	12 Sept 2026 07:08 UTC → current	current	Artificial AnalysisT2	medium	deterministic

Aa opennessaa_openness1

Claim history for Aa openness
Value	Valid from → to	Status	Source	Confidence	Extractor
open-weights	12 Sept 2026 07:08 UTC → current	current	Artificial AnalysisT2	medium	deterministic

Accessaccess1

Claim history for Access
Value	Valid from → to	Status	Source	Confidence	Extractor
open	16 Sept 2026 13:21 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Artifact kindartifact_kind1

Claim history for Artifact kind
Value	Valid from → to	Status	Source	Confidence	Extractor
quantization	16 Sept 2026 13:35 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 V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Hf inference providershf_inference_providers1

Claim history for Hf inference providers
Value	Valid from → to	Status	Source	Confidence	Extractor
baseten, deepinfra, fireworks-ai, novita	16 Sept 2026 13:35 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	16 Sept 2026 13:35 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
2026-09-10T08:18:10+00:00	16 Sept 2026 13:21 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	16 Sept 2026 13:35 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

License keylicense_key1

Claim history for License key
Value	Valid from → to	Status	Source	Confidence	Extractor
MIT	16 Sept 2026 13:35 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

License rawlicense_raw1

Claim history for License raw
Value	Valid from → to	Status	Source	Confidence	Extractor
mit	16 Sept 2026 13:35 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Livebench hf linklivebench_hf_link1

Claim history for Livebench hf link
Value	Valid from → to	Status	Source	Confidence	Extractor
https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash	11 Sept 2026 22:42 UTC → current	current	LiveBenchT2	medium	deterministic

Aa median output tokens per secondmetric.aa_median_output_tokens_per_second1

Claim history for Aa median output tokens per second
Value	Valid from → to	Status	Source	Confidence	Extractor
213.2	11 Sept 2026 22:42 UTC → current	current	Artificial AnalysisT2	medium	deterministic

Downloads all timemetric.downloads_all_time1

Claim history for Downloads all time
Value	Valid from → to	Status	Source	Confidence	Extractor
366,459	16 Sept 2026 13:35 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_v41	16 Sept 2026 13:35 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-v4.1-flash	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Openrouter listed atopenrouter_listed_at1

Claim history for Openrouter listed at
Value	Valid from → to	Status	Source	Confidence	Extractor
10 Sept 2026	12 Sept 2026 04:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Reasoningreasoning1

Claim history for Reasoning
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 20:52 UTC → current	current	DeepSeek — site & API docsT1	high	deterministic

Structured outputstructured_output1

Claim history for Structured output
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 20:52 UTC → current	current	DeepSeek — site & API docsT1	high	deterministic

Supported parameterssupported_parameters1

Claim history for Supported parameters
Value	Valid from → to	Status	Source	Confidence	Extractor
frequency_penalty, include_reasoning, logit_bias, logprobs, 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	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
8-bit, deepseek_v41, fp8, image-text-to-text, safetensors, text-generation, transformers	16 Sept 2026 13:35 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 20:52 UTC → current	current	DeepSeek — site & API docsT1	high	deterministic

Visionvision1

Claim history for Vision
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 20:52 UTC → current	current	DeepSeek — site & API docsT1	high	deterministic

Weights availableweights_available1

Claim history for Weights available
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	12 Sept 2026 06:34 UTC → current	current	AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2	high	derived

Weights dtypeweights_dtype1

Claim history for Weights dtype
Value	Valid from → to	Status	Source	Confidence	Extractor
BF16, F32, F8_E4M3, I8	16 Sept 2026 13:35 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

T1T210 / 36

Freshest observation

4 h ago

Conflicts

11 flagged

Source documents 9

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
Fireworks AI — pricing	docs.fireworks.ai/serverless/pricing.md	pricing	T1· Official	3 h ago	2
Together AI — pricing	together.ai/pricing	pricing	T1· Official	6 h ago	3
DeepSeek — site & API docs	api-docs.deepseek.com/quick_start/pricing	pricing	T1· Official	35 h ago	1
OpenRouter public model & pricing listing	openrouter.ai/api/v1/models	catalogue	T2· Quality secondary	2 h ago	74
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash/raw/main/README.md	model_card	T2· Quality secondary	3 h ago	1
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash	model_page	T2· Quality secondary	4 h ago	1
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/models?author=deepseek-ai&p=0&sort=downloads	listing	T2· Quality secondary	4 h ago	31
Artificial Analysis	artificialanalysis.ai/leaderboards/models	leaderboard	T2· Quality secondary	5 h ago	17
LiveBench	livebench.ai/table_2026_06_25.csv	leaderboard	T2· Quality secondary	5 d 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 (77/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →