LLM
DeepSeek-V4-Flash
Smaller DeepSeek V4 MoE model (284B / 13B active), text only, with a 0731 update; base model released separately.
Levelmodel
ClassLLM
Parameters284B
Context1,000,000
Released24 Apr 2026
Opennessopen weights permissive
Runs onmulti-GPU node, single datacentre GPU
Statusactive
Benchmark Results
vendor-reported
GPQA Diamondknowledge and reasoning
vendor-reported
89.9
050100
Score in %. Higher is better.
LiveCodeBenchcoding
vendor-reported
91.6
050100
Score in %. Higher is better.
SWE-bench Verifiedcoding
vendor-reported
79
050100
Score in %. Higher is better.
Terminal-Bench 2.0agents and tool use
vendor-reported
56.9
050100
Score in %. Higher is better.
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Lineage
instruct ofsuccessorfinetune
DeepSeek-V4-Flash Base is the parent (instruct of)medium confidencenotesDeepSeek-V4-Flash-0731 is a child (successor)medium confidencenotesDeepSeek-V4-Flash Vision-Exp is a child (finetune)medium confidencenotesWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 4 models. Confidence and evidence are the notes' own.
R&D Topics
Identity
- Developer
- DeepSeek
- Family
- DeepSeek V4
- Released
- 24 Apr 2026 sourcessecondary report
- Weights published
- –
- Record checked
- 10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- MoE
- Total parameters
- 284B sources
- Active parameters
- 13B
- Checkpoint parameters
- –
- Context length
- 1,000,000 tokens
- Input
- text
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- MIT License sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- multi-GPU node, single datacentre GPU
- Footprint
- T3 estimate (unverified). Output 384K.
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Industry Use Cases
No industry use case links this model.
Links
DeveloperDeepSeekstartup, China
DeepSeekstartup, ChinaModelDeepSeek-V4-FlashDeepSeek, LLM
DeepSeek-V4-FlashDeepSeek, LLMR&D TopicsEfficiency Architectures (MoE, Sparse Attention, Long Context)Open-Weight Frontier Releases as Research Substrate
Use CasesClinical LLM (Open Weights)HealthcareProcess Optimisation and Advanced Process ControlIndustrialTelecom Domain LLMs and BenchmarksTelecomUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
PT Amman Mineral Nusa Tenggara (AMMAN)In production, 8 Jul 2026MIND IDResearch, 14 Oct 2025
Conch CementIn production, 23 Jun 2025
PT Kalbe Morinaga IndonesiaIn production, Oct 2024+2 moreDeployments of these use cases; none names this model.
PT Amman Mineral Nusa Tenggara (AMMAN)In production, 8 Jul 2026MIND IDResearch, 14 Oct 2025Conch CementIn production, 23 Jun 2025PT Kalbe Morinaga IndonesiaIn production, Oct 2024+2 moreDeployments of these use cases; none names this model.Models 4
Organisations 1
Sources
- DeepSeek V4-Pro Review: Benchmarks, Pricing & Architecture blog.buildfastwithai.com https://blog.buildfastwithai.com/deepseek-v4-pro-review-2026
- deepseek-ai (DeepSeek) huggingface.co https://huggingface.co/deepseek-ai
- leaderboard.steel.dev/leaderboards/swe-bench-verified.md https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md
- DeepSeek Releases V4: Open-Source 1.6T MoE with 1M Context rits.shanghai.nyu.edu https://rits.shanghai.nyu.edu/ai/deepseek-releases-v4-open-source-1-6t-moe-with-1m-context
- deepseek-ai/DeepSeek-V4-Pro , Hugging Face huggingface.co https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "DeepSeek-V4-Flash", https://aurion.semai.id/models/deepseek-deepseek-v4-flash/, records of October 2026.