AI lab · founded 2023 · 14 models tracked

DeepSeek models

Every DeepSeek model on the API today, with release dates, context windows, API prices and benchmark scores. Newest: DeepSeek V4.1 Flash 1017, 5d ago.

First model
Nov 2, 2023 DeepSeek Coder
Models · 30 days
1 of 14
Latest release
5d ago
Cheapest input / 1M
$0.047 DeepSeek V4 Flash 0731
Largest context
1M DeepSeek V4.1 Flash 1017

Release history

Timeline

DeepSeek ships a new model about every 51 days. Each dot is a release; click one to open it. Hollow dots are retired models.

Jul 2024Oct 2024Jan 2025Apr 2025Jul 2025Oct 2025Jan 2026Apr 2026Jul 2026Oct 2026 DeepSeek V2 — May 6, 2024 · retiredDeepSeek V3 — Dec 26, 2024DeepSeek R1 — Jan 20, 2025 · retiredDeepSeek V3 0324 — Mar 24, 2025R1 0528 — May 28, 2025DeepSeek V3.1 — Aug 21, 2025DeepSeek V3.1 Terminus — Sep 22, 2025DeepSeek V3.2 Exp — Sep 29, 2025DeepSeek V3.2 — Dec 1, 2025DeepSeek V4 Flash 0423 — Apr 24, 2026DeepSeek V4 Pro 0423 — Apr 24, 2026DeepSeek V4 Flash 0731 — Jul 31, 2026DeepSeek V4 Pro 0813 — Aug 12, 2026DeepSeek V4 Flash Vision Exp — Aug 21, 2026DeepSeek V4.1 Flash — Sep 10, 2026DeepSeek V4.1 Flash 1017 — Oct 17, 2026

Lineup

All DeepSeek models

ModelReleasedContextInput / 1MOutput / 1MGPQA Diamond
DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017
ReasoningOpen weightsVision
Oct 17, 2026 1M393K out $0.15 $0.60 93.2%
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash
ReasoningOpen weightsVision
Sep 10, 2026 1M944K out $0.30 $1.20 93.2%
DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp
ReasoningOpen weightsVision
Aug 21, 2026 1M262K out $0.22 $0.65 —
DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813
ReasoningOpen weights
Aug 12, 2026 1M393K out $0.66 $1.98 91.7%
DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731
ReasoningOpen weights
Jul 31, 2026 1M131K out $0.047 $0.14 91.0%
DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro
ReasoningOpen weights
Apr 24, 2026 1M384K out $0.44 $0.89 91.7%
DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash
ReasoningOpen weights
Apr 24, 2026 1M944K out $0.091 $0.18 91.0%
DeepSeek V3.2deepseek/deepseek-v3.2
ReasoningOpen weights
Dec 1, 2025 164K66K out $0.28 $0.42 —
DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp
ReasoningOpen weights
Sep 29, 2025 164K147K out $0.27 $0.41 —
DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus
ReasoningOpen weights
Sep 22, 2025 164K147K out $0.27 $1.00 —
DeepSeek V3.1deepseek/deepseek-chat-v3.1
ReasoningOpen weights
Aug 21, 2025 164K33K out $0.25 $0.95 —
R1 0528deepseek/deepseek-r1-0528
ReasoningOpen weights
May 28, 2025 164K33K out $0.50 $2.15 76.3%
DeepSeek V3 0324deepseek/deepseek-chat-v3-0324
Open weights
Mar 24, 2025 164K115K out $0.29 $1.14 —
DeepSeek V3deepseek/deepseek-chat
Open weights
Dec 26, 2024 164K16K out $0.26 $1.03 71.2%

Benchmarks

DeepSeek's best scores

The top DeepSeek model on each benchmark, and where it ranks among all 281 tracked models.

BenchmarkBest DeepSeek modelScoreOverall rank
FrontierCodeSoftware engineering DeepSeek V4.1 Flash 1017 43.9% #16of 41
SWE-bench VerifiedSoftware engineering DeepSeek V4 Pro 0813 77.6% #5of 32
Terminal-BenchSoftware engineering DeepSeek V3.2 39.6% #23of 40
SciCodeSoftware engineering DeepSeek V4.1 Flash 1017 51.8% #39of 102
Aider PolyglotSoftware engineering DeepSeek V3.2 74.2% #4of 26
WeirdML v3Software engineering DeepSeek V4.1 Flash 1017 5.9% #18of 22
METR time horizonSoftware engineering R1 0528 31 min #16of 23
APEX-AgentsAgents & computer use DeepSeek V4 Pro 0813 47.3% #30of 51
Vending-Bench 2Agents & computer use DeepSeek V4 Pro 0813 $3,285 #41of 61
Lech Mazur WritingWriting & content R1 0528 8.30/10 #8of 27
Fiction.LiveBenchWriting & content DeepSeek V3.2 83.3% #5of 24
DeepResearch BenchWriting & content R1 0528 35.1% #20of 21
GDP.pdfWriting & content DeepSeek V4.1 Flash 1017 19.8% #22of 38
SimpleQA VerifiedWriting & content DeepSeek V4 Pro 0813 52.9% #22of 79
WebDev ArenaDesign & visual DeepSeek V4.1 Flash 1017 1614 #18of 90
Furniture AssemblyDesign & visual DeepSeek V4.1 Flash 1017 34.2% #20of 34
GPQA DiamondReasoning & knowledge DeepSeek V4.1 Flash 1017 93.2% #17of 122
ARC-AGI-2Reasoning & knowledge DeepSeek V4.1 Flash 1017 72.9% #19of 75
ARC-AGI-1Reasoning & knowledge DeepSeek V4.1 Flash 1017 94.5% #16of 75
SimpleBenchReasoning & knowledge DeepSeek V4 Flash 0731 61.1% #18of 58
CritPtReasoning & knowledge DeepSeek V4 Pro 0813 18.0% #29of 111
Chess PuzzlesReasoning & knowledge DeepSeek V4.1 Flash 1017 48.0% #17of 83
LMCAReasoning & knowledge DeepSeek V4.1 Flash 1017 47.0% #32of 123
FrontierMathMaths DeepSeek V4.1 Flash 1017 71.2% #25of 87
FrontierMath Tier 4Maths DeepSeek V4.1 Flash 1017 46.3% #19of 64
ProofBenchMaths DeepSeek V4 Flash 0731 56.0% #24of 70
OTIS Mock AIMEMaths DeepSeek V4.1 Flash 1017 99.4% #12of 120

Directory

Other labs