llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsDeepSeek-V4-Flash

DeepSeek model product

DeepSeek-V4-Flash

DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version with substantially stronger agentic capabilities. It retains the V4-Flash architecture and adds an attached DSpark speculative-decoding module for faster inference. The open-weight model supports a 1M-token context window and low, high, and max reasoning-effort levels, and DeepSeek reports that it outperforms the much larger DeepSeek-V4-Pro Preview across its published agent benchmark suite.

Updated Aug 10, 2026. Default version: DeepSeek-V4-Flash-0731

Compare
LLMBoard score71.7DeepSeek-V4-Flash-Max
Coverage100%10 benchmark families
Context window1MTokens
Official input priceN/AOfficial price unavailable

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
DeepSeek-V4-Flash-0731
Released
Jul 31, 2026
Knowledge cutoff
May 1, 2025
Parameters
304B
Context window
1M
Max output
384K
Inputs
text
Outputs
text
Open weights
Yes
License
MIT

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

DeepSeek-V4-Flash-Max category scores

Benchmark results

Published benchmark records for the scored version DeepSeek-V4-Flash-Max.

19 rows
Columns

Show columns

CodeForces1.0116100.0%CAug 7, 2026
CorpusQA 1M0.6220.0%CAug 7, 2026
LiveCodeBench0.927398.6%CAug 7, 2026
MathArena Apex0.92783.3%CAug 7, 2026
MRCR 1M0.82350.0%CAug 7, 2026
HMMT Feb 260.931180.0%CAug 7, 2026
CSimpleQA0.84750.0%CAug 7, 2026
IMO-AnswerBench0.961972.2%CAug 7, 2026
MMLU-Pro0.91112992.2%CAug 7, 2026
SWE-bench Multilingual0.7123466.7%CAug 7, 2026
SWE-Bench Verified0.81610485.4%CAug 7, 2026
MCP Atlas0.7193037.9%CAug 7, 2026
Toolathlon0.5193140.0%CAug 7, 2026
SimpleQA0.3234651.1%CAug 7, 2026
Humanity's Last Exam0.5279271.4%CAug 7, 2026
Terminal-Bench 2.00.6274945.8%CAug 7, 2026
BrowseComp0.7285852.6%CAug 7, 2026
GPQA0.93023387.5%CAug 7, 2026
SWE-Bench Pro0.5384413.9%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

No published Arena match

The default version has no published Arena rows, or its source alias has not been resolved.

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.12 input, $0.21 output per 1M via CrofAI
Tracked offerings
10
10 rows
Columns

Show columns

Alibaba Token Plandeepseek-v4-flash-0731globalN/AN/A1MAug 7, 2026
Alibaba Token Plan (China)deepseek-v4-flash-0731globalN/AN/A1MAug 7, 2026
CrofAIdeepseek-v4-flash-0731global$0.12$0.211MAug 7, 2026
EmpirioLabs AIdeepseek-v4-flash-0731global$0.14$0.281MAug 7, 2026
DigitalOceandeepseek-v4-flash-0731global$0.14$0.281MAug 7, 2026
Requestydeepseek-v4-flash-0731global$0.14$0.281MAug 7, 2026
GreenPTdeepseek-v4-flash-0731global$0.1596$0.3991MAug 7, 2026
Venice AIdeepseek-v4-flash-0731global$0.175$0.351MAug 7, 2026
Charm Hyperdeepseek-v4-flash-0731global$0.20$0.401MAug 7, 2026
Cortecsdeepseek-v4-flash-0731global$0.25$0.301MAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

DeepSeek-V4-Flash versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

3 rows
Columns

Show columns

DeepSeek-V4-Flash-0731Jul 31, 2026N/A304B1M384KYesMIT
DeepSeek V4 FlashApr 24, 2026N/AN/A1M384KYesUnspecified
DeepSeek-V4-Flash-MaxApr 23, 202671.7284B1M393.2KNoMIT

What is DeepSeek-V4-Flash?

A concise description based on the published model registry.

DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version with substantially stronger agentic capabilities. It retains the V4-Flash architecture and adds an attached DSpark speculative-decoding module for faster inference. The open-weight model supports a 1M-token context window and low, high, and max reasoning-effort levels, and DeepSeek reports that it outperforms the much larger DeepSeek-V4-Pro Preview across its published agent benchmark suite.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

DeepSeek-V4-Flash vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

DeepSeek-V4-FlashvsQwen3.6 PlusDeepSeek-V4-FlashvsQwen3.6 27BDeepSeek-V4-FlashvsNemotron 3 UltraDeepSeek-V4-FlashvsKimi K2.5DeepSeek-V4-FlashvsGPT-5DeepSeek-V4-FlashvsLlama 3.1 405B

Models similar to DeepSeek-V4-Flash

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#32-2.2
DE

DeepSeek-V2.5

DeepSeek

69.5 LLMBoard

DetailsCompare
#18+3.8
DE

DeepSeek-V3.2

DeepSeek

75.5 LLMBoard

DetailsCompare
#12+8.4
DE

DeepSeek-V4-Pro

DeepSeek

80.1 LLMBoard

DetailsCompare
#101-27.6
DE

DeepSeek-R1

DeepSeek

44.1 LLMBoard

DetailsCompare
#119-33.6
DE

DeepSeek-V3

DeepSeek

38.1 LLMBoard

DetailsCompare
#126-35.7
DE

DeepSeek-V3.1

DeepSeek

36.0 LLMBoard

DetailsCompare

FAQ

Common questions about DeepSeek-V4-Flash.

When was DeepSeek-V4-Flash released?

DeepSeek-V4-Flash's default version was released on Jul 31, 2026.

How much does DeepSeek-V4-Flash cost?

No official standard PAYG price is currently available for DeepSeek-V4-Flash. The lowest tracked third-party offer starts at $0.12 input and $0.21 output via CrofAI.

Who created DeepSeek-V4-Flash?

DeepSeek-V4-Flash is published under DeepSeek in the model registry.

What is the context window for DeepSeek-V4-Flash?

The default version has a 1M token context window.

Is DeepSeek-V4-Flash open weight?

Yes. The default version is marked as open weight under MIT.

How many API providers offer DeepSeek-V4-Flash?

10 published provider offerings are linked to the default version.

What models should I compare DeepSeek-V4-Flash with?

Nearby ranked alternatives include Qwen3.6 Plus, Qwen3.6 27B, Nemotron 3 Ultra.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai