DeepSeek

DeepSeek-V4-Flash-0731

SIZE304B

87Quality

Text

Downloads4.3M/mo

Likes4.1K

Language model from DeepSeek, 304B parameters.

Open weightsMIT960/1044

Drag to turn

DeepSeekTextPromo

DeepSeek-V4-Flash-0731

Language model from DeepSeek, 304B parameters.

deepseek-ai/DeepSeek-V4-Flash-0731

Type: Text
Quality: 87 · Top 13% on the Epoch Capabilities Index
Parameters: 304B (304,180,418,494)
Downloads: 4.3M in the last 30 days
Likes: 4.1K
Access to weights: Open download
On Hugging Face since: Jul 31, 2026
Takes in: Text
Puts out: Text
Access: Open weights
License: MIT
Rarity: Promo
Set number: 960/1044

Open on Hugging Face Quality 87 Where to run it 55 Evolution 1/2 Race it 110 tok/s Meet its creature Battle Qwen3-1.7B

License read from the model’s Hugging Face card. Stats from DeepSeek’s official Hugging Face account, refreshed daily.

How good is it?

Public leaderboard scores for DeepSeek-V4-Flash-0731, refreshed daily from Epoch AI and LMArena.

Top 13% of the 277 models on the Epoch Capabilities Index: #37.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Epoch Capabilities Index#37 of 277
One number fitted from dozens of hard benchmarks, from science questions to agentic coding.154.5 index

Benchmarks Epoch AI runs

Scores from Epoch AI, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

49 providers sell DeepSeek-V4-Flash-0731 through an API, and 6 Hugging Face hosts serve it. Prices are per million tokens, cheapest first.

CheapestMerge Gateway$0.035 in · $0.07 out
Free to try4 providersAlibaba Token Plan, Alibaba Token Plan (China), Nvidia, …
Fastest on Hugging FaceBaseten110 tokens/s

API providers

Provider	Input	Output	Context
Alibaba Token PlanFree`deepseek-v4-flash-0731`	Free	Free	1M
Alibaba Token Plan (China)Free`deepseek-v4-flash-0731`	Free	Free	1M
NvidiaFree`deepseek-ai/deepseek-v4-flash-0731`	Free	Free	1M
SCNet Token PlanFree`DeepSeek-V4-Flash-0731`	Free	Free	1M
Merge GatewayCheapest paid`deepseek/deepseek-v4-flash-0731`	$0.035	$0.07	1.05M
engy`deepseek-v4-flash-0731`	$0.045	$0.09	1.05M
CrofAI`deepseek-v4-flash-0731`	$0.08	$0.10	1M
OpenRouter`deepseek/deepseek-v4-flash-0731`	$0.15	$0.15	1.05M
Vercel AI Gateway`deepseek/deepseek-v4-flash-0731`	$0.076	$0.15	1M
NanoGPT`deepseek/deepseek-v4-flash-0731`	$0.05	$0.16	1.05M

Show 39 more providers

Provider	Input	Output	Context
Deep Infra`deepseek-ai/DeepSeek-V4-Flash-0731`	$0.06	$0.18	1.05M
Eden AI`deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731`	$0.06	$0.18	1.05M
Ambient`deepseek/deepseek-v4-flash-0731`	$0.08	$0.18	1.05M
Boundless`dsv4`	$0.04	$0.21	1.05M
Vultr`deepseek-v4-flash-0731`	$0.10	$0.25	1.05M
Baseten`deepseek-ai/DeepSeek-V4-Flash-0731`	$0.13	$0.26	1.05M
Perplexity Agent`deepseek/deepseek-v4-flash-0731`	$0.13	$0.26	1M
Venice AI`deepseek-v4-flash-0731`	$0.13	$0.26	1M
RunInfra`deepseek-ai/DeepSeek-V4-Flash-0731`	$0.13	$0.27	1.05M
OpenReason`deepseek-ai/deepseek-v4-flash-0731`	$0.14	$0.27	1M
Bothub`deepseek-v4-flash-0731`	$0.10	$0.28	1M
CoreWeave`deepseek-ai/DeepSeek-V4-Flash-0731`	$0.13	$0.28	262K
Inceptron`deepseek-ai/DeepSeek-V4-Flash-0731`	$0.13	$0.28	1.05M
AMD`DeepSeek-V4-Flash`	$0.14	$0.28	1.05M
DigitalOcean`deepseek-v4-flash-0731`	$0.14	$0.28	1.05M
Nebius Token Factory`deepseek-ai/DeepSeek-V4-Flash-0731`	$0.14	$0.28	1.02M
Together AI`deepseek-ai/DeepSeek-V4-Flash-0731`	$0.14	$0.28	1.05M
AIHubMix`deepseek-v4-flash-0731`	$0.14	$0.28	1M
Melious`deepseek-v4-flash-0731`	$0.12	$0.29	1M
OrcaRouter`deepseek/deepseek-v4-flash-0731`	$0.15	$0.29	1M
Moark`deepseek-v4-flash-0731`	$0.15	$0.30	1M
TensorX`deepseek/deepseek-v4-flash-0731`	$0.25	$0.30	1.05M
GreenPT`deepseek-v4-flash-0731`	$0.16	$0.40	1M
Alibaba`deepseek-v4-flash-0731`	$0.20	$0.40	1M
Cortecs`deepseek-v4-flash-0731`	$0.082	$0.41	1.05M
Requesty`deepseek-v4-flash-0731`	$0.28	$0.56	1.05M
Ollama Cloud`deepseek-v4-flash:0731`	$0.22	$0.66	1.05M
SiliconFlow`deepseek-ai/DeepSeek-V4-Flash-0731`	$0.22	$0.66	1M
Scaleway`deepseek-v4-flash-0731`	$0.47	$0.94	256K
IteraCompute`deepseek/deepseek-v4-flash-0731`	$0.29	$1.16	1.05M
EmpirioLabs AI`deepseek-v4-flash-0731`	$0.42	$1.27	1M
Charm Hyper`deepseek-v4-flash-0731`	$0.44	$1.32	1M
Cloudflare Workers AI`@cf/deepseek-ai/deepseek-v4-flash-0731`	$0.44	$1.32	1.05M
Kilo Gateway`deepseek/deepseek-v4-flash-0731`	$0.44	$1.32	1.05M
Novita AI`deepseek/deepseek-v4-flash-0731`	$0.44	$1.32	1.05M
Ofox`deepseek/deepseek-v4-flash-0731`	$0.44	$1.32	1M
Prime Inference`deepseek/deepseek-v4-flash-0731`	$0.44	$1.32	1.05M
Standard Compute`deepseek/deepseek-v4-flash-0731`	$0.44	$1.32	1M
Volcengine Ark`deepseek-v4-flash-ga-260731`	$0.45	$1.34	1M

Hugging Face Inference Providers

Host	Input	Output	Context	Speed	First token
DeepInfraTools	$0.06	$0.18	1.05M	40 tok/s	0.7s
BasetenFastestTools	$0.13	$0.26	1.05M	110 tok/s	1.7s
Together AITools	$0.14	$0.28	1.05M	7 tok/s	1.8s
NovitaTools	$0.44	$1.32	1.05M	98 tok/s	0.8s
Featherless	—	—	—	—	—
ScalewayTools	—	—	—	32 tok/s	1.3s

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.