DeepSeek V4 Flash by Hugging Face | AI model information

$10 off the fastest Kimi K3 and GLM 5.2$10 off the fastest Kimi K3 and GLM 5.2

Discuss

Model details

DeepSeek V4 Flash

Hugging Facedeepseek-ai/DeepSeek-V4-Flashdeepseek-flash

Open provider page Provider docs

Quick Info

Provider: Hugging Face
Model key: deepseek-ai/DeepSeek-V4-Flash
Release date: Apr 24, 2026

Cost

Input token cost: $0.14
Output token cost: $0.28

Limits

Output tokens: 384,000 tokens
Context window

Latest news about DeepSeek V4 Flash

Videos about DeepSeek V4 Flash

Recent tweets and retweets from Hugging Face

Aug 6, 2026, 1:26 PMUTC

Uploaded a dataset of 1,080,814 public domain images, mostly from 19th-century books, to the Hub. huggingface.co/datasets/bigl…

Aug 7, 2026, 4:00 PMUTC

How AI agents reproduced ICML 2026 papers nitter.net/i/broadcasts/1OxwbbdvR… Link Hugging Face How AI agents reproduced ICML 2026 papers https://nitter.net/i/broadcasts/1OxwbbdvRygJB

Aug 6, 2026, 4:24 PMUTC

We're the fastest provider for DeepSeek V4 Flash and Kimi K3 on @huggingface, which measures based on real production traffic vs test data.

Aug 7, 2026, 9:44 AMUTC

Building competitive AI from Korea for the global open-source community. SK Telecom’s A.X K2 is a 688B MoE with 256K context, excelling in math and long-context reasoning. Apache 2.0, open for commercial use. 🔗huggingface.co/skt/A.X-K2

Aug 6, 2026, 8:37 AMUTC

every 3D mesh is kind of a compiled binary: printable, usable, but frozen. you can't just "make this hole 2mm wider" Cadena is just out to fix this, a decompiler of 3D meshes - converting it into an editable CAD program, step by step 🧊 app on spaces ▶️…