DeepSeek V4 Flash by Nvidia | AI model information

$10 off Synthetic - fastest OpenCode provider$10 off Synthetic - the fastest Kimi K2.6 and GLM 5.1 provider Discuss

Model details

DeepSeek V4 Flash

Nvidiadeepseek-ai/deepseek-v4-flashdeepseek-flash

Open provider page Provider docs

Quick Info

Provider: Nvidia
Model key: deepseek-ai/deepseek-v4-flash
Release date: Apr 24, 2026
Last updated: Apr 24, 2026

Cost

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

Limits

Output tokens: 393,216 tokens
Context window

Latest news about DeepSeek V4 Flash

No articles yet. Fetch the latest news to show it here.

Videos about DeepSeek V4 Flash

Recent tweets and retweets from Nvidia

Jun 9, 2026, 10:58 PMUTC

At #WWDC26, NVIDIA Confidential Computing on @GoogleCloud is enabling Apple to extend their groundbreaking Private Cloud Compute service to third-party data centers for the first time. NVIDIA is collaborating with Apple and Google to power Apple Intelligence workloads built…

Jun 9, 2026, 10:24 PMUTC

Voice AI calls just got a privacy upgrade. 🔒 @DeepgramAI now runs fully on-prem with encrypted audio and model weights, powered by @fortanix Confidential AI and NVIDIA Confidential Computing. Read the press release: nvda.ws/43KdoyN

Jun 9, 2026, 7:33 PMUTC

🔗 nvda.ws/4vHphRZ

Jun 9, 2026, 7:33 PMUTC

This is what happens when GTC lands in Taipei. 🇹🇼 Keynote reveals, hands-on demos, real connections, and Jensen fans everywhere. It's not just a conference. It's where the AI era gets built together — and the energy of the community proves it. Join us at our next GTC —…

Jun 9, 2026, 5:05 PMUTC

🔗 To learn more, visit nvda.ws/43WJvuT