DeepSeek V4 Pro by Deep Infra | 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 Pro

Deep Infradeepseek-ai/DeepSeek-V4-Prodeepseek-thinking

Open provider page Provider docs

Quick Info

Provider: Deep Infra
Model key: deepseek-ai/DeepSeek-V4-Pro
Release date: Apr 24, 2026
Last updated: Apr 24, 2026

Cost

Input token cost: $1.30
Output token cost: $2.60

Limits

Output tokens: 16,384 tokens
Context window

Latest news about DeepSeek V4 Pro

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

Videos about DeepSeek V4 Pro

Recent tweets and retweets from Deep Infra

Jun 10, 2026, 3:18 PMUTC

Big upgrade to @bria_ai_'s video background removal on DeepInfra — shipping today. 2x better quality · 9x faster · 33x cheaper 26 fps / 38ms per frame on L40S. Smarter foreground detection — now recognizes mics, desks, and products. Video Video

Jun 10, 2026, 3:18 PMUTC

Play around with it here: deepinfra.com/Bria/video_rem…

Jun 6, 2026, 12:28 PMUTC

Lol Video

Jun 6, 2026, 12:28 PMUTC

9gag.com/gag/amoeE82 is the source.

Jun 4, 2026, 2:45 PMUTC

We just added @NVIDIA Nemotron 3.x to DeepInfra — Day 0. Two open and highly efficient models, live now: → Nemotron 3 Ultra: Frontier reasoning for long-running agents with, up to 5x faster inference and up to 30% lower cost → Nemotron 3.5 Content Safety: 4B multimodal,…