DataLearner logo
DE

DeepSeek-V4-Pro-Base

Foundation modelDeepSeek V4

DeepSeek V4 Pro Base

Release date: 2026-04-24Knowledge cutoff: 2025-05121
Live demoGitHubHugging FaceCompare
Parameters
1.6T
Context length
1M
Chinese support
Supported
Reasoning ability

DeepSeek V4 Pro Base is an AI model published by DeepSeek-AI, released on 2026-04-24, for Foundation model, with 1.6T parameters, and 1M context length, with a 51.50 score on LongBench v2.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

DeepSeek-V4-Pro-Base

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
1M tokens
Max output length
375K tokens
Model type
Foundation model
Modality (in / out)
Text → Text
Release date
2026-04-24
Model file size
No data
MoE architecture
Yes
Total params / Active params
1.6T / 49B
Knowledge cutoff
2025-05
DeepSeek-V4-Pro-Base

Open source & experience

Code license
Weights license
MIT License- Commercial use permitted
GitHub repo
GitHub link unavailable
Live demo
No live demo
DeepSeek-V4-Pro-Base

Official resources

Paper
DataLearnerAI blog
No blog post yet
DeepSeek-V4-Pro-Base

API details

API speed
4/5
No public API pricing yet.
DeepSeek-V4-Pro-Base

Benchmark Results

DeepSeek-V4-Pro-Base currently shows benchmark results led by LongBench v2 (10 / 11, score 51.50). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

Long Context

1 evaluations
Benchmark / mode
Score
Rank/total
LongBench v2
Standard Mode
51.50
10 / 11

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

DeepSeek-V4-Pro-Base

Publisher

DeepSeek V4 Pro Base

Model Overview

DeepSeek V4 Pro Base is an AI model published by DeepSeek-AI, released on 2026-04-24, for Foundation model, with 1.6T parameters, and 1M context length, with a 51.50 score on LongBench v2.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code