Model

DeepSeek-V4-Pro (Think High)

OPEN

DeepSeek · DeepSeek-V4 family · released Apr 24, 2026

Fast/low-latency mode of the DeepSeek-V4-Pro preview checkpoint, the default reasoning tier a user gets without selecting anything. (middle reasoning-effort tier, called 'Think High' on the official HF model-card benchmark table).

ReasoningCodingVisionFunction callingTool useAgentic

2351.3

Elo · rank #46

Parameters

1600B

Active params

49B (MoE)

Context

1M tokens

Architecture

Mixture-of-Experts (1.6T total / 49B active), hybrid Compressed Sparse Attention + Heavily Compressed Attention, Manifold-Constrained Hyper-Connections, Muon optimizer

License

MIT

Languages

—

API price (in/out)

$0.435 / $0.87

Modalities

text

Benchmark results

Bar shows position within the tracked field; marker = field best

Agents' Last ExamAgents27.6%#19

best: GPT-6 Astra · 59.3%

BrowseCompAgents80.4%#18

best: Kimi K3 · 91.2%

CodeforcesCoding2919#3

best: DeepSeek-V4-Pro (Think Max) · 3206

GPQA DiamondReasoning89.1%#36

best: GPT-6 Astra · 96.0%

Humanity's Last ExamReasoning34.5%#41

best: Claude Opus 5 · 64.7%

LiveCodeBenchCoding89.8%#8

best: DeepSeek-V4-Pro (Think Max) · 93.5%

MMLU-ProKnowledge87.1%#13

best: Claude Fable 5 · 91.5%

SWE-bench ProCoding54.4%#36

best: Claude Fable 5.1 · 81.2%

SWE-bench VerifiedCoding79.4%#22

best: Claude Opus 5 · 96.0%

Terminal-Bench 2.0Coding63.3%#40

best: Gemini 3.8 Flash · 89.4%

Run it locally

VRAM @ Q4

—

VRAM @ FP16

—

Fits on (Q4)

Multi-node cluster required

Throughput data unavailable.

Quantizations

—

Fine-tune it

Permissive

QLoRA1088.0 GB8× H200 141GB

LoRA3408.0 GBbeyond 8× B200

Full fine-tune25680.0 GBbeyond 8× B200

QLoRA SFT on ~10k samples ≈ $25.34 (8× H200 141GB)

Plan a fine-tune →

DeepSeek-V4 family

Elo progression across releases

DeepSeek-V4-Flash (Non-Think)Apr 20261596.6 DeepSeek-V4-Flash (Think High)Apr 20262202.0 DeepSeek-V4-Flash (Think Max)Apr 20262289.9 DeepSeek-V4-Pro (Non-Think)Apr 20261643.5 DeepSeek-V4-Pro (Think High)Apr 20262351.3 DeepSeek-V4-Pro (Think Max)Apr 20262487.3 DeepSeek-V4-Flash-0731Jul 20262697.3

Resources

HFdeepseek-ai/DeepSeek-V4-Pro DOCShttps://api-docs.deepseek.com/news/news260424/APIAvailable via DeepSeek API

API price $0.435/$0.87 · each benchmark row carries its own source badge (see methodology)