DeepSeek-V4-Pro-Max

Name: DeepSeek-V4-Pro-Max
Author: DeepSeek

DeepSeek

DeepSeek-V4-Pro-Max is the maximum reasoning effort mode of DeepSeek-V4-Pro, a 1.6T-parameter MoE model with 49B activated parameters and a 1M-token context window.

Key Specifications

Parameters

1.6T

Context

524.3K

Release Date

April 23, 2026

Average Score

72.3%

API Documentation Repository Model Weights

Timeline

Key dates in the model's history

Announcement

April 23, 2026

Last Update

August 29, 2026

Technical Specifications

Parameters

1.6T

Training Tokens

32.0T tokens

Knowledge Cutoff

Family

Capabilities

MultimodalZeroEval

Pricing & Availability

Input (per 1M tokens)

$1.74

Output (per 1M tokens)

$3.48

Max Input Tokens

524.3K

Max Output Tokens

65.5K

Supported Features

Function CallingStructured OutputCode ExecutionWeb SearchBatch InferenceFine-tuning

Benchmark Results

Model performance metrics across various tests and benchmarks

Programming

Programming skills tests

SWE-Bench Verified

• Self-reported

80.6%

Reasoning

Logical reasoning and analysis

GPQA

Diamond (Pass@1) • Self-reported

90.1%

Other Tests

Specialized benchmarks

BrowseComp

Pass@1 • Self-reported

83.4%

CodeForces

Rating • Self-reported

100.0%

CorpusQA 1M

Accuracy • Self-reported

62.0%

CSimpleQA

Pass@1 • Self-reported

84.4%

FrontierCode 1.1

FrontierCode 1.1 current leaderboard; mergeability score: 17.6%. • Verified

17.6%

FrontierSWE

Claude Code • Verified

29.0%

HMMT Feb 26

Pass@1 • Self-reported

95.2%

Humanity's Last Exam

Pass@1 (w/ tools) • Self-reported

48.2%

IMO-AnswerBench

Pass@1 • Self-reported

89.8%

LiveBench

2026-01-08 • Verified

73.6%

LiveCodeBench

Pass@1 • Self-reported

93.5%

MathArena Apex

Shortlist (Pass@1) • Self-reported

90.2%

MCP Atlas

Public (Pass@1) • Self-reported

73.6%

MMLU-Pro

Max • Self-reported

87.5%

MRCR 1M

MMR • Self-reported

83.5%

SimpleQA

Verified (Pass@1) • Self-reported

57.9%

SWE-bench Multilingual

• Self-reported

76.2%

SWE-Bench Pro

• Self-reported

55.4%

Terminal-Bench 2.0

• Self-reported

67.9%

Toolathlon

Pass@1 • Self-reported

51.8%

License & Metadata

License

mit

Announcement Date

April 23, 2026

Last Updated

August 29, 2026

Similar Models

All Models

DeepSeek-R1

DeepSeek

671.0B

Best score:0.9 (MMLU)

Released:Jan 2025

Price:$3.00/1M tokens

DeepSeek-V2.5

DeepSeek

236.0B

Best score:0.9 (HumanEval)

Released:May 2024

Price:$2.00/1M tokens

DeepSeek-V4-Flash-0423

DeepSeek

284.0B

Best score:0.9 (GPQA)

Released:Apr 2026

Price:$0.14/1M tokens

DeepSeek-V3.2 (Thinking)

DeepSeek

685.0B

Best score:0.8 (GPQA)

Released:Nov 2025

Price:$0.28/1M tokens

DeepSeek-V4-Pro-0813

DeepSeek

1.6T

Released:Aug 2026

Price:$1.32/1M tokens

DeepSeek-V4-Flash-0731

DeepSeek

304.0B

Released:Jul 2026

Price:$0.14/1M tokens

DeepSeek-V3.2-Speciale

DeepSeek

685.0B

Released:Nov 2025

Price:$0.28/1M tokens

DeepSeek-V3.2 (Non-thinking)

DeepSeek

685.0B

Released:Nov 2025

Price:$0.28/1M tokens

Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.