DeepSeek V4 Pro

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with a 1M-token context window, built for advanced reasoning, coding, long-horizon agent workflows, knowledge, math, and software engineering tasks.

Reasoning
Tool Calling
Structured Output

Added Apr 24, 2026

Model weights

Pricing

Auto routing · per 1M tokens

Input: $1.10
Output: $2.20
Cache read: $0.11

Compare provider prices

Specifications

Context window: 1M
Max output: 384K
Parameters: 1.6T / 49B; Total / active
Avg output (7d): 473 tokens; Longer than 42% of models

Benchmarks

Artificial Analysis

LMArena

Vectara

Design Arena

Sourced from Artificial Analysis.

Intelligence Index

36.0

Better than 89% of models compared

Coding Index

68.8

Better than 80% of models compared

Agentic work

AutomationBench-AA

Workflow automation with guardrail penalties

56.7%

Better than 78% of models compared

AA-Briefcase

Agentic knowledge work (Elo)

1256 Elo

Better than 66% of models compared

GDPval-AA v2

Economically valuable tasks (Elo)

1454 Elo

Better than 80% of models compared

Document reasoning

GDP.pdf

Professional PDF reasoning: all-pass rate

11.4%

Better than 47% of models compared

AA-LCR v1.1

Long context reasoning with updated grading

80.3%

Better than 88% of models compared

MLCR-AA

Medical long-context reasoning

17.8%

Better than 60% of models compared

Reasoning

HLE

Humanity's Last Exam

41.0%

Better than 88% of models compared

Coding

Terminal-Bench v4.0

Practical coding and terminal tasks

14.1%

Better than 68% of models compared

SciCode

Python programming for scientific computing

51.0%

Better than 58% of models compared

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

92.8%

Better than 95% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

80.3%

Better than 87% of models compared

Last updated Oct 14, 2026