Nano GPT logo
NanoGPT

DeepSeek V4 Pro 0813 Thinking

DeepSeek V4 Pro 0813 Thinking enables reasoning by default on the general-availability release of DeepSeek V4 Pro, built for coding, tool use, cybersecurity, automation, and long-horizon agent workflows. DeepSeek reports strong gains over the preview and scores above Opus 4.8 on Terminal Bench 2.1, Cybergym, DeepSWE, and AutomationBench. It supports a 1M-token context window.

  • Reasoning
  • Tool Calling
  • Structured Output

Added Aug 12, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.37
Output
$2.93
Cache read
$0.088
Compare provider prices

Specifications

Context window
1M
Max output
384K
Parameters
1.6T / 49B
Total / active
Avg output (7d)
2.2K tokens
Longer than 93% of models

Benchmarks

Sourced from Artificial Analysis.

Intelligence Index

36.0

Better than 90% of models compared

Coding Index

68.8

Better than 80% of models compared

Agentic Index

41.3

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 89% of models compared

CritPt

Research-level physics reasoning

18.0%

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

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

49.1%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

94.8%

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 88% of models compared

GDPval-AA (unversioned / legacy)

Economically valuable tasks

47.7%

Last updated Oct 12, 2026

Artificial Analysis

Providers

Choose explicit providers for this model. Auto routing remains available as the default option.

Loading provider options…