NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/DeepSeek V4 Pro 0813
DeepSeek logo

DeepSeek V4 Pro 0813

by DeepSeek · Released Aug 2026

1M Context
62.6
avg score
Rank #75
Compare
Better than 77% of all models
Context
1.0M tokens (~524 books)
Input $/1M
$0.11
Output $/1M
$4.44
Type
text
License
Proprietary
Benchmarks
22 tested
Data as of
About

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Tested on 22 benchmarks · BenchGecko score 62.6. Top scores: OTIS Mock AIME 2024-2025 (98.6%), GPQA diamond (92.6%), ARC-AGI (90.5%).

Looking for similar performance at lower cost?
GLM 5.3 scores 63.0 (101% as good) at $0.07/1M input · 37% cheaper
Capabilities
coding
42.7
#131 globally
reasoning
75.9
#34 globally
math
64.5
#77 globally
knowledge
62.9
#44 globally
agentic
47.3
#32 globally
general
57.6
#24 globally
speed
24.9
#103 globally
Benchmark Scores
Compare All
Tested on 22 benchmarks · Ranked across 7 categories
Score Distribution (all 326 models)
0255075100
▲ You are here
codingCompare coding →
WeirdML

Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.

66.2·
Mirrorcode
33.3·
Frontiercode
28.6·
reasoningCompare reasoning →
ARC-AGI

Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.

90.5·
ARC-AGI-2

ARC-AGI 2, harder sequel to ARC. More complex abstract reasoning patterns that test generalization ability beyond training data.

61.3·
mathCompare math →
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

98.6·
FrontierMath-Tiers-1-3-v2-Private
68.0·
FrontierMath-Tier-4-v2-Private
26.8·
Quick compare:z-ai logovs GLM 5.1xAI logovs Grok 4.6Alibaba Qwen logovs Qwen3.6 Plus
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · DeepSeek DeepSeek V4
Apr 2026
68.6
$0.09/M in1.0Mctx16 benchmarks
Jul 2026
58.9-9.7
$0.04/M in(-0.05)1.0Mctx15 benchmarks
Jul 2026
$0.05/M in(+0.00)1.0Mctx
Jul 2026
$0.00/M in(-0.05)1.0Mctx
Aug 2026
$0.44/M in(+0.44)1.0Mctx
Aug 2026
$0.11/M in(-0.33)1.0Mctx
Apr 2026
60.5+1.6
$0.88/M in(+0.77)1.0Mctx34 benchmarks
Aug 2026
62.6+2.1
$0.11/M in(-0.77)1.0Mctx22 benchmarks
Aug 2026
$0.66/M in(+0.55)1.0Mctx
See the full DeepSeek V4 family →
Recently Happened
DeepSeek V4 Pro 0813 pricing dropped 5%
Nov 8, 2026
DeepSeek V4 Pro 0813 pricing dropped 91%
Nov 4, 2026
DeepSeek V4 Pro 0813 pricing increased 100%
Oct 26, 2026
DeepSeek V4 Pro 0813 pricing dropped 50%
Oct 17, 2026
DeepSeek V4 Pro 0813 pricing increased 140%
Oct 6, 2026
DeepSeek V4 Pro 0813 pricing increased 230%
Sep 30, 2026
Similar Models
z-ai logo
GLM 5.1
z-ai
62.6$1.33/1M
xAI logo
Grok 4.6
xAI
62.6$2.00/1M
Alibaba Qwen logo
Qwen3.6 Plus
Alibaba Qwen
62.3$0.33/1M
Links
Info
DeepSeekPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@DeepSeek
BenchGecko API
deepseek-v4-pro-0813
Specifications
  • Typetext
  • Context1.0M tokens (~524 books)
  • ReleasedAug 2026
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.005
Available On
DeepSeek logoDeepSeek$0.11
Categories
codingreasoningmathknowledgeagenticgeneralspeed
Learn More
context-windowtransformertokens
Share & Export
Tweet
Related Models
z-ai logoGLM 5.1
62.6
xAI logoGrok 4.6
62.6
Alibaba Qwen logoQwen3.6 Plus
62.3
moonshotai logoKimi K2.7 Code
62.3
DeepSeek V4 Pro 0813 is a proprietary text AI model by DeepSeek, released in August 2026. It has an average benchmark score of 62.6. Context window: 1M tokens.

Related Models

GLM 5.1 · z-aiGrok 4.6 · xAIQwen3.6 Plus · Alibaba QwenKimi K2.7 Code · moonshotaiGLM 5.3 · z-ai

Benchmarks

OTIS Mock AIME 2024-2025GPQA diamondARC-AGIDtbenchFrontierMath-Tiers-1-3-v2-Private

Related Pages

DeepSeek · ProviderDeepSeek · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-11-11

  • DeepSeek V4 Pro 0813 by DeepSeek. BenchGecko score 62.6, rank 75 of 326 scored models (normalized average of public benchmark scores).
  • List price $0.11 input · $4.44 output per 1M tokens (as of 2026-11-11).
  • Sold by 24 providers (as of 2026-11-11): Relace (fp4) $0.0999 in / $8.00 out · Wafer (mxfp4) $0.11 in / $4.44 out · Wafer (mxfp4) $0.28 in / $4.30 out · StreamLake $0.66 in / $1.98 out · Novita (fp8) $0.99 in / $2.97 out · and 19 more. Every provider
  • Gecko Tests · Gecko Score 39 (rank 41): Who Are You E (Sometimes says it is OpenAI or Anthropic) · Censorship Index E (Refuses or dodges 10%) · Knowledge Horizon C (Knows news up to Nov 2025) · Tokenizer Tax A (17% more tokens outside English).

How to cite · data as of 2026-11-11

DeepSeek V4 Pro 0813 · benchmarks, pricing and providers. BenchGecko, data as of 2026-11-11. https://benchgecko.ai/model/deepseek-v4-pro-0813

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP