The AI arena is free today

Open Superagent

DeepSeek-V3 vs DeepSeek-V4-Pro-0813

Comparing DeepSeek-V3 and DeepSeek-V4-Pro-0813 across benchmarks, pricing, and capabilities.

DeepSeek · DeepSeek · Updated for 2026

Which is better?

DeepSeek-V3 and DeepSeek-V4-Pro-0813 trade strengths across price, capabilities, and technical limits. The better choice depends on the workload.

On price, DeepSeek-V3 is roughly 1.1x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

DeepSeek-V4-Pro-0813 also accepts a larger context window (1,048,576 input tokens), making it the stronger choice for long documents and large codebases.

Based on current benchmark, pricing, and model metadata for 2026.

Choose DeepSeek-V3

  • cost matters — it's about 1.1x cheaper per token

Choose DeepSeek-V4-Pro-0813

  • you process long inputs — it offers a 1,048,576 token context window
  • you want the most recent training data — it shipped Aug 2026

At a glance

The differences that matter most.

DeepSeek-V3
DeepSeek
DeepSeek-V4-Pro-0813
DeepSeek
Benchmark wins
—
—
Input price
$0.27 / M
$0.43 / M
Output price
$1.10 / M
$0.87 / M
Context window
131,072
1,048,576
Released
Dec 2024
Aug 2026
License
MIT + Model License (Commercial use allowed)
MIT

Performance Benchmarks

Comparative analysis across standard metrics

No common benchmarks found

DeepSeek-V3 and DeepSeek-V4-Pro-0813don't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Arena Performance

Playground indexes and blind preference scores

Pricing Analysis

Price comparison per million tokens

DeepSeek-V3 costs less

For input processing, DeepSeek-V3 ($0.27/1M tokens) is 1.6x cheaper than DeepSeek-V4-Pro-0813 ($0.43/1M tokens).

For output processing, DeepSeek-V3 ($1.10/1M tokens) is 1.3x more expensive than DeepSeek-V4-Pro-0813 ($0.87/1M tokens).

In conclusion, DeepSeek-V4-Pro-0813 is more expensive than DeepSeek-V3.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Mon Aug 24 2026 • llm-stats.com
DeepSeek
DeepSeek-V3
Input tokens$0.27
Output tokens$1.10
Best providerDeepSeek
DeepSeek
DeepSeek-V4-Pro-0813
Input tokens$0.43
Output tokens$0.87
Best providerDeepSeek
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

929.0B diff

DeepSeek-V4-Pro-0813 has 929.0B more parameters than DeepSeek-V3, making it 138.5% larger.

DeepSeek
DeepSeek-V3
671.0Bparameters
DeepSeek
DeepSeek-V4-Pro-0813
1.6Tparameters
671.0B
DeepSeek-V3
1600.0B
DeepSeek-V4-Pro-0813

Context Window

Maximum input and output token capacity

DeepSeek-V4-Pro-0813 accepts 1,048,576 input tokens compared to DeepSeek-V3's 131,072 tokens. DeepSeek-V4-Pro-0813 can generate longer responses up to 393,216 tokens, while DeepSeek-V3 is limited to 131,072 tokens.

DeepSeek
DeepSeek-V3
Input131,072 tokens
Output131,072 tokens
DeepSeek
DeepSeek-V4-Pro-0813
Input1,048,576 tokens
Output393,216 tokens
Mon Aug 24 2026 • llm-stats.com

License

Usage and distribution terms

DeepSeek-V3 is licensed under MIT + Model License (Commercial use allowed), while DeepSeek-V4-Pro-0813 uses MIT.

License differences may affect how you can use these models in commercial or open-source projects.

DeepSeek-V3

MIT + Model License (Commercial use allowed)

Open weights

DeepSeek-V4-Pro-0813

MIT

Open weights

Release Timeline

When each model was launched

DeepSeek-V3 was released on 2024-12-25, while DeepSeek-V4-Pro-0813 was released on 2026-08-13.

DeepSeek-V4-Pro-0813 is 20 months newer than DeepSeek-V3.

DeepSeek-V3

Dec 25, 2024

1.7 years ago

DeepSeek-V4-Pro-0813

Aug 13, 2026

1 weeks ago

1.6yr newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

DeepSeek-V3 is available from DeepSeek. DeepSeek-V4-Pro-0813 is available from DeepSeek, DeepInfra, Novita, Together.

DeepSeek-V3

deepseek logo
DeepSeek
Input Price:Input: $0.27/1MOutput Price:Output: $1.10/1M

DeepSeek-V4-Pro-0813

deepseek logo
DeepSeek
Input Price:Input: $0.43/1MOutput Price:Output: $0.87/1M
deepinfra logo
Deepinfra
Input Price:Input: $1.30/1MOutput Price:Output: $2.60/1M
novita logo
Novita
Input Price:Input: $1.32/1MOutput Price:Output: $3.96/1M
together logo
Together
Input Price:Input: $1.32/1MOutput Price:Output: $3.96/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against DeepSeek-V3 and DeepSeek-V4-Pro-0813 side-by-side, then vote on the output you prefer.

DeepSeek-V3
✓ Preferred
DeepSeek-V4-Pro-0813
Open in Playground

FAQ

Common questions about DeepSeek-V3 vs DeepSeek-V4-Pro-0813.

Which is better, DeepSeek-V3 or DeepSeek-V4-Pro-0813?

DeepSeek-V3 (DeepSeek) and DeepSeek-V4-Pro-0813 (DeepSeek) each have strengths in different areas. Compare their benchmark scores, pricing, context windows, and capabilities above to determine which fits your needs.

How does DeepSeek-V3 compare to DeepSeek-V4-Pro-0813 in benchmarks?

DeepSeek-V3 scores DROP: 91.6%, CLUEWSC: 90.9%, MATH-500: 90.2%, MMLU-Redux: 89.1%, MMLU: 88.5%. DeepSeek-V4-Pro-0813 scores Terminal-Bench 2.1: 87.9%, CyberGym: 83.3%, Toolathlon: 74.1%, DSBench-FullStack: 71.1%, DSBench-Hard: 67.2%.

Is DeepSeek-V3 cheaper than DeepSeek-V4-Pro-0813?

DeepSeek-V3 is 1.6x cheaper for input tokens. DeepSeek-V3 costs $0.27/M input and $1.10/M output via deepseek. DeepSeek-V4-Pro-0813 costs $0.43/M input and $0.87/M output via deepseek.

What are the context window sizes for DeepSeek-V3 and DeepSeek-V4-Pro-0813?

DeepSeek-V3 supports 131K tokens and DeepSeek-V4-Pro-0813 supports 1.0M tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between DeepSeek-V3 and DeepSeek-V4-Pro-0813?

Key differences include context window (131K vs 1.0M), input pricing ($0.27 vs $0.43/M), licensing (MIT + Model License (Commercial use allowed) vs MIT). See the full comparison above for benchmark-by-benchmark results.

Related comparisons