DeepSeek-V4-Pro-0813 vs Hy3

DeepSeek-V4-Pro-0813 leads the LLM Stats Score 52.0 to 43.2. Hy3 is 2.2x cheaper per token.

DeepSeek · Tencent · Updated for 2026

Which is better?

DeepSeek-V4-Pro-0813 leads the overall LLM Stats Score 52.0 to 43.2, ranking #12 overall.

In the 6 individual benchmarks reported for both models, DeepSeek-V4-Pro-0813 wins 5; this is a narrower head-to-head signal than the composite indexes.

On price, Hy3 is roughly 2.2x 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 LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose DeepSeek-V4-Pro-0813

overall performance matters — it scores 52.0 and ranks #12 on LLM Stats
your work emphasizes reasoning and coding — it leads those capability indexes
you value its reported benchmark strengths — it wins 5 of 6 exact shared results
you process long inputs — it offers a 1,048,576 token context window
you want the most recent training data — it shipped Aug 2026

Choose Hy3

cost matters — it's about 2.2x cheaper per token

At a glance

The differences that matter most.

Better token value: Hy3

Core performance indexes

LLM Stats Score

52.0

#12 · 11 evals

Best

43.2

#41 · 29 evals

Reasoning

50.0

#15 · 7 evals

Best

43.1

#42 · 23 evals

Coding

40.4

#12 · 5 evals

Best

33.2

#35 · 10 evals

Agents

37.6

#13 · 8 evals

Best

27.2

#44 · 14 evals

Cost, coverage & limits

Benchmark wins

5 of 6

Best

1 of 6

Input price

$0.43 / M

$0.14 / M

Best

Output price

$0.87 / M

$0.58 / M

Best

Context window

1,048,576

Best

262,144

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared

Index

DeepSeek-V4-Pro-0813

Hy3

Math

41.0#10 · 3 evals

36.9#33 · 8 evals

Tool use

31.3#10 · 4 evals

21.4#50 · 3 evals

Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

12 reported for DeepSeek-V4-Pro-0813 · 31 for Hy3

6 shared

DeepSeek-V4-Pro-0813 outperforms in 5 benchmarks (DeepSWE, Humanity's Last Exam (with tools, text-only), NL2Repo, Terminal-Bench 2.1, Toolathlon), while Hy3 is better at 1 benchmark (Humanity's Last Exam (no tools, text-only)).

DeepSeek-V4-Pro-0813 significantly outperforms across most benchmarks.

Thu Sep 17 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Hy3 costs less

For input processing, DeepSeek-V4-Pro-0813 ($0.43/1M tokens) is 3.1x more expensive than Hy3 ($0.14/1M tokens).

For output processing, DeepSeek-V4-Pro-0813 ($0.87/1M tokens) is 1.5x more expensive than Hy3 ($0.58/1M tokens).

In conclusion, DeepSeek-V4-Pro-0813 is more expensive than Hy3.*

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

Lowest available price from all providers

Thu Sep 17 2026 • llm-stats.com

DeepSeek-V4-Pro-0813

Input tokens$0.43

Output tokens$0.87

Best providerDeepSeek

Hy3

Input tokens$0.14

Output tokens$0.58

Best providerDeepinfra

Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

1305.0B diff

DeepSeek-V4-Pro-0813 has 1305.0B more parameters than Hy3, making it 442.4% larger.

DeepSeek-V4-Pro-0813

1.6Tparameters

Hy3

295.0Bparameters

1600.0B

DeepSeek-V4-Pro-0813

295.0B

Hy3

Context Window

Maximum input and output token capacity

DeepSeek-V4-Pro-0813 accepts 1,048,576 input tokens compared to Hy3's 262,144 tokens. DeepSeek-V4-Pro-0813 can generate longer responses up to 393,216 tokens, while Hy3 is limited to 262,144 tokens.

DeepSeek-V4-Pro-0813

Input1,048,576 tokens

Output393,216 tokens

Hy3

Input262,144 tokens

Output262,144 tokens

Thu Sep 17 2026 • llm-stats.com

License

Usage and distribution terms

DeepSeek-V4-Pro-0813 is licensed under MIT, while Hy3 uses Apache 2.0.

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

DeepSeek-V4-Pro-0813

MIT

Open weights

Hy3

Apache 2.0

Open weights

Release Timeline

When each model was launched

DeepSeek-V4-Pro-0813 was released on 2026-08-13, while Hy3 was released on 2026-07-06.

DeepSeek-V4-Pro-0813 is 1 month newer than Hy3.

DeepSeek-V4-Pro-0813

Aug 13, 2026

1 months ago

1mo newer

Hy3

Jul 6, 2026

2 months ago

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-V4-Pro-0813 is available from DeepSeek, DeepInfra, Novita, Together. Hy3 is available from DeepInfra.

DeepSeek-V4-Pro-0813

DeepSeek

Input Price:Input: $0.43/1MOutput Price:Output: $0.87/1M

Deepinfra

Input Price:Input: $1.30/1MOutput Price:Output: $2.60/1M

Novita

Input Price:Input: $1.32/1MOutput Price:Output: $3.96/1M

Together

Input Price:Input: $1.32/1MOutput Price:Output: $3.96/1M

Hy3

Deepinfra

Input Price:Input: $0.14/1MOutput Price:Output: $0.58/1M

* 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-V4-Pro-0813 and Hy3 side-by-side, then vote on the output you prefer.

DeepSeek-V4-Pro-0813

✓ Preferred

Hy3

Open in Playground

FAQ

Common questions about DeepSeek-V4-Pro-0813 vs Hy3.

Which is better, DeepSeek-V4-Pro-0813 or Hy3?

DeepSeek-V4-Pro-0813 leads the LLM Stats Score 52.0 to 43.2. DeepSeek-V4-Pro-0813 is made by DeepSeek and Hy3 is made by Tencent. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does DeepSeek-V4-Pro-0813 compare to Hy3 in benchmarks?

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%. Hy3 scores DeepSearchQA: 91.0%, GPQA: 90.4%, IMO-AnswerBench: 90.0%, BrowseComp: 84.2%, MCP Atlas: 79.1%.

Is DeepSeek-V4-Pro-0813 cheaper than Hy3?

Hy3 is 3.1x cheaper for input tokens. DeepSeek-V4-Pro-0813 costs $0.43/M input and $0.87/M output via deepseek. Hy3 costs $0.14/M input and $0.58/M output via deepinfra.

What are the context window sizes for DeepSeek-V4-Pro-0813 and Hy3?

DeepSeek-V4-Pro-0813 supports 1.0M tokens and Hy3 supports 262K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between DeepSeek-V4-Pro-0813 and Hy3?

Key differences include LLM Stats Score (52.0 vs 43.2), context window (1.0M vs 262K), input pricing ($0.43 vs $0.14/M), licensing (MIT vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek-V4-Pro-0813 and Hy3?

DeepSeek-V4-Pro-0813 is developed by DeepSeek and Hy3 is developed by Tencent.

DeepSeek-V4-Pro-0813 vs Hy3