The AI arena is free today

Open Superagent

DeepSeek-V4-Pro-0813 vs MiniMax M3.1 Flash

DeepSeek-V4-Pro-0813 and MiniMax M3.1 Flash are closely matched at 50.3 and 48.5 on the LLM Stats Score. MiniMax M3.1 Flash is 6.2x cheaper per token.

DeepSeek · MiniMax · Updated for 2026

Which is better?

DeepSeek-V4-Pro-0813 and MiniMax M3.1 Flash are closely matched on the overall LLM Stats Score at 50.3 and 48.5.

The models split the 4 individual benchmarks reported for both models evenly.

On price, MiniMax M3.1 Flash is roughly 6.2x 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

  • you process long inputs — it offers a 1,048,576 token context window
  • you need open weights you can self-host or fine-tune

Choose MiniMax M3.1 Flash

  • cost matters — it's about 6.2x cheaper per token
  • you want the most recent training data — it shipped Oct 2026

At a glance

The differences that matter most.

DeepSeek-V4-Pro-0813
DeepSeek
MiniMax M3.1 Flash
MiniMax
Core performance indexes
LLM Stats Score
50.3
#18
48.5
#29
Reasoning
48.5
#19
45.8
#34
Coding
38.1
#22
37.8
#23
Agents
35.3
#24
35.6
#23
Cost, coverage & limits
Benchmark wins
2 of 4
2 of 4
Input price
$1.30 / M
$0.15 / M
Output price
$2.60 / M
$0.60 / M
Context window
1,048,576
1,000,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
DeepSeek-V4-Pro-0813
MiniMax M3.1 Flash
Tool use
28.0#22
26.8#30
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

12 reported for DeepSeek-V4-Pro-0813 · 14 for MiniMax M3.1 Flash

4 shared

DeepSeek-V4-Pro-0813 outperforms in 2 benchmarks (CyberGym, NL2Repo), while MiniMax M3.1 Flash is better at 2 benchmarks (Agents' Last Exam, Humanity's Last Exam (no tools, text-only)).

Both models are evenly matched across the benchmarks.

Mon Oct 19 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

MiniMax M3.1 Flash costs less

For input processing, DeepSeek-V4-Pro-0813 ($1.30/1M tokens) is 8.7x more expensive than MiniMax M3.1 Flash ($0.15/1M tokens).

For output processing, DeepSeek-V4-Pro-0813 ($2.60/1M tokens) is 4.3x more expensive than MiniMax M3.1 Flash ($0.60/1M tokens).

In conclusion, DeepSeek-V4-Pro-0813 is more expensive than MiniMax M3.1 Flash.*

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

Lowest available price from all providers
Mon Oct 19 2026 • llm-stats.com
DeepSeek
DeepSeek-V4-Pro-0813
Input tokens$1.30
Output tokens$2.60
Best providerDeepinfra
MiniMax
MiniMax M3.1 Flash
Input tokens$0.15
Output tokens$0.60
Best providerMiniMax
Notice missing or incorrect data?

Context Window

Maximum input and output token capacity

DeepSeek-V4-Pro-0813 accepts 1,048,576 input tokens compared to MiniMax M3.1 Flash's 1,000,000 tokens. DeepSeek-V4-Pro-0813 can generate longer responses up to 1,048,576 tokens, while MiniMax M3.1 Flash is limited to 524,288 tokens.

DeepSeek
DeepSeek-V4-Pro-0813
Input1,048,576 tokens
Output1,048,576 tokens
MiniMax
MiniMax M3.1 Flash
Input1,000,000 tokens
Output524,288 tokens
Mon Oct 19 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

MiniMax M3.1 Flash supports multimodal inputs, whereas DeepSeek-V4-Pro-0813 does not.

MiniMax M3.1 Flash can handle both text and other forms of data like images, making it suitable for multimodal applications.

DeepSeek-V4-Pro-0813

Text
Images
Audio
Video

MiniMax M3.1 Flash

Text
Images
Audio
Video

License

Usage and distribution terms

DeepSeek-V4-Pro-0813 is licensed under MIT, while MiniMax M3.1 Flash uses a proprietary license.

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

DeepSeek-V4-Pro-0813

MIT

Open weights

MiniMax M3.1 Flash

Proprietary

Closed source

Release Timeline

When each model was launched

DeepSeek-V4-Pro-0813 was released on 2026-08-13, while MiniMax M3.1 Flash was released on 2026-10-19.

MiniMax M3.1 Flash is 2 months newer than DeepSeek-V4-Pro-0813.

DeepSeek-V4-Pro-0813

Aug 13, 2026

2 months ago

MiniMax M3.1 Flash

Oct 19, 2026

0 days ago

2mo 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-V4-Pro-0813 is available from DeepInfra, DeepSeek, Novita, Together. MiniMax M3.1 Flash is available from MiniMax.

DeepSeek-V4-Pro-0813

deepinfra logo
Deepinfra
Input Price:Input: $1.30/1MOutput Price:Output: $2.60/1M
deepseek logo
DeepSeek
Input Price:Input: $1.32/1MOutput Price:Output: $3.96/1M
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

MiniMax M3.1 Flash

minimax logo
MiniMax
Input Price:Input: $0.15/1MOutput Price:Output: $0.60/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against DeepSeek-V4-Pro-0813 and MiniMax M3.1 Flash side-by-side, then vote on the output you prefer.

DeepSeek-V4-Pro-0813
✓ Preferred
MiniMax M3.1 Flash
Open in Playground

FAQ

Common questions about DeepSeek-V4-Pro-0813 vs MiniMax M3.1 Flash.

Which is better, DeepSeek-V4-Pro-0813 or MiniMax M3.1 Flash?

DeepSeek-V4-Pro-0813 and MiniMax M3.1 Flash are closely matched on the LLM Stats Score at 50.3 and 48.5. DeepSeek-V4-Pro-0813 is made by DeepSeek and MiniMax M3.1 Flash is made by MiniMax. 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 MiniMax M3.1 Flash 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%. MiniMax M3.1 Flash scores BabyVision: 91.0%, CharXiv-R: 82.5%, CyberGym: 82.2%, BankerToolBench: 76.2%, DeepSWE 1.1: 73.7%.

Is DeepSeek-V4-Pro-0813 cheaper than MiniMax M3.1 Flash?

MiniMax M3.1 Flash is 8.7x cheaper for input tokens. DeepSeek-V4-Pro-0813 costs $1.30/M input and $2.60/M output via deepinfra. MiniMax M3.1 Flash costs $0.15/M input and $0.60/M output via minimax.

What are the context window sizes for DeepSeek-V4-Pro-0813 and MiniMax M3.1 Flash?

DeepSeek-V4-Pro-0813 supports 1.0M tokens and MiniMax M3.1 Flash 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-V4-Pro-0813 and MiniMax M3.1 Flash?

Key differences include LLM Stats Score (50.3 vs 48.5), context window (1.0M vs 1.0M), input pricing ($1.30 vs $0.15/M), multimodal support (no vs yes), licensing (MIT vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek-V4-Pro-0813 and MiniMax M3.1 Flash?

DeepSeek-V4-Pro-0813 is developed by DeepSeek and MiniMax M3.1 Flash is developed by MiniMax.

Related comparisons