DeepSeek-V4-Flash-0731 vs DeepSeek-V4-Pro-0813
DeepSeek-V4-Pro-0813 leads the LLM Stats Score 51.0 to 43.8. DeepSeek-V4-Flash-0731 is 18.1x cheaper per token.
DeepSeek · DeepSeek · Updated for 2026
Which is better?
DeepSeek-V4-Pro-0813 leads the overall LLM Stats Score 51.0 to 43.8, ranking #16 overall.
In the 9 individual benchmarks reported for both models, DeepSeek-V4-Pro-0813 wins 9; this is a narrower head-to-head signal than the composite indexes.
On price, DeepSeek-V4-Flash-0731 is roughly 18.1x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose DeepSeek-V4-Flash-0731
- cost matters — it's about 18.1x cheaper per token
Choose DeepSeek-V4-Pro-0813
- overall performance matters — it scores 51.0 and ranks #16 on LLM Stats
- you value its reported benchmark strengths — it wins 9 of 9 exact shared results
- you want the most recent training data — it shipped Aug 2026
At a glance
The differences that matter most.
Capability indexes
Additional strengths measured across groups of related public benchmarks
Individual benchmarks
9 reported for DeepSeek-V4-Flash-0731 · 12 for DeepSeek-V4-Pro-0813
DeepSeek-V4-Flash-0731 outperforms in 0 benchmarks, while DeepSeek-V4-Pro-0813 is better at 9 benchmarks (Agents' Last Exam, AutomationBench, CyberGym, DeepSWE, DSBench-FullStack, DSBench-Hard, NL2Repo, Terminal-Bench 2.1, Toolathlon).
DeepSeek-V4-Pro-0813 significantly outperforms across most benchmarks.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, DeepSeek-V4-Flash-0731 ($0.06/1M tokens) is 21.7x cheaper than DeepSeek-V4-Pro-0813 ($1.30/1M tokens).
For output processing, DeepSeek-V4-Flash-0731 ($0.18/1M tokens) is 14.4x cheaper than DeepSeek-V4-Pro-0813 ($2.60/1M tokens).
In conclusion, DeepSeek-V4-Pro-0813 is more expensive than DeepSeek-V4-Flash-0731.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
DeepSeek-V4-Pro-0813 has 1296.0B more parameters than DeepSeek-V4-Flash-0731, making it 426.3% larger.
Context Window
Maximum input and output token capacity
Both models have the same input context window of 1,048,576 tokens. Both models can generate responses up to 1,048,576 tokens.
License
Usage and distribution terms
Both models are licensed under MIT.
Both models share the same licensing terms, providing consistent usage rights.
MIT
Open weights
MIT
Open weights
Release Timeline
When each model was launched
DeepSeek-V4-Flash-0731 was released on 2026-07-31, while DeepSeek-V4-Pro-0813 was released on 2026-08-13.
DeepSeek-V4-Pro-0813 is 0 month newer than DeepSeek-V4-Flash-0731.
Jul 31, 2026
2 months ago
Aug 13, 2026
1 months ago
1w newerKnowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
DeepSeek-V4-Flash-0731 is available from DeepInfra, Novita, Fireworks. DeepSeek-V4-Pro-0813 is available from DeepInfra, DeepSeek, Novita, Together.
DeepSeek-V4-Flash-0731
DeepSeek-V4-Pro-0813
Outputs Comparison
Judge for yourself.
Run your own prompts against DeepSeek-V4-Flash-0731 and DeepSeek-V4-Pro-0813 side-by-side, then vote on the output you prefer.
FAQ
Common questions about DeepSeek-V4-Flash-0731 vs DeepSeek-V4-Pro-0813.