DeepSeek V4 Pro 0813 Max vs GLM-5.3-Flash compared

GLM-5.3-Flash leads the intelligence index 27.8 to 23.1. GLM-5.3-Flash costs 88% less on blended price. Price per token, response speed and when to pick each.

Metric	DeepSeek V4 Pro 0813 (Max)	GLM-5.3-Flash
Intelligence Index	23.1	27.8
Input price (per 1M tokens)	$1.32	$0.15
Output price (per 1M tokens)	$3.96	$0.50
Output speed (tokens/s)	67	56
Time to first token	1.7s	1.6s
Release date	2026-08-13	2026-08-26

Metric

DeepSeek V4 Pro 0813 (Max)

GLM-5.3-Flash

Intelligence Index

23.1

27.8

Input price (per 1M tokens)

$1.32

$0.15

Output price (per 1M tokens)

$3.96

$0.50

Output speed (tokens/s)

Time to first token

1.7s

1.6s

Release date

2026-08-13

2026-08-26

Choosing between DeepSeek V4 Pro 0813 (Max) and GLM-5.3-Flash also means choosing between DeepSeek and Z AI. The clearest gap is on the bill: DeepSeek V4 Pro 0813 Max is 8.3 times the blended price of GLM-5.3-Flash. This page is written automatically from catalogue numbers only: benchmark scores, list prices and measured speed.

Token pricing and a sample bill

Per million tokens, DeepSeek V4 Pro 0813 Max charges $1.32 for input and $3.96 for output, while GLM-5.3-Flash charges $0.15 and $0.50. For output tokens, DeepSeek V4 Pro 0813 Max is 7.9 times the price of GLM-5.3-Flash.

For a sample workload of 1 million input tokens and 200,000 output tokens, DeepSeek V4 Pro 0813 Max would cost $2.11 and GLM-5.3-Flash $0.25, a difference of $1.86. Scale it up to summarising 1,000 documents of 8,000 tokens into 400-token summaries and the bill is $12.14 for DeepSeek V4 Pro 0813 Max against $1.40 for GLM-5.3-Flash.

How the intelligence index compares

The catalogue puts DeepSeek V4 Pro 0813 Max at 23.1 and GLM-5.3-Flash at 27.8 on its intelligence index. It is a meaningful gap rather than a rounding difference. Put another way, DeepSeek V4 Pro 0813 Max would need 20% more on this index to draw level.

Among 109 active scored models, DeepSeek V4 Pro 0813 Max sits 72nd and GLM-5.3-Flash 63rd.

The catalogue does not yet split either model's score into coding and math indexes.

Waiting time

DeepSeek V4 Pro 0813 Max generates about 67 tokens per second and GLM-5.3-Flash about 56 tokens per second. DeepSeek V4 Pro 0813 Max is ahead by 20% on throughput. Time to first token is 1.7 seconds for DeepSeek V4 Pro 0813 Max and 1.6 seconds for GLM-5.3-Flash.

For a 1,500-token response, first token plus generation comes to roughly 24 seconds on DeepSeek V4 Pro 0813 Max and 28 seconds on GLM-5.3-Flash. The two totals cross at about 50 tokens; past that, DeepSeek V4 Pro 0813 Max finishes first.

Which is newer

The release dates are August 13, 2026 for DeepSeek V4 Pro 0813 Max and August 26, 2026 for GLM-5.3-Flash, 13 days apart. They are effectively contemporaries.

Cost per point of intelligence

A blunt value measure, blended price over intelligence score, puts DeepSeek V4 Pro 0813 Max at $0.086 and GLM-5.3-Flash at $0.0085 per point. GLM-5.3-Flash scores higher and costs less per point, so on price per point there is nothing to trade off.

Common questions about DeepSeek V4 Pro 0813 Max and GLM-5.3-Flash

Is GLM-5.3-Flash better than DeepSeek V4 Pro 0813 Max?

It depends on what you need: GLM-5.3-Flash scores higher on the intelligence index, 27.8 to 23.1; GLM-5.3-Flash is 88% cheaper on blended price; and DeepSeek V4 Pro 0813 Max streams output 1.2 times as fast.

Was this comparison tested by hand?

The figures are the recorded benchmark, price and speed data in Franklin AI's model catalogue. This page is written from that data automatically; neither model was tested by hand for it.

Does DeepSeek V4 Pro 0813 Max respond faster than GLM-5.3-Flash?

DeepSeek V4 Pro 0813 Max generates output faster, at 67 tokens per second against 56 tokens per second. Time to first token is similar: 1.7 seconds and 1.6 seconds. Counting the first-token wait, GLM-5.3-Flash finishes short replies first and DeepSeek V4 Pro 0813 Max pulls ahead beyond about 50 tokens.

Which is newer, DeepSeek V4 Pro 0813 Max or GLM-5.3-Flash?

GLM-5.3-Flash is newer. It was released on August 26, 2026, 13 days after DeepSeek V4 Pro 0813 Max (August 13, 2026).

How much do DeepSeek V4 Pro 0813 Max and GLM-5.3-Flash cost?

GLM-5.3-Flash is cheaper on a blended basis. DeepSeek V4 Pro 0813 Max lists $1.32 per million input tokens and $3.96 per million output tokens; GLM-5.3-Flash lists $0.15 and $0.50. For 1 million input and 200,000 output tokens that is $2.11 against $0.25.

Final whistle

GLM-5.3-Flash is the stronger all-round pick on this data, while DeepSeek V4 Pro 0813 Max makes sense in narrower cases. Pick GLM-5.3-Flash if cost matters ($0.50 against $3.96 per million output tokens) and you need the higher overall score (27.8 against 23.1). Pick DeepSeek V4 Pro 0813 Max if your outputs often run past about 50 tokens.

Where the numbers come from

The scores, speed and prices in this comparison come from independent third-party model evaluations that Franklin AI syncs each day, and the article was written from a snapshot of them. For the latest results, open the DeepSeek V4 Pro 0813 (Max) and GLM-5.3-Flash pages. The AI Benchmark methodology explains how that data is collected and shown.