Models
Anthropic
Latency vs Throughput for AI Models

@ArtificialAnlysX · Mar 6, 2024

Latency vs Throughput for AI Models

@ArtificialAnlys's scatter plot drew 2.4K views on X: 0.2x @artificialanlys's median post and #1,058 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Latency vs throughput scatter for provider and model combinations

XData Scatter plot Claude 3 All Anthropic modelsGPT-4 Turbo (OpenAI)GPT-4 Turbo (Azure)Mistral Large (Azure)Mistral Medium (Mistral)Mistral Large (Mistral)Claude 3 Opus (Anthropic)Claude 3 Sonnet (Amazon)Claude 3 Sonnet (Anthropic)

@ArtificialAnlys: Latency vs Throughput for AI Models — Published by @ArtificialAnlys on X, Mar 6, 2024. Source: x.com

34/ 100

ViralChart score

Small but loved

Fewer views than the median post but a higher engagement rate: a smaller crowd that acted on it.

#850 of 1,162 AI chart posts we hold · #272 of 491 @artificialanlys posts. Score = views 40%, likes 30%, engagement rate 15%, save rate 15%, each as a percentile of every AI chart post we hold.

Our read

It lands in Small but loved, with a score rank of #850 of 1,162 AI chart posts.

A 0.46% save rate lands at the 99th percentile among AI chart posts, against a 0.076% median.

Its 2.4K views are 0.21x this company's 11.4K median, at #421 of 491 @ArtificialAnlys posts.

The score of 34 sits at #850 of 1,162 AI chart posts and #272 of 491 @ArtificialAnlys posts.

0.1xthe median scatter plot post

Across 187 scatter plot posts we hold, the median gets 22.4K views.

0.2x@artificialanlys's median post

2.4K views, where @artificialanlys's typical post gets 11.4K.

top 1%save rate

0.460% of viewers bookmarked it to come back to. The median post gets 0.076%.

top 23%engagement rate

1.09% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

Public X numbers from our read on Oct 12, 2026. Peers: 1,162 AI chart posts we hold and 491 from @artificialanlys.

Where it sits

Reach against resonance

Each dot is a post. Right is more views, up is a higher engagement rate. The lines are the medians, so the four corners are the four kinds of post.

Among 1,162 AI chart posts we hold

Score #850 of 1,162

Views	2.4K	#1,058	bottom 9%
Likes	19	#1,032	bottom 11%
Engagement rate	1.09%	#264	top 23%
Save rate	0.460%	#6	top 1%

Among 491 @artificialanlys posts

Score #272 of 491

Views	2.4K	#421	bottom 14%
Likes	19	#393	bottom 20%
Engagement rate	1.09%	#139	top 28%
Save rate	0.460%	#4	top 1%

Growth

One read so far

Views2.4K

Age at our read950 days

Views per day of life3views divided by days since it was posted

Dots are our reads. The dotted line from the day it was posted to our first read is a gap, not data.

@artificialanlys's posts over time

Every post from this account we hold, by date and views. This one is marked; the line is the running median of the last 10.

News · Mar 6, 2024

@ArtificialAnlys scatter plots latency against throughput for AI models

A scatter plot of latency versus throughput drew 2.4K views and a 0.46% save rate, the 99th percentile among AI chart posts.

What happened

@ArtificialAnlys posted a scatter plot on latency versus throughput for provider and model combinations on March 6, 2024. It was the account's only post that day.

The numbers

It reached 2.4K views, #1,058 of 1,162 AI chart posts, against a 39.9K median among AI chart posts. Its score of 34 ranks #850 of 1,162 AI chart posts.

The lesson

A 0.46% save rate, the 99th percentile among AI chart posts, shows readers bookmark a scatter plot at a far higher rate than the 0.076% median.

What it means

At #421 of 491 @ArtificialAnlys posts by views, this chart sits below the company's 11.4K median even as its save rate reaches the top decile.

Written by ViralChart from public numbers read on Oct 12, 2026. Every number is checked against our data before it is shown.

Updates: what @artificialanlys posted next

Data and API

8 points read off this chart

Estimated from the image 55%

Group	Value	Read
Mistral Large (Azure)	2.2 Seconds	estimated
Claude 3 Opus (Anthropic)	1.8 Seconds	estimated
GPT-4 Turbo (Azure)	0.6 Seconds	estimated
Claude 3 Sonnet (Amazon)	0.8 Seconds	estimated
GPT-4 Turbo (OpenAI)	0.7 Seconds	estimated
Mistral Medium (Mistral)	0.3 Seconds	printed
Mistral Large (Mistral)	0.2 Seconds	printed
Claude 3 Sonnet (Anthropic)	0.2 Seconds	printed

Max plan · API

GET https://viral-chart.com/api/posts/bdfce8f4a160.json
GET https://viral-chart.com/api/charts/bdfce8f4a160.json
GET https://viral-chart.com/api/charts/bdfce8f4a160.skill.md

Make one like this Open the post JSON Chart data JSON Skill file API docs

Static files in this prototype. The post JSON holds the public numbers, ranks, score, quadrant, our reads and, when checked, our copy.

API · Max

Use this chart via API

On the Max plan you can pull this chart's numbers with the provenance of each one, as JSON or CSV, with its redraw spec, or call it from an agent over MCP. Chart id bdfce8f4a160.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/bdfce8f4a160`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/bdfce8f4a160/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/bdfce8f4a160/render?view=1`	The draw-only view this page uses	Open
POST	`/mcp`	Tool get_chart_data with this id, for Claude, Cursor and other agents	Max

curlMax

curl -s https://viral-chart.com/api/v1/charts/bdfce8f4a160/data \
  -H "Authorization: Bearer $VIRALCHART_KEY"

Claude CodeMax

claude mcp add --transport http viralchart https://viral-chart.com/mcp \
  --header "Authorization: Bearer $VIRALCHART_KEY"

60 requests a minute per key; over that you get 429 with Retry-After. Up to 5 keys per account, made on your account page and shown once. Without Max, the data route answers 402 with a link to the plans. The numbers describe a chart its publisher owns, and every file carries a license note.