1. Models
  2. OpenAI
  3. Cost per Hour of Input Audio (Big Bench
A
@ArtificialAnlysX · Sep 15, 2026

Cost per Hour of Input Audio (Big Bench

@ArtificialAnlys's bar chart drew 4.9K views on X: 0.4x @artificialanlys's median post and #952 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Cost per hour of input audio varies across models

XDataBar chartGPT-LiveAll OpenAI modelsGemini 2.5 Audio PreviewGemini 2.5 Flash PreviewGemini 2.5 Flash Lite PreviewQwen3-Omni-28BQwen3-Omni-30B-A3B-InstructGrok Voice Fast 1.0Grok Voice Mini (Opaque)GPT-Realtime Mini (Opaque)
Published by @ArtificialAnlys on X, Sep 15, 2026. Source: x.com
13/ 100

ViralChart score

Quiet

Fewer views and a lower engagement rate than the median post.

#1,134 of 1,162 AI chart posts we hold · #473 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

The post sits in the Quiet quadrant, with a score rank of #1,134 of 1,162 AI chart posts.

Its score of 13 lands at #1,134 of 1,162 AI chart posts, below the field.

Engagement rate of 0.31% sits at the 10th percentile among AI chart posts, in the bottom decile.

It was one of 9 posts from this account that day, ranking #6 of 9 by views.

9posts from @artificialanlys that day

Part of a run of 9 posts on Sep 15, 2026. This one was #6 of 9 by views that day.

bottom 10%engagement rate

0.31% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

0.2xthe median bar chart post

Across 241 bar chart posts we hold, the median gets 25.6K views.

0.4x@artificialanlys's median post

4.9K views, where @artificialanlys's typical post gets 11.4K.

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 #1,134 of 1,162

Views4.9K#952bottom 18%
Likes11#1,100bottom 5%
Engagement rate0.31%#1,049bottom 10%
Save rate0.041%#908bottom 22%

Among 491 @artificialanlys posts

Score #473 of 491

Views4.9K#340bottom 31%
Likes11#443bottom 9%
Engagement rate0.31%#457bottom 7%
Save rate0.041%#371bottom 25%

Growth

One read so far

Views4.9K
Age at our read28 days
Views per day of life176views 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 · Sep 15, 2026

@ArtificialAnlys charts cost per hour of input audio

A 17-model bar chart on audio input cost drew 4.9K views and an engagement rate of 0.31%, below the AI chart median.

What happened

On September 15, 2026, @ArtificialAnlys posted a bar chart on cost per hour of input audio across 17 models. It was one of 9 posts from the account that day, alongside posts on the Artificial Analysis Speech to Speech Index and Arena Preference Elo vs Task Success Rate.

The numbers

The post reached 4.9K views, ranking #952 of 1,162 AI chart posts, against a median of 39.9K views among AI chart posts. Its score of 13 ranks #1,134 of 1,162 AI chart posts and #473 of 491 @ArtificialAnlys posts.

The lesson

A 17-model bar chart drew 4.9K views and a save rate of 0.041%, with engagement at 0.31% against the 0.73% median among AI chart posts. The chart type and model count did not lift saves or engagement above the field.

What it means

At #473 of 491 @ArtificialAnlys posts, this chart sits near the bottom of the account's own range. The gap between its 4.9K views and the 39.9K median among AI chart posts shows the distance from the field's typical reach.

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

  1. Speech to Speech Arena Elo6.6K views
  2. Agentic Performance (τ-Voice)3.2K views
  3. Speech Reasoning: Big Bench Audio1.8K views
  4. Cost per Hour of Input Audio5.3K views
  5. AI Model Benchmark Performance22.9K views
  6. AA-WER Streaming Index120K views

Data and API

18 points read off this chart

Estimated from the image 30%
SeriesGroupValueRead
Gemini 2.5 Audio Preview1.42 USDestimated
Gemini 3.1 Flash Preview1.5 USDestimated
Gemini 3.1 Flash Preview (8B)1.75 USDestimated
Qwen3-Omni 30B A3B Instruct (Flash)1.77 USDestimated
Qwen3-Omni 30B A3B Instruct (Think)2.26 USDestimated
GLM Voice Flash 1.03 USDestimated
GLM Voice Think 1.03 USDestimated
GPT-4o-mini Mini (Text)3.04 USDestimated
GPT-4o-mini (Text)3.07 USDestimated
GPT-4.1-mini (Text)3.45 USDestimated
GPT-4.1-mini (Text)4.14 USDestimated
Qwen3-Omni 30B A3B Instruct (Flash)4.42 USDestimated

Showing 12 of 18. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/8a4808aad7c8.json
GET https://viral-chart.com/api/charts/8a4808aad7c8.json
GET https://viral-chart.com/api/charts/8a4808aad7c8.skill.md
Make one like thisOpen the post JSONChart data JSONSkill fileAPI 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 8a4808aad7c8.

Approximate values. Our two readings of this chart agreed only in part (confidence 0.30 of 1), so check the original before you quote a number. The API marks it lowConfidence, and ?min_confidence=0.5 leaves it out.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/8a4808aad7c8Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/8a4808aad7c8/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/8a4808aad7c8/render?view=1The draw-only view this page usesOpen
POST/mcpTool get_chart_data with this id, for Claude, Cursor and other agentsMax
curlMax
curl -s https://viral-chart.com/api/v1/charts/8a4808aad7c8/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.

More charts about GPT-Live

GPT-Live: GPT-Live-1 Performance Bench
OfficialX · OpenAISep 10, 2026
GPT-Live-1 Performance Bench55.3K views · 761 likes
Data
GPT-Live: GPT-Live-1 Performance
OfficialX · OpenAISep 10, 2026
GPT-Live-1 Performance55.3K views · 761 likes
Data
GPT-Live: GPT-Live-1 Performance Bench
OfficialX · OpenAISep 10, 2026
GPT-Live-1 Performance Bench55.3K views · 761 likes
Data
GPT-Live: GPT-Live-1 Performance and Tau Banking Knowledge
OfficialX · OpenAISep 10, 2026
GPT-Live-1 Performance and Tau Banking Knowledge55.3K views · 761 likes
Data
GPT-Live: Word Error Rate Comparison
OfficialX · OpenAIJul 28, 2026
Word Error Rate Comparison24.2K views · 174 likes
Data
GPT-Live: Context Aware ASR Benchmark
OfficialX · OpenAIJul 28, 2026
Context Aware ASR Benchmark24.2K views · 174 likes
Data

More from OpenAI

OpenAI line chart: Output tokens by department2.3x
OpenAI·Jun 2026
Output tokens by department
1.3M views5.4K likes0.5% eng.
Data
OpenAI annotated chart: Research paper benchmarking2.9x
OpenAI·Apr 2025
Research paper benchmarking
1.1M views7K likes0.8% eng.
OpenAI bar chart: AI model performance2.0x
OpenAI·Sep 2026
AI model performance
999.9K views4.8K likes0.6% eng.
Data
ChatGPT: Artificial Analysis Intelligence Index v4.1
OfficialX · OpenAIJul 30, 2026
Artificial Analysis Intelligence Index v4.121M views · 19.5K likes
Data
ChatGPT: AI Model Benchmark Comparison
OfficialX · OpenAIMar 5, 2026
AI Model Benchmark Comparison7.2M views · 23.2K likes
Data
ChatGPT: GPT4 Turbo Benchmark Comparison
OfficialX · OpenAIApr 12, 2024
GPT4 Turbo Benchmark Comparison6.4M views · 6.7K likes
Data
GPT-5.6: AI Model Benchmark Comparison
OfficialX · OpenAISep 3, 2026
AI Model Benchmark Comparison5.4M views · 10.3K likes
Data
GPT-5: AI Model Benchmark Comparison
OfficialX · OpenAIDec 11, 2025
AI Model Benchmark Comparison2M views · 3.8K likes
Data
GPT-5.6: TerminalBench 2.1 AI Model Scores
OfficialX · OpenAIJun 26, 2026
TerminalBench 2.1 AI Model Scores1.9M views · 3.9K likes
Data

Questions people ask

Where does this chart come from?

@ArtificialAnlys published it on Sep 15, 2026 on X (x.com). We keep it here, with the publisher and date credited as text, so you can study it without leaving.

Can I make a chart like this?

Use the format, not the picture. Open its data page and use Make one like this: it starts from this chart's numbers and takes yours.