- Giants
- SemiAnalysis
- LLM token cost interactivity
LLM token cost interactivity
SemiAnalysis's scatter plot drew 57.6K views on X: 1.4x @semianalysis_'s median post and #504 of 1,162 AI chart posts we hold by views. Read Oct 10, 2026.
AMD MI355X becomes the first official TileRT result no AgentX! This configuration achieves an astounding 470 TPS on GLM 5.3 (FP8). This is over 40% faster than GB300 TRTLLM using FP4!
Why it spread
It spread because an independent author with a big source posted a branded scatter chart showing GLM models' cost-performance tradeoff with interactivity, earning 57,561 views, 364 likes, 31 reposts, 9 quotes, and 88 saves.
What worked
- The post leads with a clear first result claim for AMD MI355X on TileRT, giving the audience a specific milestone to react to.
- The chart is a branded scatter plot with a source line, which makes the cost-performance tradeoff easy to grasp and share.
- The author is independent and the source has top quarter reach, so the post carries both credibility and distribution.
What to borrow
We could use a branded scatter chart with a source line to frame our own cost-performance tradeoff, then pair it with a short first result claim and a thread hook.
Careful
Do not over-read the low unusual form, medium design polish, medium self-labelling, below average quote rate, or the missing points and comments as proof of what drove the spread.
Written by our analysis model from the measured numbers above, not by SemiAnalysis.
Make it yours
Your numbers, the bar chart way.
Starts from the real numbers of "GLM5.2/GLM5.3 744B Agentic Total Tokens per $1 TCO vs. P90 Interactivity" by SemiAnalysis. Replace every number with yours before you post. Make one like this, step by step
Free pictures carry a small "Made with ViralChart" line. That line is how other people find us.
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 371cbf842b85.
Approximate values. Our two readings of this chart agreed only in part (confidence 0.49 of 1), so check the original before you quote a number. The API marks it lowConfidence, and ?min_confidence=0.5 leaves it out.
| Path | Returns | Plan | |
|---|---|---|---|
| GET | /api/v1/charts/371cbf842b85 | Title, publisher, date, form, point count; with a Max key, the data link | Open |
| GET | /api/v1/charts/371cbf842b85/data | Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV | Max |
| GET | /api/v1/charts/371cbf842b85/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 |
curl -s https://viral-chart.com/api/v1/charts/371cbf842b85/data \
-H "Authorization: Bearer $VIRALCHART_KEY"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 from SemiAnalysis
All 33
Other giants using a scatter plot
All 78
Questions people ask
How far did SemiAnalysis's "LLM token cost interactivity" chart travel?
57,561 views, 364 likes, 31 reposts and 88 saves on X, read Oct 10, 2026. A normal post from @SemiAnalysis_ gets about 52.2K views.
What kind of chart is it?
A scatter plot. GLM models show cost-performance tradeoff with interactivity.
Can I use SemiAnalysis's chart?
Use the format, not the picture. The chart, logo and design belong to SemiAnalysis. ViralChart redraws the chart type with your numbers and words, and credits the original publisher.