# How do I analyse the comments under TikTok videos with AI?

Connect SocialToAI to your AI client over MCP, then ask in plain words. In this recorded run an AI client answered “What are people saying in the comments under NASA's latest TikTok videos?” with 1 request on TikTok: 199 items read in 14.2 seconds for 38 credits ($0.13). Below are the calls it made, the answer with its sources, and the prompt and API calls to run it yourself. Recorded 2026-10-18.

- Page: https://socialtoai.com/docs/guides/analyse-tiktok-comments/
- Last updated: 2026-10-18

## The question

> What are people saying in the comments under NASA's latest TikTok videos?

A popular video has hundreds of comments, ordered by what the app chooses to show. Grouping them into topics and counting each takes reading all of them. Reading what this run returned by hand takes about 7 minutes (1,616 words at 240 a minute).

## What the AI did

It chose the tools itself: 1 request on TikTok. Each row is one tool call as the client showed it, with what it sent, how much came back and what it cost.

| Platform | Tool | Sent | Requests | Returned | Credits |
| --- | --- | --- | --- | --- | --- |
| TikTok | [`comment_insights`](https://socialtoai.com/tools/comment-insights.md) | `targets: ["https://www.tiktok.com/@nasa/video/7691683140015820046","https://www.tiktok.com/@nasa/video/7694283957839400206"] · scale: "small"` | 1 | 199 comments | 38 |
| **Total** |  |  | 1 | 199 items | **38** |

## The answer

What the client answered, from what it had read. The line under each finding is a post it read, or a figure from those posts.

Recorded 2026-10-18

I read 199 comments under 2 videos; 157 could be judged. The topics that come up most:

1. **Excitement about space** (18%, 28 comments): [“fuck yeah space is so fucking cool”](https://www.tiktok.com/@nasa/video/7691683140015820046)
2. **Flat-earth and “space is fake” claims** (17%, 27 comments): [“people saying the world is flat and this is all lies lol”](https://www.tiktok.com/@nasa/video/7694283957839400206)
3. **SpaceX missions** (13%, 21 comments): [“Imagine your last car ride on earth is in a Tesla”](https://www.tiktok.com/@nasa/video/7691683140015820046)

Used 38 credits · $0.13. Every claim links to its source.

### The posts it rests on

A selection of what was read; the marked words are what a finding rests on. An item without a link says so.

- TikTok · comment · 2w: “"WOULD YOU PICK ME OVER NASA?" fuck yeah space is so fucking cool” ([Open the source](https://www.tiktok.com/@nasa/video/7691683140015820046))
- TikTok · comment · 10d: “ne doing all this and the research it involves only to hear people saying the world is flat and this is all lies lol” ([Open the source](https://www.tiktok.com/@nasa/video/7694283957839400206))
- TikTok · comment · 2w: “[Sticker] Imagine your last car ride on earth is in a Tesla” ([Open the source](https://www.tiktok.com/@nasa/video/7691683140015820046))

## What it cost

1 request, 38 credits in total: $0.13 at the $10 rate. Every answer of the API states the credits it charged and the balance left, so your AI can tell you what a question cost. A call that fails costs nothing.

| Pack | Credits per dollar | This answer |
| --- | --- | --- |
| $10 = 3,000 credits | 300 | $0.13 |
| $50 = 20,000 credits | 400 | $0.095 |
| $200 = 100,000 credits | 500 | $0.076 |

## Ask it yourself

Connect SocialToAI to your AI client once ([the steps for each client](https://socialtoai.com/mcp.md)), then paste the question. You do not name tools or parameters: the client picks them.

**Prompt**

```
What are people saying in the comments under NASA's latest TikTok videos?
```

The same in code: the calls this run made, as requests to the API.

**tool.comment_insights**

```
curl https://api.socialtoai.com/v1/tools/comment_insights \
  -H "Authorization: Bearer $SOCIALTOAI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "targets": ["https://www.tiktok.com/@nasa/video/7691683140015820046","https://www.tiktok.com/@nasa/video/7694283957839400206"],
    "scale": "small"
  }'
```

## What to try next

- Ask next: “Quote the questions people ask”
- Ask next: “Which comments want to buy?”
- Ask for the questions viewers ask.
- Add your own topics to sort the comments by.
- Run it as one request with the ready-made tool [Comment analysis](https://socialtoai.com/tools/comment-insights.md): What the comments under your posts are about: the topics and their shares, the questions asked, who wants to buy and what is complained about, with the comments quoted.

- [TikTok MCP server](https://socialtoai.com/mcp/tiktok.md): What your AI can read on TikTok, and how to connect it.
- [TikTok API](https://socialtoai.com/platforms/tiktok.md): Every call on TikTok, with its credits and a request you can copy.