> ## Documentation Index
> Fetch the complete documentation index at: https://docs.influship.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Lookalikes
> Find creators similar to ones you already know, with weighted seeds and filtering
# Lookalikes
Lookalike search finds creators who resemble a set of seed creators. You provide one or more examples of what you're looking for, and the API returns ranked results based on content themes, audience overlap, posting style, and engagement patterns.
This is useful when you have creators that work and want to find more like them — or when you need to replace a creator who declined and want someone with a similar profile.
## How It Works
1. You provide 1-10 seed creators (by ID or platform + username)
2. Optionally weight each seed to control how much it influences results
3. The API analyzes content, audience, and style similarities
4. You get back ranked results with similarity scores and human-readable shared traits
Each result tells you *why* a creator is similar, not just *that* they are.
## Seeds
A seed is a reference creator. You can identify seeds two ways:
```json theme={null}
// By creator ID (if you already have one from search or a previous lookup)
{ "creator_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890", "weight": 1.0 }
// By platform + username (if you're starting from a social handle)
{ "platform": "instagram", "username": "fitness_coach_jane", "weight": 1.0 }
```
You can mix both formats in the same request. If a platform + username can't be found, the API skips that seed and continues with the rest — the request only fails if *none* of the seeds resolve.
## Weighting
Weights control how much each seed influences the results. They range from 0 to 1, with 1.0 as the default.
```json theme={null}
{
"seeds": [
{ "platform": "instagram", "username": "top_performer", "weight": 1.0 },
{ "platform": "instagram", "username": "decent_creator", "weight": 0.5 },
{ "platform": "instagram", "username": "niche_pick", "weight": 0.3 }
],
"limit": 20
}
```
A higher weight means the API leans more heavily on that seed's characteristics when ranking results. This is where lookalike search becomes genuinely useful beyond simple "find similar" — you can encode your preferences into the weights.
### Using Performance Data as Weights
If you have campaign performance data (ROI, conversion rates, engagement), turn it into weights. Your best-performing creator gets weight 1.0, and others scale relative to that.
For example, if you ran a campaign with three creators:
| Creator | Campaign ROI | Weight |
| ---------------- | ------------ | ------ |
| @top\_performer | 4.2x | 1.0 |
| @decent\_creator | 2.1x | 0.5 |
| @niche\_pick | 1.3x | 0.3 |
The resulting lookalike search finds creators who skew toward your best performer's profile while still incorporating traits from the others. Over time, this creates a feedback loop — each campaign's results improve your next lookalike search.
## Filters
Apply the same filters available on search to narrow lookalike results:
```json theme={null}
{
"seeds": [
{ "platform": "instagram", "username": "fitness_coach_jane" }
],
"filters": {
"followers": { "min": 25000, "max": 500000 },
"engagement_rate": { "min": 2.0 },
"verified": true
},
"limit": 15
}
```
| Filter | Type | Description |
| --------------------------------------------- | ------- | ---------------------------------------- |
| `followers.min` / `followers.max` | integer | Follower count range |
| `engagement_rate.min` / `engagement_rate.max` | number | Engagement rate as percentage (2.0 = 2%) |
| `verified` | boolean | Only verified accounts |
## Response
Each result includes a similarity score and shared traits explaining the match:
```json theme={null}
{
"data": [
{
"creator": {
"id": "d9e8f7a6-b5c4-3d2e-1f0a-9b8c7d6e5f4a",
"name": "Lena Park",
"bio": "Yoga & strength training | NYC",
"avatar_url": "https://cdn.example.com/lena.jpg"
},
"primary_profile": {
"platform": "instagram",
"username": "lenapark_fit",
"url": "https://www.instagram.com/lenapark_fit",
"followers": 87000,
"engagement_rate": 4.1,
"is_verified": false
},
"similarity": {
"score": 0.89,
"shared_traits": [
"Both focus on fitness and wellness content",
"Similar audience demographics (women 25-34)",
"Comparable engagement patterns on workout videos",
"Clean, professional content style"
]
}
}
],
"has_more": true,
"next_cursor": "eyJvZmZzZXQiOjI1fQ=="
}
```
The `similarity.score` ranges from 0 to 1. Scores above 0.8 typically indicate strong overlap. The `shared_traits` list explains what the seed and result have in common — useful for displaying to end users or for your own review.
## Pagination
Lookalike uses cursor pagination. Pass `next_cursor` from the response to fetch the next page:
```bash theme={null}
curl -X POST https://api.influship.com/v1/creators/lookalike \
-H 'X-API-Key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"seeds": [{"platform": "instagram", "username": "fitness_coach_jane"}],
"limit": 25,
"cursor": "eyJvZmZzZXQiOjI1fQ=="
}'
```
Stop when `has_more` is `false`. See the [Pagination guide](/guides/pagination) for patterns.
## Pricing
Lookalike is billed per creator returned: **1.5 credits per creator** (\$0.015). No base fee. See [Pricing](/concepts/pricing) for the full table.
## Limits
| Parameter | Min | Max | Default |
| --------------- | --- | --- | ------- |
| Seeds | 1 | 10 | -- |
| Weight per seed | 0 | 1 | 1.0 |
| Limit (results) | 1 | 100 | 25 |
## Implementation Advice
* **Start with one seed** to calibrate. Add more seeds once you understand what the single-seed results look like.
* **Use weights to encode knowledge.** If you know one creator drives better results than another, the weights should reflect that. Don't default everything to 1.0 if you have data.
* **Combine with match scoring.** Run lookalike to expand your list, then pass the results through `POST /v1/creators/match` with your campaign brief to filter for actual campaign fit. Lookalikes find *similar* creators — match scoring tells you if they're a good fit for *this specific campaign*.