ai-text-detector

Async AI text detector — score any text 0–100 for AI authorship with a multi-engine breakdown. Up to 30,000 words per call, billed per word.

ai-text-detector is a single async endpoint that scores text 0–100 for how likely it is AI-generated, aggregating several third-party detection engines into one result plus per-engine sub-scores. See current pricing on the model page.

Quick example

curl https://reapi.ai/api/v1/detect \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ai-text-detector",
    "text": "Citizen science involves the public participating in scientific research. This can take many forms, from collecting data on local wildlife populations to analyzing astronomical images."
  }'

import requests

resp = requests.post(
    "https://reapi.ai/api/v1/detect",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "ai-text-detector",
        "text": "Citizen science involves the public participating in scientific research. This can take many forms, from collecting data on local wildlife populations to analyzing astronomical images.",
    },
    timeout=30,
)
print(resp.json())

const r = await fetch("https://reapi.ai/api/v1/detect", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "ai-text-detector",
    text: "Citizen science involves the public participating in scientific research. This can take many forms, from collecting data on local wildlife populations to analyzing astronomical images.",
  }),
});
console.log(await r.json());

package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "io"
    "net/http"
)

func main() {
    body, _ := json.Marshal(map[string]any{
        "model": "ai-text-detector",
        "text":  "Citizen science involves the public participating in scientific research. This can take many forms, from collecting data on local wildlife populations to analyzing astronomical images.",
    })
    req, _ := http.NewRequest("POST",
        "https://reapi.ai/api/v1/detect", bytes.NewReader(body))
    req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
    req.Header.Set("Content-Type", "application/json")

    resp, _ := http.DefaultClient.Do(req)
    defer resp.Body.Close()
    out, _ := io.ReadAll(resp.Body)
    fmt.Println(string(out))
}

Submit response

{
  "id": "task_018f5a3a1b6e7d9f8c2b4d6e8f0a2c4e",
  "model": "ai-text-detector",
  "status": "processing",
  "created_at": 1735000000
}

Poll GET /api/v1/tasks/{id} until status === "completed". A check usually finishes in a few seconds.

Authentication

Every call needs a Bearer token. Generate keys at reapi.ai/settings/apikeys.

Authorization: Bearer YOUR_API_KEY

Endpoint

POST /api/v1/detect
GET  /api/v1/tasks/{id}

Submission is async. The POST returns immediately with a task_id; polling the task endpoint returns the same envelope until completion. Polling does not consume credits.

Request body

`model` — required

Always "ai-text-detector".

`text` — required (string)

The text to check for AI authorship.

Maximum: under 30,000 words per request.
Recommended: at least ~200 words. Short snippets carry less signal, though the detector still returns a result.
Encode line breaks inside the JSON string as \n.

Output

{
  "id": "task_018f5a3a1b6e7d9f8c2b4d6e8f0a2c4e",
  "model": "ai-text-detector",
  "status": "completed",
  "created_at": 1735000000,
  "output": {
    "detection": {
      "result": 12.0,
      "human": 88.0,
      "detectors": {
        "scoreGptZero": 50.0,
        "scoreOpenAI": 0.0,
        "scoreWriter": 0.0,
        "scoreCrossPlag": 0.0,
        "scoreCopyLeaks": 50.0,
        "scoreSapling": 0.0,
        "scoreContentAtScale": 0.0,
        "scoreZeroGPT": 50.0
      }
    }
  },
  "error": null
}

Interpreting the score

result is the headline AI-likelihood, 0–100:

Range	Reading
under 50	Likely human-written.
50 – 60	Possible AI.
over 60	Likely AI-generated.

human is the complementary human-likelihood. detectors carries each third-party engine's sub-score so you can see whether the engines agree or split. The headline result is the most accurate signal; treat the sub-scores as supporting detail.

Pricing

Billed per word of the text you submit, with a 50-word floor. AI detection is priced at one-tenth the per-word rate of text humanization. Polling does not add any charge. Failed requests are refunded automatically.

1 credit = $0.001 USD. See the live banner on the model page for the current per-1,000-words rate in credits.

Errors

Standard envelope:

{
  "error": {
    "code": 20002,
    "message": "text is required",
    "request_id": "req_..."
  }
}

Common cases:

Code	When
`20002`	`text` missing.
`20003`	`text` empty or at/over the 30,000-word cap.
`30001`	Insufficient credits for the submitted word count.
`80001`	Provider rejected the submission — includes insufficient upstream credits.
`80003`	Provider failed while processing the detection.

AI Humanizer — rewrite AI text to read human. Pair it with ai-text-detector for a detect → rewrite → detect QA loop.

Quick example

curl https://reapi.ai/api/v1/detect \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ai-text-detector",
    "text": "Citizen science involves the public participating in scientific research. This can take many forms, from collecting data on local wildlife populations to analyzing astronomical images."
  }'

import requests

resp = requests.post(
    "https://reapi.ai/api/v1/detect",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "ai-text-detector",
        "text": "Citizen science involves the public participating in scientific research. This can take many forms, from collecting data on local wildlife populations to analyzing astronomical images.",
    },
    timeout=30,
)
print(resp.json())

const r = await fetch("https://reapi.ai/api/v1/detect", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "ai-text-detector",
    text: "Citizen science involves the public participating in scientific research. This can take many forms, from collecting data on local wildlife populations to analyzing astronomical images.",
  }),
});
console.log(await r.json());

package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "io"
    "net/http"
)

func main() {
    body, _ := json.Marshal(map[string]any{
        "model": "ai-text-detector",
        "text":  "Citizen science involves the public participating in scientific research. This can take many forms, from collecting data on local wildlife populations to analyzing astronomical images.",
    })
    req, _ := http.NewRequest("POST",
        "https://reapi.ai/api/v1/detect", bytes.NewReader(body))
    req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
    req.Header.Set("Content-Type", "application/json")

    resp, _ := http.DefaultClient.Do(req)
    defer resp.Body.Close()
    out, _ := io.ReadAll(resp.Body)
    fmt.Println(string(out))
}

Submit response

{
  "id": "task_018f5a3a1b6e7d9f8c2b4d6e8f0a2c4e",
  "model": "ai-text-detector",
  "status": "processing",
  "created_at": 1735000000
}

Poll GET /api/v1/tasks/{id} until status === "completed". A check usually finishes in a few seconds.

Authentication

Every call needs a Bearer token. Generate keys at reapi.ai/settings/apikeys.

Authorization: Bearer YOUR_API_KEY

Endpoint

POST /api/v1/detect
GET  /api/v1/tasks/{id}

Submission is async. The POST returns immediately with a task_id; polling the task endpoint returns the same envelope until completion. Polling does not consume credits.

Maximum: under 30,000 words per request.
Recommended: at least ~200 words. Short snippets carry less signal, though the detector still returns a result.
Encode line breaks inside the JSON string as \n.

Output

{
  "id": "task_018f5a3a1b6e7d9f8c2b4d6e8f0a2c4e",
  "model": "ai-text-detector",
  "status": "completed",
  "created_at": 1735000000,
  "output": {
    "detection": {
      "result": 12.0,
      "human": 88.0,
      "detectors": {
        "scoreGptZero": 50.0,
        "scoreOpenAI": 0.0,
        "scoreWriter": 0.0,
        "scoreCrossPlag": 0.0,
        "scoreCopyLeaks": 50.0,
        "scoreSapling": 0.0,
        "scoreContentAtScale": 0.0,
        "scoreZeroGPT": 50.0
      }
    }
  },
  "error": null
}

Interpreting the score

result is the headline AI-likelihood, 0–100:

Range	Reading
under 50	Likely human-written.
50 – 60	Possible AI.
over 60	Likely AI-generated.

Pricing

1 credit = $0.001 USD. See the live banner on the model page for the current per-1,000-words rate in credits.

Errors

Standard envelope:

{
  "error": {
    "code": 20002,
    "message": "text is required",
    "request_id": "req_..."
  }
}

Common cases:

Code	When
`20002`	`text` missing.
`20003`	`text` empty or at/over the 30,000-word cap.
`30001`	Insufficient credits for the submitted word count.
`80001`	Provider rejected the submission — includes insufficient upstream credits.
`80003`	Provider failed while processing the detection.

AI Humanizer — rewrite AI text to read human. Pair it with ai-text-detector for a detect → rewrite → detect QA loop.

ai-text-detector

Quick example

Submit response

Authentication

Endpoint

Request body

`model` — required

`text` — required (string)

Output

Interpreting the score

Pricing

Errors

Table of Contents

ai-text-detector

Quick example

Submit response

Authentication

Endpoint

Request body

`model` — required

`text` — required (string)

Output

Interpreting the score

Pricing

Errors

Table of Contents