HeyGen Decision 1 Turbo overview
Decision example
Help! My payments have been failing for 3 days.
| Question | Result |
|---|---|
| Damaged item | P(yes): 0.0004 |
| Team | billing (confidence 0.9943) |
| Urgency | 0.8706 / 2 (confidence 0.7965) |
Actual model response from Nov 20, 2026.
View request and response
Request
{
"model": "heygen/decision-1-turbo",
"state": "Help! My payments have been failing for 3 days.",
"questions": {
"damaged_item": {
"type": "noul",
"instructions": "Does the customer report an item that arrived damaged?"
},
"team": {
"type": "choice",
"instructions": "Which team should handle this request?",
"criteria": {
"returns": "Damaged products, replacements and returns",
"billing": "Payments, invoices and charges",
"technical": "App errors and integrations"
}
},
"urgency": {
"type": "score",
"instructions": "Rate how urgently the request needs attention.",
"criteria": [
"Routine follow-up",
"Customer is blocked",
"Immediate safety risk"
]
}
}
}Response
{
"model": "heygen-decision-1-turbo",
"answers": {
"damaged_item": {
"noul": 0.0003799845312014112,
"type": "noul"
},
"team": {
"choice": "billing",
"confidence": 0.9943066456895693,
"probabilities": {
"billing": 0.9962044304597129,
"returns": 0.00020269614342955923,
"technical": 0.0035928733968576087
},
"type": "choice"
},
"urgency": {
"confidence": 0.7964994731258297,
"legend": {
"0": "Routine follow-up",
"1": "Customer is blocked",
"2": "Immediate safety risk"
},
"probabilities": {
"0": 0.13254974593472657,
"1": 0.8643329820838865,
"2": 0.003117271981386943
},
"score": 0.8705675260466604,
"type": "score"
}
},
"usage": {
"input_tokens": 605,
"output_tokens": 0
}
}HeyGen Decision 1 Turbo by HeyGen
HeyGen built Decision 1 Turbo as a preview model that answers named yes/no, choice and score questions. HeyGen recommends Decision 1 for classifying, checking and scoring content based on shared text or structured state and optional media.
HeyGen Decision 1 Turbo specs
- Model ID
heygen/decision-1-turbo- Developer
- HeyGen
- Context window
- 262,144 tokens
- Input
- Image, Text
- Output
- Text
- Endpoint
POST https://api.aimlapi.com/v1/decisions
One request, many typed answers
A request carries a map of question keys to typed questions. Each key comes back with a result of the matching type, so one call can run a checklist of 1 to 400 questions against the same material.
Put all checks for one piece of content into a single request. Share the text and media once instead of sending one call per question.
Pick the question type first
A yes/no question returns the probability of yes as a value from 0 to 1. You can add descriptions of what true and false mean for that question, as text or as a JSON object or array. A choice question takes 2 to 255 options and returns the selected key, a calibrated confidence and a probability for each option.
A score question takes 2 to 10 ordered level descriptions, lowest first. It returns an expected level index that may be fractional, such as 1.34, plus a confidence, the legend and a probability per level. Start with yes/no questions and write out what true and false mean. Read the probabilities in the response and set your own threshold instead of relying only on the label.
Sizing a request with media
HeyGen describes the model as answering questions about text, images, video and audio. It states limits of up to 100 images per request, up to 10 videos of at most 60 seconds each, and up to 10 audio clips of at most 30 minutes each.
Start with a small batch of your own media and compare the probabilities against labels you already trust before you raise the volume.
Use cases
Check whether an uploaded image and its caption match a content policy and get the probability of a violation.
Sort support messages into one of a fixed set of categories and keep the confidence for routing rules.
Score the quality of a product listing on an ordered scale from poor to excellent.
Run a list of yes/no checks on a batch of images in a single request.
Capabilities
- Vision
HeyGen Decision 1 Turbo API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $0.084 | 1M tokens |
| Output | $0 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 20, 2026.
How to use the HeyGen Decision 1 Turbo API
View docs (opens in a new tab)Build with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/decisions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "heygen/decision-1-turbo",
"state": "Help! My payments have been failing for 3 days.",
"questions": {
"damaged_item": {
"type": "noul",
"instructions": "Does the customer report an item that arrived damaged?"
},
"team": {
"type": "choice",
"instructions": "Which team should handle this request?",
"criteria": {
"returns": "Damaged products, replacements and returns",
"billing": "Payments, invoices and charges",
"technical": "App errors and integrations"
}
},
"urgency": {
"type": "score",
"instructions": "Rate how urgently the request needs attention.",
"criteria": [
"Routine follow-up",
"Customer is blocked",
"Immediate safety risk"
]
}
}
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "heygen/decision-1-turbo",
"state": "Help! My payments have been failing for 3 days.",
"questions": {
"damaged_item": {
"type": "noul",
"instructions": "Does the customer report an item that arrived damaged?"
},
"team": {
"type": "choice",
"instructions": "Which team should handle this request?",
"criteria": {
"returns": "Damaged products, replacements and returns",
"billing": "Payments, invoices and charges",
"technical": "App errors and integrations"
}
},
"urgency": {
"type": "score",
"instructions": "Rate how urgently the request needs attention.",
"criteria": [
"Routine follow-up",
"Customer is blocked",
"Immediate safety risk"
]
}
}
}
response = requests.post("https://api.aimlapi.com/v1/decisions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/decisions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "heygen/decision-1-turbo",
"state": "Help! My payments have been failing for 3 days.",
"questions": {
"damaged_item": {
"type": "noul",
"instructions": "Does the customer report an item that arrived damaged?"
},
"team": {
"type": "choice",
"instructions": "Which team should handle this request?",
"criteria": {
"returns": "Damaged products, replacements and returns",
"billing": "Payments, invoices and charges",
"technical": "App errors and integrations"
}
},
"urgency": {
"type": "score",
"instructions": "Rate how urgently the request needs attention.",
"criteria": [
"Routine follow-up",
"Customer is blocked",
"Immediate safety risk"
]
}
}
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());HeyGen Decision 1 Turbo FAQ
How much does HeyGen Decision 1 Turbo cost?
HeyGen Decision 1 Turbo is billed at $0.084 / 1M tokens for input. There are no output-token charges.
Which question types does HeyGen Decision 1 Turbo support?
It supports yes/no, choice and score questions. Each question has its own key, and every key comes back with a result of that type.
How many questions and options can one request hold?
A request holds 1 to 400 questions. A choice question takes 2 to 255 options, and a score question takes 2 to 10 levels.
What does a score answer contain?
It contains the expected level index, which may be fractional, and a calibrated confidence. It also returns the legend as you gave it and a probability for each level.
Can I give the model more context about what a question means?
Yes. A yes/no question accepts descriptions of what true and false mean. Choice options and score levels accept descriptions as text or as a JSON object or array, and a choice option can be null when its key is self-explanatory.
What is the HeyGen Decision 1 Turbo model ID?
Use heygen/decision-1-turbo as the model parameter. Requests go to https://api.aimlapi.com/v1/decisions with your AI/ML API key.