About
Nace.AI Drex Max evaluates text, structured JSON, and images using Noul, Choice, and Score questions and returns typed decisions with probabilities. Infron sends synchronous JSON requests directly to Nace.AI using drex-max. Each question has a 262,144-token input limit including the shared state, images, question, and formatting. Each request accepts 1–512 questions. Drex Max also accepts up to eight PNG, JPEG, or WebP images. The API returns one JSON response without streaming or task polling.
1. Calling the API
Setup your API Key
To begin using Infron, create an account and generate your API Key.
export INFRON_KEY="YOUR_API_KEY"
Submit a request
Send JSON to POST https://llm.onerouter.pro/v1/decisions using your Infron API key.
Image request — Data URL
curl --request POST "https://llm.onerouter.pro/v1/decisions" \
--header "Authorization: Bearer $INFRON_KEY" \
--header "Content-Type: application/json" \
--data '{
"model": "nace-ai/drex-max",
"state": "Inspect the supplied image.",
"images": [
"data:image/png;base64,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"
],
"questions": {
"square_color": {
"type": "choice",
"instructions": "What is the color of the square in the image?",
"criteria": {
"red": "Red",
"blue": "Blue",
"green": "Green"
}
}
},
"provider": {
"only": [
"nace"
],
"allow_fallbacks": false,
"service_tier": "standard"
},
"usage": {
"include": true
}
}'
Response
These examples illustrate the response structure. Request IDs are placeholders; answers, usage, timings, and costs vary by request.
Response from Infron
{
"answers": {
"square_color": {
"type": "choice",
"choice": "red",
"probabilities": {
"red": 0.98,
"blue": 0.01,
"green": 0.01
},
"confidence": 0.96
}
},
"cost": 0.000003,
"cost_details": {
"audio_cost": 0,
"byok_cost": 0,
"completion_cost": 0,
"image_cost": 0,
"native_web_search_cost": 0,
"plugin_web_search_cost": 0,
"prompt_cache_read_cost": 0,
"prompt_cache_write_1_h": 0,
"prompt_cache_write_5_min": 0,
"prompt_cache_write_cost": 0,
"reasoning_cost": 0,
"tools_cost": 0,
"video_cost": 0,
"discount_rate": 1,
"is_byok": false,
"prompt_cost": 0.000003
},
"id": "YOUR_REQUEST_ID",
"model": "nace-ai/drex-max",
"provider": "nace",
"request_id": "YOUR_REQUEST_ID",
"service_tier": "standard",
"usage": {
"input_tokens": 100,
"output_tokens": 20
}
}
Nace upstream response structure
{
"model": "drex-max",
"answers": {
"square_color": {
"type": "choice",
"choice": "red",
"probabilities": {
"red": 0.98,
"blue": 0.01,
"green": 0.01
},
"confidence": 0.96
}
},
"usage": {
"input_tokens": 100,
"output_tokens": 20
},
"evaluation_time_ms": 12.3,
"request_id": "req_YOUR_UPSTREAM_REQUEST_ID"
}
Routing and usage
provider.only=["nace"], provider.allow_fallbacks=false, and provider.service_tier="standard" select this route. usage.include=true requests platform cost details. Infron handles these platform fields; they are not sent to Nace. Input and output token counts come from the upstream response. Free output pricing does not change the reported output count.
Errors
Read error.message and retain the request ID. Nace rejects invalid questions, media, or oversized requests. Token, serialized-body, account, and media-content limits are enforced upstream. A Noul question must contain nonempty instructions or a nonempty criterion. Correct invalid inputs before sending another request.
2. Schema
Input
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
model | string | Yes | -- | nace-ai/drex-max | Public model ID; upstream selector is drex-max. |
state | string / number / boolean / null / object / array | Yes | -- | Included in the 262,144-token per-question limit | Shared JSON input; the key must be present and may contain null. |
questions | object | Yes | -- | 1–512 entries | Map of nonblank question IDs to typed questions. |
questions.<id>.type | string | Yes | -- | noul, choice, score | Question type. |
questions.<id>.instructions | string / null | No | -- | String when supplied | Evaluation instructions; null is treated as omitted. |
questions.<id>.criteria | object / array | For choice and score | -- | See Question types | Labels or an ordered rating scale. |
images | array | No | -- | 0–8 images | Base64 strings, Data URLs, or same-account Nace file references. |
provider | object | No | -- | -- | Platform routing options. |
usage.include | boolean | No | false | true, false | Include platform cost details. |
The serialized state and questions plus nonempty images must fit within 4,194,304 UTF-8 bytes. The shared state, images, question, and formatting must fit within 262,144 tokens for each question. These are separate limits, not character counts.
Question types
Noul: yes/no probability
Supply nonempty instructions or at least one nonempty criterion. Optional criteria.true and criteria.false are strings or null. The answer contains type, noul (a probability from 0 to 1), and confidence.
Choice: classification
criteria is an object with 1–255 labels; each description is a string or null. The answer contains choice, probabilities, and confidence.
Score: ordered rating
criteria is an array with 1–255 string levels. Indices start at zero. The answer contains score, the legend array, probabilities, and confidence.
Media inputs
Supply PNG, JPEG, or WebP bytes as a base64 string or Data URL. HTTP/HTTPS URLs are not fetched. The limits are 16 MiB per decoded image, 32 MiB combined, and 40 million source pixels per image. Inline base64 also counts toward the 4 MiB serialized body limit. Nace resizes each image to at most 1,638,400 pixels. Image tokens are included in input usage. Keep media outside state and questions.
Nace also accepts objects with type="workspace_file", workspace_id, and file_id; the file must have been uploaded without a workspace by the Nace account used for this route. A file uploaded under your separate Nace account cannot be used by this route.
Create an image Data URL from local files
import base64
from pathlib import Path
image_url = "data:image/png;base64," + base64.b64encode(
Path("image.png").read_bytes()
).decode("ascii")
Use the actual MIME type of your file. Long questions also share an aggregate budget. Nace may shorten long state before inference and rejects state beyond its selector input limit; see the current Drex Max guide.
Output
| Parameter | Type | Range | Description |
|---|---|---|---|
id, request_id | string | -- | Platform request ID. |
model | string | -- | Public model ID. |
provider, service_tier | string | -- | Selected route. |
answers | object | Request question IDs | Typed answers from Nace. |
answers.<id>.type | string | noul, choice, score | Answer type. |
answers.<id>.noul | number | 0–1 | Yes probability. |
answers.<id>.choice | string | Choice keys | Selected option. |
answers.<id>.score | number | 0 to levels minus 1 | Probability-weighted level. |
answers.<id>.confidence | number | 0–1 | Answer confidence for Noul, Choice, and Score. |
answers.<id>.probabilities | object | Values 0–1 | Probability distribution. |
answers.<id>.legend | array | -- | Score level labels in order. |
usage.input_tokens, usage.output_tokens | integer | Non-negative | Actual upstream usage. |
cost | number | USD | Charge when cost details are requested. |
cost_details | object | -- | Billing breakdown when requested. |
3. Detailed Pricing
| Model | Billing unit | Input price | Output price |
|---|---|---|---|
| Nace.AI Drex Max | Per 1 million tokens | $0.03 | Free |
Billing uses Nace's actual usage.input_tokens. Image tokens are included at the same input rate. There is no separate request or question charge. Nace account credits are separate from Infron account billing.
Sources: Nace models, request schema, question types, limits, pricing, and Drex Max.