Model Fluency Query
Query the fluency status (congestion level) of each model on the platform. No authentication required.
Query the fluency status of each model on the platform, indicating the current response congestion level. Fluency is determined by the system periodically submitting real image generation tasks to each model and recording the elapsed time, divided into four levels.
- Endpoint:
GET https://apione.org/v1/api/fluency - Authentication: Not required
Request Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | No | Filter by exact model name; returns all enabled models when omitted |
Response Fields
| Field | Type | Description |
|---|---|---|
success | bool | Whether the request succeeded |
data | array | Model fluency list |
data[].model_name | string | Model name |
data[].fluency_status | int | Fluency level (see table below) |
data[].fluency_label | string | Fluency label |
data[].last_test_time | string | Last test completion time (UTC+8, format YYYY-MM-DD HH:MM:SS); empty string if not tested |
fluency_status Values
| Value | Label | Meaning |
|---|---|---|
0 | Not Tested | No fluency test has been conducted yet |
1 | Fluent | Test succeeded and elapsed time ≤ 3 minutes (green) |
2 | Slight Congestion | Test succeeded and elapsed time 3~5 minutes (blue) |
3 | Moderate Congestion | Test succeeded but elapsed time > 5 minutes (yellow) |
4 | Severe Congestion | Test failed, or no result within 30 minutes (red) |
Request Examples
# Query all models
curl -X GET "https://apione.org/v1/api/fluency"
# Query a single model
curl -X GET "https://apione.org/v1/api/fluency?model=gpt-image-1"Response Example
{
"success": true,
"data": [
{
"model_name": "gpt-image-1",
"fluency_status": 1,
"fluency_label": "Fluent",
"last_test_time": "2026-06-08 14:30:00"
},
{
"model_name": "dall-e-3",
"fluency_status": 3,
"fluency_label": "Moderate Congestion",
"last_test_time": "2026-06-08 12:00:00"
},
{
"model_name": "stable-diffusion-xl",
"fluency_status": 0,
"fluency_label": "Not Tested",
"last_test_time": ""
}
]
}Note:
last_test_timeis always in UTC+8 timezone.
Token Balance Query
Query the quota information of the current API Key or account, compatible with OpenAI billing API format.
Language Models
Call the platform's LLMs via a unified chat completion interface. Compatible with OpenAI, Claude, and Gemini request formats, with streaming, function calling, and vision support.