Overview
The model catalog is the entry point for capabilities, ratios, size tiers, public prices, and routability. Do not hard-code model capabilities in a client; inspect the current catalog before submission.
Authentication: No authentication
Request
Query parameters
| Name | Type | Description |
|---|---|---|
model_company | string | Filter by published model company. |
modality | string | Filter by modality, for example image. |
page | integer | Page number, starting at 1. |
page_size | integer | Items per page, 1–100; default 20. |
Response
JSON endpoints use the standard response envelope. HTTP status represents the request outcome; business errors are not disguised as HTTP 200.
| HTTP | Meaning |
|---|---|
200 | Request succeeded |
400 | Invalid business parameter or filter |
422 | Request-structure validation failed |
500 | Internal service error |
Complete success example (optional fields vary by state)
{
"code": 0,
"message": "success",
"data": {
"items": [
{
"model_id": "gpt-image-2",
"company": "OpenAI",
"modality": "image",
"lifecycle_status": "active",
"availability_status": "available",
"capabilities": [],
"verified_capabilities": []
}
],
"total": 1,
"page": 1,
"page_size": 20
},
"request_id": "8f25b42f-2ed1-4ad7-99de-61d7f779bc7b",
"timestamp": "2026-08-10T00:00:00Z"
}Important boundaries
- Public and read-only. Capabilities and prices come from the returned current snapshot.