Skip to main content
GET
/
v1
/
models
/
{model_id}
import httpx

response = httpx.get(
    "https://gateway.vlm.run/v1/models/paddleocr/pp-ocrv6",
    headers={"Authorization": "Bearer <VLMRUN_API_KEY>"},
)
print(response.json())

{
  "id": "<string>",
  "name": "<string>",
  "description": "<string>",
  "architecture": {
    "input_modalities": [
      "<string>"
    ],
    "output_modalities": [
      "<string>"
    ],
    "modality": "<string>"
  },
  "capabilities": {
    "max_images": 1,
    "max_videos": 0,
    "supports_text_only": true,
    "supports_document_url": false,
    "supported_input_types": [
      "<string>"
    ]
  },
  "pricing": {
    "prompt": 0,
    "completion": 0,
    "input_cache_read": 0,
    "input_cache_write": 0,
    "image": 0,
    "request": 0,
    "per_page": 0
  },
  "hf_model_id": "<string>",
  "task": "chat",
  "context_length": 123,
  "aliases": [
    "<string>"
  ],
  "methods": [
    "<string>"
  ],
  "supported_parameters": [
    "<string>"
  ]
}
Authentication is optional. See Rate Limits for per-tier quotas. For the full catalog, use List Models or see Models. 
import httpx

response = httpx.get(
    "https://gateway.vlm.run/v1/models/paddleocr/pp-ocrv6",
    headers={"Authorization": "Bearer <VLMRUN_API_KEY>"},
)
print(response.json())

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

​
model_id
string
required

Response

Successful Response

Flat JSON response for GET /v1/models/{model_id}.

Internal catalog fields such as provider are intentionally omitted.

​
id
string
required
​
name
string
required
​
description
string
required
​
architecture
ModelArchitecture · object
required
​
capabilities
ModelCapabilities · object
required

Declared input capabilities exposed via GET /v1/openai/models.

Mirrors :class:vlmrt.chat.backends.ChatCapabilities but as a Pydantic model so the info surfaces cleanly in the API response (and in the vlmrt chat --models table). None means unlimited.

​
pricing
ModelPricing · object
required

USD per 1M tokens (image is per-1M image-token equivalent).

​
hf_model_id
string | null
​
task
enum<string>
default:chat
Available options:
chat,
embed,
transcribe
​
context_length
integer | null
​
aliases
string[]
​
methods
string[]
​
supported_parameters
string[]