> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vlm.run/llms.txt
> Use this file to discover all available pages before exploring further.
# Get Model
> Retrieve a single VLM Run Gateway model and its capabilities
Authentication is optional. See [Rate Limits](/gateway/rate-limits) for per-tier
quotas. For the full catalog, use [List Models](/gateway/api-reference/get-models)
or see [Models](/gateway/models).
`model_id` is a path parameter, so any `/` in the id (e.g. `paddleocr/pp-ocrv6`)
must be percent-encoded as `%2F`. An unencoded slash is read as two path
segments and returns `404`.
```python Python theme={"theme":{"light":"github-light","dark":"dark-plus"}}
import httpx
from urllib.parse import quote
model_id = quote("paddleocr/pp-ocrv6", safe="")
response = httpx.get(
f"https://gateway.vlm.run/v1/models/{model_id}",
headers={"Authorization": "Bearer "},
)
print(response.json())
```
```bash cURL theme={"theme":{"light":"github-light","dark":"dark-plus"}}
curl "https://gateway.vlm.run/v1/models/paddleocr%2Fpp-ocrv6" \
-H "Authorization: Bearer $VLMRUN_API_KEY"
```
```typescript Node.js theme={"theme":{"light":"github-light","dark":"dark-plus"}}
const modelId = encodeURIComponent("paddleocr/pp-ocrv6");
const response = await fetch(`https://gateway.vlm.run/v1/models/${modelId}`, {
headers: { Authorization: "Bearer " },
});
console.log(await response.json());
```
## Response fields
This endpoint returns a flat, single-model detail object, richer than the
entries in [`GET /v1/openai/models`](/gateway/api-reference/get-models):
| Field | Description |
| ---------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `id` | Preferred public model id. |
| `name`, `description` | Human-readable catalog metadata. |
| `hf_model_id` | Upstream Hugging Face repo id, when the model is open-weight. |
| `task` | `chat`, `embed`, or `transcribe`. |
| `context_length` | Maximum context length, when defined. |
| `architecture` | `input_modalities`, `output_modalities`, and a summary `modality` string. |
| `capabilities` | Same shape as on [List Models](/gateway/api-reference/get-models#model-fields): max images/videos, accepted input types. |
| `aliases`, `methods` | Accepted request ids and supported `method` values. |
| `supported_parameters` | Request fields this model actually honors (a model may ignore fields like `temperature` or `top_p` that don't apply to it). |
| `pricing` | USD per 1M tokens for `prompt`, `completion`, `image`, `input_cache_read`, and `input_cache_write`, plus `request` and `per_page` flat rates. Zero during the free alpha; see [Pricing](/gateway/pricing). |
`pricing` and `supported_parameters` are only available here, not on the
list endpoint. Fetch a single model's detail before you build cost
estimates or validate which request fields it will respect.
## Related
Full catalog in one call.
How to read the `pricing` object during the free alpha.
## OpenAPI
````yaml gateway/openapi.json GET /v1/models/{model_id}
openapi: 3.1.0
info:
title: VLM Run Gateway API
summary: Unified gateway for real-time vision-language inference.
description: |
The **VLM Run Gateway API** is the public entry point to the VLM Run
inference platform. It fronts vision-language and computer-vision models
behind a single OpenAI-compatible surface plus first-class real-time
transports.
[Terms of service](https://vlm.run/terms) |
[VLM Run](https://vlm.run) |
[Send email to support@vlm.run](mailto:support@vlm.run)
termsOfService: https://vlm.run/terms
contact:
name: VLM Run
url: https://vlm.run/
email: support@vlm.run
version: 0.10.0
servers:
- url: https://gateway.vlm.run
description: Production
- url: http://localhost:8001
description: Local development
security: []
paths:
/v1/models/{model_id}:
get:
summary: Get Model Detail
operationId: get_model_detail_v1_models__model_id__get
parameters:
- name: model_id
in: path
required: true
schema:
type: string
title: Model Id
example: {}
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/ModelDetail'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- HTTPBearer: []
components:
schemas:
ModelDetail:
properties:
id:
type: string
title: Id
hf_model_id:
anyOf:
- type: string
- type: 'null'
title: Hf Model Id
name:
type: string
title: Name
description:
type: string
title: Description
task:
type: string
enum:
- chat
- embed
- transcribe
title: Task
default: chat
context_length:
anyOf:
- type: integer
- type: 'null'
title: Context Length
architecture:
$ref: '#/components/schemas/ModelArchitecture'
capabilities:
$ref: '#/components/schemas/ModelCapabilities'
aliases:
items:
type: string
type: array
title: Aliases
methods:
items:
type: string
type: array
title: Methods
supported_parameters:
items:
type: string
type: array
title: Supported Parameters
pricing:
$ref: '#/components/schemas/ModelPricing'
type: object
required:
- id
- name
- description
- architecture
- capabilities
- pricing
title: ModelDetail
description: |-
Flat JSON response for ``GET /v1/models/{model_id}``.
Internal catalog fields such as ``provider`` are intentionally omitted.
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
ModelArchitecture:
properties:
input_modalities:
items:
type: string
type: array
title: Input Modalities
output_modalities:
items:
type: string
type: array
title: Output Modalities
modality:
type: string
title: Modality
type: object
required:
- input_modalities
- output_modalities
- modality
title: ModelArchitecture
ModelCapabilities:
properties:
max_images:
anyOf:
- type: integer
- type: 'null'
title: Max Images
default: 1
max_videos:
anyOf:
- type: integer
- type: 'null'
title: Max Videos
default: 0
supports_text_only:
type: boolean
title: Supports Text Only
default: true
supports_document_url:
type: boolean
title: Supports Document Url
default: false
supported_input_types:
items:
type: string
type: array
title: Supported Input Types
type: object
title: ModelCapabilities
description: |-
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.
ModelPricing:
properties:
prompt:
type: number
title: Prompt
default: 0
completion:
type: number
title: Completion
default: 0
input_cache_read:
type: number
title: Input Cache Read
default: 0
input_cache_write:
type: number
title: Input Cache Write
default: 0
image:
type: number
title: Image
default: 0
request:
type: number
title: Request
default: 0
per_page:
type: number
title: Per Page
default: 0
type: object
title: ModelPricing
description: USD per 1M tokens (``image`` is per-1M image-token equivalent).
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
input:
title: Input
ctx:
type: object
title: Context
type: object
required:
- loc
- msg
- type
title: ValidationError
securitySchemes:
HTTPBearer:
type: http
scheme: bearer
````