from openai import OpenAI
client = OpenAI(
base_url="https://gateway.vlm.run/v1/openai",
api_key="<VLMRUN_API_KEY>",
)
models = client.models.list()
for model in models.data:
caps = model.capabilities
print(f"{model.id}: {caps.supported_input_types}")
curl https://gateway.vlm.run/v1/openai/models \
-H "Authorization: Bearer $VLMRUN_API_KEY"
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://gateway.vlm.run/v1/openai",
apiKey: process.env.VLMRUN_API_KEY,
});
const models = await client.models.list();
for (const model of models.data) {
console.log(model.id);
}
API Reference
List Models
List available VLM Run Gateway models and their capabilities
GET
/
v1
/
openai
/
models
from openai import OpenAI
client = OpenAI(
base_url="https://gateway.vlm.run/v1/openai",
api_key="<VLMRUN_API_KEY>",
)
models = client.models.list()
for model in models.data:
caps = model.capabilities
print(f"{model.id}: {caps.supported_input_types}")
curl https://gateway.vlm.run/v1/openai/models \
-H "Authorization: Bearer $VLMRUN_API_KEY"
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://gateway.vlm.run/v1/openai",
apiKey: process.env.VLMRUN_API_KEY,
});
const models = await client.models.list();
for (const model of models.data) {
console.log(model.id);
}
Send
Authorization: Bearer vlmrun for anonymous access. This route draws on
the same rate-limit budget as chat completions. See
Authentication for tier details.
For availability status and use-case guidance, see Models.
Model fields
VLM Run Gateway model entries extend the OpenAI list-models shape with these fields:| Field | Description |
|---|---|
id | Preferred public model id (use this in POST /chat/completions). |
aliases | All accepted request ids, including short and Hugging Face forms. |
methods | Operations supported via the method request field. This list is authoritative: a method not listed is a 400. |
default_method | Applied when method is omitted. |
extra_body_help | Example method / method_params payloads. |
capabilities | Input limits and accepted content part types. |
task | chat, embed, or transcribe (non-chat models use other endpoints). |
from openai import OpenAI
client = OpenAI(
base_url="https://gateway.vlm.run/v1/openai",
api_key="<VLMRUN_API_KEY>",
)
models = client.models.list()
for model in models.data:
caps = model.capabilities
print(f"{model.id}: {caps.supported_input_types}")
curl https://gateway.vlm.run/v1/openai/models \
-H "Authorization: Bearer $VLMRUN_API_KEY"
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://gateway.vlm.run/v1/openai",
apiKey: process.env.VLMRUN_API_KEY,
});
const models = await client.models.list();
for (const model of models.data) {
console.log(model.id);
}
The OpenAI Python and Node.js SDKs may not surface VLM Run Gateway-specific
fields like
capabilities or methods on the typed Model object. Parse
the raw response or use cURL when you need the full catalog metadata.Related
Models
Full catalog with availability status and use-case guidance.
Chat Completions
Send inference requests using model ids from this endpoint.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Response
200 - application/json
Successful Response