curl --request GET \
--url https://external.nebius.tensormesh.ai/v1/models \
--header 'Authorization: Bearer <token>' \
--header 'X-User-Id: <x-user-id>'{
"object": "list",
"data": [
{
"id": "openai-gpt-oss-120b-gpu-type-h200x1_8nic16",
"object": "model",
"owned_by": "vllm"
}
]
}List models from the selected Tensormesh On-Demand host.
curl --request GET \
--url https://external.nebius.tensormesh.ai/v1/models \
--header 'Authorization: Bearer <token>' \
--header 'X-User-Id: <x-user-id>'{
"object": "list",
"data": [
{
"id": "openai-gpt-oss-120b-gpu-type-h200x1_8nic16",
"object": "model",
"owned_by": "vllm"
}
]
}Use this page when you need the raw model catalog from the routed On-Demand inference host.Documentation Index
Fetch the complete documentation index at: https://docs.tensormesh.ai/llms.txt
Use this file to discover all available pages before exploring further.
Authorization: Bearer <API_KEY>X-User-Id: <uuid>model string to reuse in routed On-Demand requestsBearer authentication using your On-Demand API key. Format: Bearer <API_KEY>
Tensormesh user id used for attribution and routing.
Was this page helpful?