List local model-profile readiness.

Returns curated model profiles with local runtime readiness, install status, route-tier policy, benchmark hints, and paid-route gates. Runtime IDs are local-only details and should not be copied into public payloads.

GET /v1/model-profiles

Authentication

Bearer Token

Responses

200 Local model-profile readiness.

application/json

model_profiles object[] REQUIRED

Array of:

id string REQUIRED

name string REQUIRED

tier string REQUIRED

family string

capability string

runtime_id string REQUIRED

runtime_kind string REQUIRED

runtime_version string

route_tier string

model string REQUIRED

use_case string REQUIRED

description string REQUIRED

download_size_gb integer

parameters_b number

serving_backend string

artifact_format string

quantization string

scheduler_features string[]

Array of: string

context_window_tokens integer

max_concurrency integer

queue_health string

recent_latency_ms integer

min_ram_gb integer REQUIRED

min_vram_gb integer REQUIRED

requires_gpu boolean REQUIRED

network_eligible boolean REQUIRED

benchmark_verified boolean REQUIRED

paid_route_eligible boolean REQUIRED

benchmark_summary object

recommended boolean REQUIRED

recommended_reason string

source string

status string REQUIRED

notes string[]

Array of: string

default B3IQ-native problem response.

curl -X GET 'http://127.0.0.1:8831/v1/model-profiles' \  -H 'Authorization: Bearer YOUR_API_TOKEN'

const response = await fetch('http://127.0.0.1:8831/v1/model-profiles', {  method: 'GET',  headers: {      "Authorization": "Bearer YOUR_API_TOKEN"  }});const data = await response.json();console.log(data);

import requestsheaders = {    'Authorization': 'Bearer YOUR_API_TOKEN'}response = requests.get('http://127.0.0.1:8831/v1/model-profiles', headers=headers)print(response.json())

200 Response

{  "model_profiles": [    {      "id": "<string>",      "name": "<string>",      "tier": "<string>",      "family": "<string>",      "capability": "<string>",      "runtime_id": "<string>",      "runtime_kind": "<string>",      "runtime_version": "<string>",      "route_tier": "<string>",      "model": "<string>",      "use_case": "<string>",      "description": "<string>",      "download_size_gb": 123,      "parameters_b": 123,      "serving_backend": "<string>",      "artifact_format": "<string>",      "quantization": "<string>",      "scheduler_features": [        "<string>"      ],      "context_window_tokens": 123,      "max_concurrency": 123,      "queue_health": "<string>",      "recent_latency_ms": 123,      "min_ram_gb": 123,      "min_vram_gb": 123,      "requires_gpu": true,      "network_eligible": true,      "benchmark_verified": true,      "paid_route_eligible": true,      "benchmark_summary": "<object>",      "recommended": true,      "recommended_reason": "<string>",      "source": "<string>",      "status": "<string>",      "notes": [        "<string>"      ]    }  ]}

default Response

{  "error": {    "status": 123,    "title": "<string>",    "detail": "<string>",    "code": "<string>"  }}

GET /v1/model-profiles

Base URL

Response

Was this page helpful?

Previous List locally installed OpenAI-compatible models.

Next List recent local receipts.