Model Routes — ML Junction docs

GET /v1/models/{public_model}/routes returns every active serving route for a public model. The backend orders routes by 30-day uptime descending, then input price ascending, then route priority.

curl "$ASTRO_BASE_URL/v1/models/gpt-5.5/routes"

{
  "route_id": "openai-gpt-5.5-global-standard",
  "provider": "openai",
  "provider_model": "gpt-5.5",
  "company": "openai",
  "region": "global",
  "endpoint_type": "serverless",
  "priority": 100,
  "quantization": "unknown",
  "context_tier": "extended",
  "context_window_tokens": 1050000,
  "max_output_tokens": 128000,
  "capabilities": {
    "streaming": true,
    "tools": true,
    "parallel_tools": true,
    "json_object": true,
    "json_schema": true,
    "vision": true,
    "audio": false,
    "pdf": true,
    "reasoning": true,
    "prompt_caching": true,
    "modalities": {
      "input": ["text", "image", "pdf"],
      "output": ["text"]
    },
    "supported_params": ["temperature", "top_p", "seed"]
  },
  "stats": {
    "throughput_tps": 86.4,
    "latency_p50_ms": 280,
    "latency_p95_ms": 540,
    "latency_p99_ms": 910,
    "uptime_30d": 99.94
  },
  "privacy": {
    "supports_zdr": true,
    "zdr_enabled": false,
    "training_allowed": false,
    "retention": "provider_api_policy",
    "privacy_rank": 3
  },
  "pricing": {
    "currency": "USD",
    "input_per_mtok": 1.25,
    "cached_input_per_mtok": 0.125,
    "output_per_mtok": 10,
    "effective_from": "2026-06-13T00:00:00Z",
    "effective_to": null,
    "source": "https://..."
  }
}

An unknown model returns 404. Individual telemetry keys or the complete stats object may be absent until the route has enough observations.

Canonical URL: https://mljunction.com/docs/model-routes