gen_8w3se82kiq

Decision timeline

1. admission+0 ms

   chat request by prin_admin under profile @company/general-balanced (requested "anthropic/claude-sonnet")

2. PRE_ROUTE+0 ms
   allowsize-budgetno findings [0.00ms]
3. PRE_ROUTE+0 ms
   allowprompt-injection-heuristicno findings [0.00ms]
4. PRE_MODEL+0 ms
   allowpattern-dlpno findings [0.00ms]
5. PRE_MODEL+0 ms
   allowsecrets-scannerno findings [0.00ms]
6. cache+0 ms

   cache bypassed (policy off or non-cacheable request)

7. route+0 ms

   selected anthropic/claude-sonnet via anthropic/acct_anthropic_ent_apse1 on node_sg_dc_01 (A-tier, ap-southeast-1) — objective=balanced, 9 candidates scored, 8 in fallback chain, 0 hard-filter rejections [router router_1.0, policy rp_default/@company/general-balanced@v7]

   9 candidates considered9 survived hard filters0 rejectedobjective: balancedfallback chain: 8router_1.0 · rp_default/@company/general-balanced@v7

   Score breakdown — top 5

   #	Candidate	quality	cacheSavings	contractValue	completionProbability	cost	latencyPenalty	shadowPrice	retryRisk	affinityPenalty	guardrailCost	Total
   1	anthropic/claude-sonnet via anthropic · node_sg_dc_01 selected	+0.558	+0.056	+0.024	+0.396	-0.037	-0.061	-0.029	-0.003	0.000	-0.040	0.864
   2	anthropic/claude-sonnet via anthropic · node_cf_use1_01	+0.558	0.000	+0.024	+0.398	-0.037	-0.061	-0.029	-0.001	0.000	-0.040	0.812
   3	anthropic/claude-sonnet via anthropic · node_sg_dc_01	+0.558	0.000	+0.024	+0.396	-0.037	-0.073	-0.029	-0.003	0.000	-0.040	0.796
   4	anthropic/claude-sonnet via anthropic · node_my_kul_office_01	+0.558	0.000	+0.024	+0.388	-0.037	-0.063	-0.029	-0.007	0.000	-0.040	0.793
   5	anthropic/claude-sonnet via anthropic · node_my_kul_office_01	+0.558	0.000	+0.024	+0.388	-0.037	-0.075	-0.029	-0.007	0.000	-0.040	0.781

8. attempt #1+0 ms

   #1 anthropic · account acct_anthropic_ent_apse1 · node node_sg_dc_01 — succeeded in 1314ms, 10 prompt-cached tokens

   succeededanthropicacct_anthropic_ent_apse1pool enterprisenode_sg_dc_01Tier C1.31 s

   12 in / 338 out / 10 cached

9. POST_MODEL+0 ms
   allowtoxicity-liteno findings [0.00ms]
10. PRE_RETURN+0 ms
    allowschema-validatorno findings [0.00ms]
11. settlement+1314 ms

    settled $0.005079 — 12 in / 338 out / 10 cached tokens (350 total)

    Ledger entries

    • reserve$0.0062budget:bud_proj_corereserve est max for anthropic/claude-sonnet
    • settle$0.0051budget:bud_proj_coresettle actual provider usage (350 tok, internal charge $0.005374)
    • settle−$0.0051account:acct_anthropic_ent_apse1credit provider account acct_anthropic_ent_apse1 (double-entry counterpart)
    • refund−$0.0011budget:bud_proj_corerefund unused reservation

    Cost layers (memo §15.3)

    Provider list

    $0.0051

    Contract-adjusted

    $0.0047

    Internal charge

    $0.0054

    Contract savings

    $0.0004

    contract ct_anthropic_committed (committed)

12. complete+1314 ms

    status=succeeded, model=anthropic/claude-sonnet, 1314ms end-to-end

fabric_metadata

The route-explanation envelope an API caller receives with X-OpenRouter-Metadata: enabled or routing.explain, reconstructed from this generation record.

{
  "requested": "anthropic/claude-sonnet",
  "resolved_model": "anthropic/claude-sonnet",
  "strategy": "balanced",
  "policy_version": "rp_default/@company/general-balanced@v7",
  "router_version": "router_1.0",
  "provider": "anthropic",
  "region": "ap-southeast-1",
  "account_pool": "enterprise",
  "node": {
    "ref": "node_sg_dc_01",
    "trust_tier": "C"
  },
  "cache": {
    "response": "BYPASS",
    "prompt_affinity": "HIT",
    "predicted_cached_tokens": 10
  },
  "guardrails": [
    {
      "stage": "PRE_ROUTE",
      "action": "allow",
      "profile": "gp_baseline",
      "evaluations": 2
    },
    {
      "stage": "PRE_MODEL",
      "action": "allow",
      "profile": "gp_baseline",
      "evaluations": 2
    },
    {
      "stage": "POST_MODEL",
      "action": "allow",
      "profile": "gp_baseline",
      "evaluations": 1
    },
    {
      "stage": "PRE_RETURN",
      "action": "allow",
      "profile": "gp_baseline",
      "evaluations": 1
    }
  ],
  "attempts": [
    {
      "provider": "anthropic",
      "status": 200
    }
  ],
  "routing_reason": [
    "selected anthropic/claude-sonnet via anthropic (balanced objective, score 0.8638)",
    "committed capacity preferred (contract economics)"
  ]
}