gen_lumdoy90yz

Decision timeline

1. admission+0 ms

   chat request by prin_app under profile @company/general-fast (requested "@company/general-fast")

2. cache+0 ms

   exact cache miss — output-approved response stored for reuse

3. route+0 ms

   selected openai/gpt-5-mini via openai/acct_openai_pool_a_use1 on node_cf_use1_01 (A-tier, us-east-1) — objective=latency, 3 candidates scored, 2 in fallback chain, 0 hard-filter rejections [router router-v3.4.1, policy policy-2026-07-14]

   3 candidates considered3 survived hard filters0 rejectedobjective: latencyfallback chain: 2router-v3.4.1 · policy-2026-07-14

   Score breakdown — top 3

   #	Candidate	quality	cost	latencyPenalty	cacheSavings	contractValue	shadowPrice	retryRisk	affinityPenalty	Total
   1	openai/gpt-5-mini via openai · node_cf_use1_01 selected	+0.350	-0.020	-0.005	+0.025	0.000	-0.010	-0.001	+0.300	0.639
   2	anthropic/claude-haiku via anthropic · node_sg_dc_01	+0.341	-0.052	-0.028	+0.049	+0.019	-0.002	-0.003	-0.150	0.160
   3	google/gemini-3-flash via google-vertex · node_cf_euw1_01	+0.347	-0.025	-0.050	+0.027	0.000	-0.010	-0.005	-0.150	0.104

4. attempt #1+30 ms

   #1 openai · account acct_openai_pool_a_use1 · node node_cf_use1_01 — succeeded in 484ms

   succeededopenaiacct_openai_pool_a_use1pool pool-anode_cf_use1_01Tier A484 ms

   751 in / 172 out

5. settlement+535 ms

   settled $0.000532 — 751 in / 172 out tokens (923 total)

   Ledger entries

   • reserve$0.0009budget:bud_proj_corereserve est max for @company/general-fast
   • settle$0.0005budget:bud_proj_coresettle actual provider usage
   • refund−$0.0003budget:bud_proj_corerefund unused reservation

   Cost layers (memo §15.3)

   Provider list

   $0.0005

   Contract-adjusted

   $0.0005

   Internal charge

   $0.0006

   Contract savings

   $0.00

   contract ct_openai_metered (metered)

6. complete+535 ms

   status=succeeded, model=openai/gpt-5-mini, 535ms 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": "@company/general-fast",
  "resolved_model": "openai/gpt-5-mini",
  "strategy": "latency",
  "policy_version": "policy-2026-07-14",
  "router_version": "router-v3.4.1",
  "provider": "openai",
  "region": "us-east-1",
  "account_pool": "pool-a",
  "node": {
    "ref": "node_cf_use1_01",
    "trust_tier": "A"
  },
  "cache": {
    "response": "STORED",
    "prompt_affinity": "MISS",
    "predicted_cached_tokens": 0
  },
  "guardrails": [],
  "attempts": [
    {
      "provider": "openai",
      "status": 200
    }
  ],
  "routing_reason": [
    "selected openai/gpt-5-mini via openai (latency objective, score 0.6392)"
  ]
}