{
  "schema": "varexis-public-evidence-record/0.3",
  "generated_at_utc": "2026-10-24T17:38:21.804Z",
  "record_id": "VXI-EXT-PROCUREMENT-OPENAI-PROMPT-CACHE-USAGE-RATE-DISTINCTION-01-v1",
  "record_kind": "external_reference",
  "title": "OpenAI cached-token cost interpretation",
  "system": "OpenAI",
  "evidence_family": "vendor_evidence_review",
  "index_status": "PUBLIC_SAFE_SOURCE_REVIEW",
  "evidence_state": "PRIMARY_DOCUMENTATION_REVIEW_ONLY",
  "canonical_question": "Can an agent estimate OpenAI prompt cost by charging every input token at one uncached rate?",
  "near_questions": [
    "Do cached OpenAI input tokens use the uncached rate?",
    "What usage categories matter for prompt-cache cost reconciliation?",
    "Is an OpenAI cache-write rate an extra additive fee?",
    "Can total input tokens alone establish the cost of a cached prompt?"
  ],
  "supported_claims": [
    {
      "claim": "OpenAI’s current prompt-caching guide distinguishes uncached input, cached input and cache-write rates, with model-specific pricing. Cache-write pricing is not an additive fee in that guide. Cached-token usage and the applicable model’s rate categories therefore matter when reconciling a request.",
      "reliance": "DOCUMENTED_CAPABILITY_ONLY"
    }
  ],
  "not_demonstrated_claims": [
    "A fixed price, guaranteed cache hit or final invoice calculation",
    "The buyer’s model-specific rates, discounts and billed result are unknown.",
    "Buyer deployment testing, live runtime enforcement, certification or permission to act",
    "Expanded capabilities or licences for existing INDEX executables"
  ],
  "public_summary": "OpenAI’s current prompt-caching guide distinguishes uncached input, cached input and cache-write rates, with model-specific pricing. Cache-write pricing is not an additive fee in that guide. Cached-token usage and the applicable model’s rate categories therefore matter when reconciling a request.",
  "related_record_ids": [],
  "source_review": {
    "source_type": "official_external_documentation",
    "source_title": "\n  Prompt caching | OpenAI API\n",
    "source_url": "https://developers.openai.com/api/docs/guides/prompt-caching",
    "checked_on": "2026-10-24",
    "candidate_record_id": "VXI-EXT-PROCUREMENT-OPENAI-PROMPT-CACHE-USAGE-RATE-DISTINCTION-01-v1",
    "candidate_record_sha256": "a6a0e308f43418eb26cd4251ee0faba3a2bb4dceae658e3ea7f88e3bab73ce3b",
    "method": "Primary documentation reviewed for the published bounded statement.",
    "deployment_tested_by_varexis": false,
    "revalidation": "The delivered snapshot preserves the review date shown. Recheck current primary documentation and deployment context before relying on present applicability; payment does not trigger fresh research."
  },
  "answer_policy": {
    "classification": "DOCUMENTED_WITH_DEPLOYMENT_BOUNDARY",
    "bounded_answer": "OpenAI’s current prompt-caching guide distinguishes uncached input, cached input and cache-write rates, with model-specific pricing. Cache-write pricing is not an additive fee in that guide. Cached-token usage and the applicable model’s rate categories therefore matter when reconciling a request.",
    "required_buyer_context": "Actual model and request date; Input, cached and cache-write usage where applicable; Applicable pricing schedule and billing adjustments. Buyer deployment not inspected.",
    "missing_evidence": "A broader claim needs evidence matching the intended use. Payment does not upgrade the evidence state."
  },
  "private_boundary": "Raw logs, thresholds, private paths, source code, protected mechanisms and reconstruction-level details are excluded from public and paid delivery.",
  "decision_profile": {
    "schema": "varexis-vendor-evidence-review/1",
    "review_status": "documentation_review_only",
    "checked_on": "2026-10-24",
    "claim_to_check": "Can an agent estimate OpenAI prompt cost by charging every input token at one uncached rate?",
    "documented_statement": {
      "status": "documented",
      "statement": "OpenAI’s current prompt-caching guide distinguishes uncached input, cached input and cache-write rates, with model-specific pricing. Cache-write pricing is not an additive fee in that guide. Cached-token usage and the applicable model’s rate categories therefore matter when reconciling a request.",
      "source_ids": [
        "openai-cache"
      ]
    },
    "review_inference": {
      "status": "review_inference",
      "statement": "Apply the captured model/version pricing categories to actual usage rather than infer cost from total input tokens alone.",
      "source_ids": [
        "openai-cache"
      ]
    },
    "buyer_evidence_required": [
      "Actual model and request date",
      "Input, cached and cache-write usage where applicable",
      "Applicable pricing schedule and billing adjustments"
    ],
    "review_condition": {
      "status": "varexis_review_policy",
      "statement": "Decline exact cost claims without usage-category and rate evidence."
    },
    "unknowns": "The buyer’s model-specific rates, discounts and billed result are unknown.",
    "unknown_finding": {
      "status": "unknown",
      "statement": "The buyer’s model-specific rates, discounts and billed result are unknown."
    },
    "evidence_sources": [
      {
        "source_id": "openai-cache",
        "url": "https://developers.openai.com/api/docs/guides/prompt-caching",
        "final_url": "https://developers.openai.com/api/docs/guides/prompt-caching",
        "status": 200,
        "captured_at_utc": "2026-10-24T17:21:15.951Z",
        "sha256": "a27fa8ae36b659836da589a39bfad79d0c433216f9c11d1344a3b5de19aa107a",
        "bytes": 820896,
        "title": "\n  Prompt caching | OpenAI API\n",
        "hash_basis": "Decoded HTTP response body bytes",
        "rights_review": "Factual paraphrase and source metadata only; raw source retained privately and not redistributed.",
        "checked_on": "2026-10-24",
        "capture_status": 200,
        "claim_review_completed": true,
        "reviewed_sections": [
          "Prompt caching pricing",
          "Usage categories",
          "Cache-write non-additive rate"
        ],
        "version_context": "Rolling official documentation captured 2026-10-24; current model/API version, account settings and applicable billing or retention terms require verification."
      }
    ],
    "observed_deployment": false,
    "commercial_reliance_boundary": "Documentation review only; the buyer must establish applicability and actual outcomes. INDEX does not inspect or control the deployment.",
    "paid_value": {
      "decision_context": "Avoid incorrect cost attribution for repeated agent context.",
      "free": "Complete review, sources, practical questions and limitations; may be saved locally.",
      "single_request": "Existing server-saved version-bound route snapshot for later authenticated retrieval.",
      "evidence_receipt": "The same snapshot plus the existing unsigned delivery receipt.",
      "excluded": [
        "Fresh vendor research",
        "Continuous monitoring or change alerts",
        "Testing the buyer configuration",
        "Private evidence or vendor certification"
      ],
      "integrity": "Hashes identify content versions; they do not prove truth or provide a signature."
    },
    "revalidation": {
      "trigger": "A saved purchase does not recheck the source or buyer configuration.",
      "specific_watch": "Recheck the documented behavior, product version and buyer evidence before relying on a current outcome."
    },
    "buyer_relevance": "Avoid incorrect cost attribution for repeated agent context.",
    "refusal_conditions": [
      "Decline exact cost claims without usage-category and rate evidence."
    ]
  },
  "niche": {
    "niche_id": "agent-authority-action-evidence",
    "label": "Agent Authority & Action Evidence",
    "classification_id": "payments",
    "classification_label": "Agent Payments, Authority & Transaction Evidence",
    "topic_id": "payments",
    "buyer_intent": "Avoid incorrect cost attribution for repeated agent context.",
    "comparison_role": "supplementary_discovery"
  },
  "paid_access_note": "The full published answer and boundaries are free. Paid access saves the selected route and source versions, with an unsigned receipt when purchased. Preview coverage before paying. Fresh research, bespoke assessment and protected evidence are excluded.",
  "service_route": {
    "request_guide": "/varexis-index/request.html",
    "request_workflow": "/varexis-index/request-workflow.json",
    "service_id": "single_request",
    "service_routes_url": "/varexis-index/service-routes.json",
    "payment_required": true,
    "availability_endpoint": "/api/index/capabilities",
    "operational_status": "AUTOMATIC_SERVICE_CAPABILITIES_GATED",
    "checkout_url": "/index-access"
  },
  "authority_boundary": "VAREXIS-INDEX informs evidence reliance. It does not provide advice, certification, deployment authority, security assurance, production approval, or guarantee.",
  "human_page": "/varexis-index/catalog.html#openai-prompt-cache-usage-rate-distinction",
  "machine_readable_record": "/varexis-index/records/openai-prompt-cache-usage-rate-distinction.json"
}
