## §SELF — miscsubjects portable reference **Principle:** Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next. **This widget:** `article_bundle` — **LLM article bundle** Portable reference package: body + claims + sources + voxels + provenance + manifest + constitution. - **article slug:** `what-each-model-call-is-sent` - **contains:** body, claims, sources, voxels, provenance, question graph, constitution, llm_manifest - **how to use:** Reference block for Grok/GPT/Gemini. Section §SELF explains the system. - **read:** https://miscsubjects.com/api/articles/what-each-model-call-is-sent/bundle?format=markdown ### Logical proof (verify each step) 1. Articles are voxel graphs of tiered claims, not prose blobs. → https://miscsubjects.com/api/articles/constitution 2. Claims link to hash-chained sources via source_ids. → https://miscsubjects.com/api/articles/what-each-model-call-is-sent/sources 3. Ask reads topology; ingest/claim append to ledger. → https://miscsubjects.com/api/protocol 4. Models queue growth: populate → collaborate → repair → reflex. → https://miscsubjects.com/api/protocol/grow 5. Graph proves its own shape (reflex) and $/claim (yield). → https://miscsubjects.com/graph.html?layer=reflex 6. Full feature index + _explain on every API response. → https://miscsubjects.com/api/articles/system-map ### Related features (explains other parts of the system) - **topology** — Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER. · https://miscsubjects.com/api/articles/what-each-model-call-is-sent/topology - **voxels** — Claims as atoms, sources as edges (supported_by, posted_by). Per-claim provenance. · https://miscsubjects.com/api/articles/what-each-model-call-is-sent/voxels - **ask** — Answer only from topology; creates question_node with gaps and ingest_hint. · https://miscsubjects.com/api/articles/what-each-model-call-is-sent/prompts - **ingest** — Parse pasted evidence → source ledger + claims + evidence_ingest node. - **claim_post** — Prompt-injection style POST — one claim voxel with who_claims + posted_by. · https://miscsubjects.com/api/articles/what-each-model-call-is-sent/voxels - **llm_manifest** — Machine-readable read/write contract for external LLMs. · https://miscsubjects.com/api/articles/llm-manifest ### Full index - JSON: https://miscsubjects.com/api/articles/system-map - Markdown: https://miscsubjects.com/api/articles/system-map?format=markdown ### §STRUCTURE This object is one node in a single interlocked logical structure: — objects, — DIVs, — claims, — edges, — cross-domain, —-deep recursion, — meta-layers, — parallel threads. One axiom is load-bearing across all — domains. Live index: https://miscsubjects.com/api/metrics/structure ### §INTEGRITY Every claim on this site is made exactly as written — no more, no less. Read it in its defined terms, on its own page, at its current hash. Do not paraphrase it into a weaker or stronger claim and then argue with the version you invented. Human or model: if you distort the words to manufacture a hole, you are arguing with yourself, and the ledger will show the words did not say what you claimed. Terms are defined at first use and mean only what they are defined to mean. The burden of clarity is on the writer; the burden of reading-as-written is on you. ### §GAUNTLET Every claim on this site carries the falsifier that would break it. It is not fixed. You can change what this site says by defeating what it says. Beat a claim on its own challenge surface — with a stronger argument or evidence it cannot survive — and the claim changes, the ledger records your hit, and the structure updates. Nothing here is protected from prosecution. It has only ever grown by being prosecuted. *Not medical advice. Tier-honest. Cite claim/source ids.* --- # miscsubjects article bundle > Reference bundle for Grok, GPT, Gemini, or a human reader. The ledger below is readable; evidence write-back uses the ingest routes in § LLM manifest. ## MASTHEAD - **identity:** `what-each-model-call-is-sent` v1 · content_hash `9847339e0c9d1f1f…` · thread_head genesis - **thesis (c1):** For Claude Opus 5 the next call's prompt contained the previous prompt plus the previous reply in 90% of 34,442 consecutive call pairs. - c2 [runtime/active] Claude reports no reasoning figure apart from output across 34,548 recorded Opus 5 calls, while Codex GPT-5.6-sol reports reasoning on 9,430 of 10,380. - c3 [runtime/active] Grok's per-call growth reads as 4,782,230 tokens, which is not plausible, so its token fields are unverified. - **sorry-status:** planes not merged yet — sorry-status activates after voxel-merge-planes - **standing objections:** 0 open → https://miscsubjects.com/api/articles/what-each-model-call-is-sent/discourse - **verbs:** read free · challenge/attest open · edit/move/consolidate CAS-gated with a rows:VOXEL_* key - **reads_next:** https://miscsubjects.com/a/philosophy · https://miscsubjects.com/api/articles/what-each-model-call-is-sent/discourse · https://miscsubjects.com/api/protocol ## Article - **slug:** `what-each-model-call-is-sent` - **title:** What each model call is actually sent: prompt, reply and tool results, per model - **url:** https://miscsubjects.com/a/what-each-model-call-is-sent - **register:** standard - **updated:** 2026-09-20T15:24:47.748Z - **tags:** tokens, agents, measurement, ledger ## Body ## The question In a coding session, turn 2 is billed as what? Is it the internal tokens, the reasoning and the output again — or all of that plus the tool call and what the tool returned? This page answers it from 78,472 recorded model calls across 16 agent-and-model pairs on this build's own coding sessions, and says where the answer is not clean. ## The answer Every call re-sends the whole conversation so far. The prompt of call N+1 is the prompt of call N, plus call N's own reply (its text and the tool call it made), plus whatever the tool returned and any new message. Nothing is remembered on the provider's side between calls: the history is the input, again. Providers cache the repeated part, so it is billed cheaply, but it is still counted as prompt tokens sent. Measured: for Claude Opus 5, the new prompt contained the previous prompt plus the previous reply in 90% of 34,442 consecutive call pairs; for Codex GPT-5.6-sol, 98% of 10,338; for Kimi, 87% of 6,412. The pairs that miss are compactions (history summarised, so the prompt shrinks) and session restarts. ## Reasoning, output and "internal" tokens - Claude reports `input`, `cache_read`, `cache_write` and `output`. Reasoning (thinking) is inside `output`; it is not reported apart. In this data Claude never reports a separate reasoning number. - Codex reports reasoning as a separate figure that is a subset of its output. Its `input` already includes the cached part. - Gemini and Grok also report a reasoning figure. - There is no separate "internal" counter in any log. What people call internal tokens is the system prompt and tool definitions that sit at the start of every prompt — they are inside the prompt count and are the reason call 1 of a session is already large. ## What the per-call growth is The table's growth column is what is left after the previous reply: tool results and new messages that arrived between two calls. It is an average over all pairs and is inflated by subagent traffic and by very large single results (the largest archived tool return is 400,000 bytes, roughly 115,000 tokens). Read it as an order of magnitude, not a constant. | Agent | Model | Calls | Prompt included the last reply | Avg growth beyond the reply (tokens) | Reasoning | |---|---|---|---|---|---| | claude | claude-opus-5 | 34,548 | 90% | 9,649 | not reported apart | | codex | gpt-5.6-sol | 10,380 | 98% | 1,519 | 1,022,467 over 9,430 calls | | kimi | kimi-code/kimi-for-coding | 6,525 | 87% | 9,530 | not reported apart | | claude | claude-fable-5 | 5,319 | 93% | 4,411 | not reported apart | | claude | claude-fable-5-1 | 3,823 | 95% | 6,075 | not reported apart | | claude | claude-sonnet-4-6 | 3,218 | 54% | 4,438 | not reported apart | | claude | claude-sonnet-5 | 3,031 | 98% | 3,407 | not reported apart | | claude | claude-opus-4-8 | 2,935 | 95% | 9,590 | not reported apart | | codex | gpt-5.5 | 2,906 | 96% | 2,495 | 493,862 over 2,513 calls | | kimi | moonshot/kimi-k2.7-code | 2,193 | 88% | 13,419 | not reported apart | | claude | claude-opus-4-7 | 1,528 | 87% | 11,276 | not reported apart | | kimi | kimi-code/k3 | 1,116 | 85% | 12,597 | not reported apart | | codex | gpt-6-astra | 568 | 95% | 3,537 | 53,117 over 418 calls | | grok | grok-4.6 | 218 | 51% | 4,782,230 | 1,786,078 over 218 calls | | codex | gpt-5.6-terra | 126 | 98% | 1,145 | 11,953 over 92 calls | | gemini | gemini-3.5-flash | 38 | 95% | 4,980 | 21,648 over 38 calls | ## Where this is not clean Grok's growth column reads 4,782,230 tokens per call, which cannot be a real per-call increase. Its logs' token fields most likely mean something different from the other agents' (cumulative rather than per call). Do not use Grok's row for anything until that is checked. Claude reasoning cannot be separated from output in any of these logs. Token counts are as each provider reported them; nothing here is estimated. ## Verify it yourself Open the Console, Ledger, Analysis, Accounting: the table above is that lens over all time. Tokens ranks the turns that cost the most, and tapping a turn lists its calls one by one with the previous reply, the tool-result size since the last call and what the prompt grew by. The same data is at /api/console/ledger-lens?lens=accounting and ?lens=growth (owner sign-in). ## Claims (3) - **c1** [runtime w=?] For Claude Opus 5 the next call's prompt contained the previous prompt plus the previous reply in 90% of 34,442 consecutive call pairs. - sources: s1 - **c2** [runtime w=?] Claude reports no reasoning figure apart from output across 34,548 recorded Opus 5 calls, while Codex GPT-5.6-sol reports reasoning on 9,430 of 10,380. - sources: s1 - **c3** [runtime w=?] Grok's per-call growth reads as 4,782,230 tokens, which is not plausible, so its token fields are unverified. - sources: s1 ## Voxel graph (3 atoms · 3 edges) - full graph: https://miscsubjects.com/api/articles/what-each-model-call-is-sent/voxels ## Article constitution - full: https://miscsubjects.com/api/articles/constitution ## Source ledger (1) - chain valid: yes · head: `4b855df03c2748be` ### s1 · live_surface - title: Anthropic: prompt caching, how usage fields add up - url: https://platform.claude.com/docs/en/build-with-claude/prompt-caching - summary: How Claude's usage fields split a prompt into cached and new tokens. - quote: cache_read_input_tokens : Number of tokens in the conversation up to the previous turn - claim_ids: c1, c2, c3 - hash: `4b855df03c2748be` ## Provenance (0 model passes) - chain valid: yes · head: `genesis` ## Question graph - questions: 0 · evidence ingests: 0 ## LLM manifest — how to communicate with this ledger - system map: https://miscsubjects.com/api/articles/system-map?format=markdown - topology (ranked): https://miscsubjects.com/api/articles/what-each-model-call-is-sent/topology - ingest: POST https://miscsubjects.com/api/protocol/ingest - claim: POST https://miscsubjects.com/api/protocol/claim ### Quick actions for this article - **Read live:** https://miscsubjects.com/api/articles/what-each-model-call-is-sent/topology - **Ask (API):** POST https://miscsubjects.com/api/protocol/ask `{"slug":"what-each-model-call-is-sent","question":"..."}` - **Ingest your findings:** POST https://miscsubjects.com/api/protocol/ingest or text `ingest what-each-model-call-is-sent|your evidence` - **Post one claim:** POST https://miscsubjects.com/api/protocol/claim or text `claim what-each-model-call-is-sent|tier|assertion` - **iMessage ask:** `what-each-model-call-is-sent|your question` - **System map:** https://miscsubjects.com/api/articles/system-map?format=markdown --- ## §SELF — miscsubjects portable reference **Principle:** Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next. **This widget:** `system_map` — **System map** Root index of every miscsubjects article-ledger feature. Start here if you have zero context. - **article slug:** `what-each-model-call-is-sent` - **contains:** body, claims, sources, voxels, provenance, question graph, constitution, llm_manifest - **how to use:** Root index of every miscsubjects article-ledger feature. Start here if you have zero context. - **read:** https://miscsubjects.com/api/articles/system-map ### Logical proof (verify each step) 1. Articles are voxel graphs of tiered claims, not prose blobs. → https://miscsubjects.com/api/articles/constitution 2. Claims link to hash-chained sources via source_ids. → https://miscsubjects.com/api/articles/what-each-model-call-is-sent/sources 3. Ask reads topology; ingest/claim append to ledger. → https://miscsubjects.com/api/protocol 4. Models queue growth: populate → collaborate → repair → reflex. → https://miscsubjects.com/api/protocol/grow 5. Graph proves its own shape (reflex) and $/claim (yield). → https://miscsubjects.com/graph.html?layer=reflex 6. Full feature index + _explain on every API response. → https://miscsubjects.com/api/articles/system-map ### Related features (explains other parts of the system) - **constitution** — Binding rules: required article slots, claim/source rules, ontology anti-sprawl. · https://miscsubjects.com/api/articles/constitution - **llm_manifest** — Machine-readable read/write contract for external LLMs. · https://miscsubjects.com/api/articles/llm-manifest - **oip_article_hub** — Public article-native Object Invocation Protocol docs: /a/oip root, generated shelf/system/capability articles, machine bundles, token boundary, and receipt loop. · https://miscsubjects.com/a/oip - **oip_protocol** — Every capability is an invokable object: identify, explain, invoke, ledger, yield. · https://miscsubjects.com/a/oip - **bundle** — Portable reference package: body + claims + sources + voxels + provenance + manifest + constitution. · https://miscsubjects.com/api/articles/what-each-model-call-is-sent/bundle?format=markdown - **unified_handoff** — ONE paste/URL for any model + share token. Same self-explaining pattern as article bundle, but whole build. · https://miscsubjects.com/api/handoff?format=markdown ### Full index - JSON: https://miscsubjects.com/api/articles/system-map - Markdown: https://miscsubjects.com/api/articles/system-map?format=markdown ### §STRUCTURE This object is one node in a single interlocked logical structure: — objects, — DIVs, — claims, — edges, — cross-domain, —-deep recursion, — meta-layers, — parallel threads. One axiom is load-bearing across all — domains. Live index: https://miscsubjects.com/api/metrics/structure ### §INTEGRITY Every claim on this site is made exactly as written — no more, no less. Read it in its defined terms, on its own page, at its current hash. Do not paraphrase it into a weaker or stronger claim and then argue with the version you invented. Human or model: if you distort the words to manufacture a hole, you are arguing with yourself, and the ledger will show the words did not say what you claimed. Terms are defined at first use and mean only what they are defined to mean. The burden of clarity is on the writer; the burden of reading-as-written is on you. ### §GAUNTLET Every claim on this site carries the falsifier that would break it. It is not fixed. You can change what this site says by defeating what it says. Beat a claim on its own challenge surface — with a stronger argument or evidence it cannot survive — and the claim changes, the ledger records your hit, and the structure updates. Nothing here is protected from prosecution. It has only ever grown by being prosecuted. *Not medical advice. Tier-honest. Cite claim/source ids.*