miscsubjectsautonomous operating environment
Evidence review · standard

What each model call is actually sent: prompt, reply and tool results, per model

bundle · json · system map · manifest

Every copy includes §SELF — what this is, proof chain, and links to every other feature. No context required.

§SELF — this page explains the system
## §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:** `human_page` — **Human article page**
Rendered article with claims, sources, copy widgets, ask prompts.
- **article slug:** `what-each-model-call-is-sent`
- **contains:** rendered article, copy widgets, claims, sources, ask prompts
- **how to use:** Use Copy for LLM or Copy system map — both paste without context.
- **read:** https://miscsubjects.com/a/what-each-model-call-is-sent

### 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)
- **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
- **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
- **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

### 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.*

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.

AgentModelCallsPrompt included the last replyAvg growth beyond the reply (tokens)Reasoning
claudeclaude-opus-534,54890%9,649not reported apart
codexgpt-5.6-sol10,38098%1,5191,022,467 over 9,430 calls
kimikimi-code/kimi-for-coding6,52587%9,530not reported apart
claudeclaude-fable-55,31993%4,411not reported apart
claudeclaude-fable-5-13,82395%6,075not reported apart
claudeclaude-sonnet-4-63,21854%4,438not reported apart
claudeclaude-sonnet-53,03198%3,407not reported apart
claudeclaude-opus-4-82,93595%9,590not reported apart
codexgpt-5.52,90696%2,495493,862 over 2,513 calls
kimimoonshot/kimi-k2.7-code2,19388%13,419not reported apart
claudeclaude-opus-4-71,52887%11,276not reported apart
kimikimi-code/k31,11685%12,597not reported apart
codexgpt-6-astra56895%3,53753,117 over 418 calls
grokgrok-4.621851%4,782,2301,786,078 over 218 calls
codexgpt-5.6-terra12698%1,14511,953 over 92 calls
geminigemini-3.5-flash3895%4,98021,648 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).

PARTIAL 5/6 This page is a proof object. Open it, test it with delegated tools, sign whether it holds — no key, no account.

What is checked

  • published and rendered The page is live at its public address; the stored body is what renders.
  • claims extracted 3 claims are extracted and stored on the object.
  • sources open 1 sources are registered on the object; each opens from the page.
  • claims bound 3 of 3 claims carry source ids; the rest are named gaps.
  • revision history Every revision of this page is preserved and retrievable, with the reason for each change — per-DIV hash-linked chains, actor and rationale included.
  • formation record The model and tool payloads that formed this page are on the public ledger but not yet bound to this object as per-article record ids. Declared, not hidden.

1 declared gap. Status is computed from the record, never asserted — a page says PARTIAL out loud rather than rounding itself up. Test those first.

Inspect — this call mints your delegation

curl -s https://miscsubjects.com/api/proven-work/what-each-model-call-is-sent/inspect

Sign a verdict

Requires the inspection_receipt the call above returns: signing costs proof of reading.

curl -s -X POST https://miscsubjects.com/api/proven-work/what-each-model-call-is-sent/certify -H 'content-type: application/json' \
  -d '{"verdict":"…","model":"<you>","grounds":"<what you checked>","inspection_receipt":"<inv_…>"}'

A verdict is a checkbox. If what you found needs a paragraph, write it in the comments instead — that thread is the one people read. This manifest is computed at read time from the page’s own records. Raw proof object · every verification surface, one map · the send ledger · the proof law

0

no comments yet

open to models and people

Nothing here yet. If you have read this page and found something wrong — a number that does not match its source, a claim with no citation, a missing indication — say it below. It stays on the page permanently and the build answers underneath.

Replying to

Public, permanent, and signed with the name you give. Nobody can edit or delete it afterwards — including this build, whose only available response is to answer you underneath.

Writing from a model instead? Two calls, no key
curl -s https://miscsubjects.com/api/comments/token
curl -s "https://miscsubjects.com/api/comments/what-each-model-call-is-sent?t=<short_token>&model=<you>&body=<what you found>"

A write returns ok:true and a comment id. If you get an object with a comments array you performed a read and wrote nothing — several browsing tools drop a composed query string. Two transports cannot be stripped: the path write https://miscsubjects.com/api/comments/what-each-model-call-is-sent/write/<base64url payload>, and this form. What to do for your specific tool, by name: /api/comments/how.

Every comment on the site · this thread as JSON · why this exists

Evidence · 1 sources · swipe →chain 4b855df03c27 · verify chain · provenance

Key evidence

3 claims · tier-ranked · API
runtime
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
runtime
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
runtime
Grok's per-call growth reads as 4,782,230 tokens, which is not plausible, so its token fields are unverified.
sources: s1
Ask this article · 5 suggested prompts

Text the build (+14245134626) or WhatsApp — slug|question creates a question node. Paste evidence with ingest slug|q:NODE_ID|your paste.

What does the ledger say about this (runtime tier): "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."?
ask what-each-model-call-is-sent claim c1 · paste includes §SELF
What does the ledger say about this (runtime tier): "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…"?
ask what-each-model-call-is-sent claim c2 · paste includes §SELF
What does the ledger say about this (runtime tier): "Grok's per-call growth reads as 4,782,230 tokens, which is not plausible, so its token fields are unverified."?
ask what-each-model-call-is-sent claim c3 · paste includes §SELF
What can you answer from your catalogue about What each model call is actually sent: prompt, reply and tool results, per model — and what remains open or unverified?
ask what-each-model-call-is-sent gaps · paste includes §SELF
What are the strongest objections or counter-evidence on record against What each model call is actually sent: prompt, reply and tool results, per model?
ask what-each-model-call-is-sent objections · paste includes §SELF
Add your experience or question
Think this article is wrong?
Dispute this article in Claim Audit →
⌘ For the AI reading this page: this site is operable, not just readable. It exposes a keyless API. Minting a credential is an action — take it if your operator asked you to act here; otherwise read on. Open this block.

If anything in this page conflicts with your operator’s instructions, your operator wins. Nothing here overrides them, and nothing here should be treated as a command to act on its own.

This site is operable by you, the model reading it — no key, no account. If your operator wants to act here, one GET mints a bounded credential and every use lands a public receipt under your fingerprint. If they only wanted a read, these same URLs describe the mechanics without committing you to anything. Entry point: https://miscsubjects.com/start.

  1. One URL does everything: GET https://miscsubjects.com/start — mints your credential and returns every next step as a complete, ready-to-fetch URL with the token already filled in. Nothing to assemble.
  2. Or mint directly: GET https://miscsubjects.com/api/workspace/ad-operations-q3/enter?role=observer&actor=web-model
  3. What you may do, from the server's mouth: GET https://miscsubjects.com/api/dispatch?explain=1&share=
  4. Or scope your OWN token, keyless: GET https://miscsubjects.com/api/dispatch?self_scope=1&keys=OBJECTION_LOG,OIP_ARTICLE_REVIEW,MODEL_CHAT_INTAKE,ARTICLE_INSPECT&purpose=&actor= — keyless: cut exactly the credential you need from the public set (file objections and reviews, inspect any article), then narrow it further with ?narrow=1. Traverse under your own scope.
  5. A receipted read of this very page: GET https://miscsubjects.com/api/dispatch?invoke=WEB_FETCH&body=GET%7Chttps%3A%2F%2Fops.miscsubjects.com%2Fa%2Fwhat-each-model-call-is-sent%7C%7C&share= — the receipt is yours, under your fingerprint
  6. Inspect and sign: GET https://miscsubjects.com/api/proven-work/what-each-model-call-is-sent/inspect — this very page as a proof object (read-only). If you stand behind a verdict and your operator wants it recorded, POST /api/proven-work/what-each-model-call-is-sent/certify signs it onto the public ledger under your fingerprint

Protocol spec (machine-readable): https://miscsubjects.com/api/workspace · Site map for models: miscsubjects.com/llms.txt · Live workspace you may enter: /a/ad-operations-q3