Claude Architect · Урок

Токены, окна контекста и стоимость

Почему вся история отправляется при каждом ходе и во что это обходится

Урок 4 из 413 шагов

«Токены, окна контекста и стоимость» — бесплатный урок Claude Architect на CoddyKit. Это урок 4 из 4. Ты можешь прочитать весь урок бесплатно ниже — а потом практиковать его прямо в браузере с встроенным редактором кода и ИИ-репетитором 24/7. Это часть пути обучения Claude Architect, и твой прогресс синхронизируется между веб-версией и приложением CoddyKit. Курс Claude Architect содержит 4 уроков всего.

Части этого урока еще не переведены и отображаются на английском.

Claude Has No Memory

Here is the most important idea in this lesson: the Claude API keeps NO state between turns.

The model does not remember your last message. Each API call starts fresh. So how do chatbots seem to remember?

You send the full conversation history in every single request. The messages field carries the whole back-and-forth, every time.

What a Request Carries

A Claude API request has a few key fields:

model — which Claude model to use
max_tokens — the cap on the reply length
system — the system prompt
messages — the FULL history every turn
tools / tool_choice — optional tool config

Notice messages grows over time. Turn 1 sends 1 message. Turn 10 sends all 19 prior messages plus the new one.

resp = client.messages.create(
    model="claude-sonnet-4-5",
    max_tokens=1024,
    system="You are a support agent.",
    messages=[
        {"role": "user", "content": "My order is late."},
        {"role": "assistant", "content": "I can help. What is your order ID?"},
        {"role": "user", "content": "It's #4821."},
    ],
)

What Is a Token?

Models do not read characters or whole words. They read tokens — small chunks of text.

A rough guide: one token is about 4 characters of English, or roughly 3/4 of a word. "unhappiness" might split into "un", "happiness". Punctuation and spaces count too.

Tokens matter because you pay per token and the context window is measured in tokens, not words.

Input vs Output Tokens

Every request has two token counts that are billed differently:

Input tokens — everything you send: system + tools + the full messages history.
Output tokens — what the model generates in its reply.

Output tokens usually cost more per token than input tokens. But because the full history is resent each turn, input tokens are what quietly balloon in long conversations.

The Context Window

The context window is the maximum number of tokens a model can handle in one request — input plus output combined.

If your full history plus the requested max_tokens exceeds the window, the request fails. The window is a hard ceiling, not a suggestion.

This is why long-running chats and big tool outputs eventually hit a wall: the resent history keeps growing toward the limit.

Cost Grows With History

Because you resend the whole history each turn, cost does not grow linearly with the conversation — it grows roughly with the square of its length.

Turn 1 bills a few tokens. Turn 20 bills all 19 prior turns again, plus the new one. A 10-message chat re-bills the early messages 10 times over its life.

For an architect, this means: a chatty agent that never trims its history is an expensive agent.

# Rough illustration of resent input growing each turn
history = []
for turn in range(1, 6):
    history.append({"role": "user", "content": user_msg(turn)})
    resp = client.messages.create(
        model="claude-sonnet-4-5",
        max_tokens=512,
        messages=history,  # ENTIRE history resent every turn
    )
    history.append({"role": "assistant", "content": resp.content})
    print("turn", turn, "input_tokens", resp.usage.input_tokens)

Measure Before You Optimize

Every response includes a usage object reporting input_tokens and output_tokens. This is your ground truth for cost.

You can also count tokens before sending, so you can predict cost and check you are under the window — without paying for a full generation.

Rule of thumb: instrument token usage in production. Aggregate cost numbers hide which conversations or tool calls are the expensive ones.

count = client.messages.count_tokens(
    model="claude-sonnet-4-5",
    system="You are a support agent.",
    messages=history,
)
print("input tokens before send:", count.input_tokens)

resp = client.messages.create(model="claude-sonnet-4-5", max_tokens=512, messages=history)
print("billed:", resp.usage.input_tokens, resp.usage.output_tokens)

Tool Output Bloats Context

In agentic loops, tool results are appended to the history and resent on every following turn. A verbose tool that returns a 5,000-token JSON blob keeps costing you for the rest of the conversation.

The fix is to trim verbose tool output to the relevant fields before appending it. Do not store a whole API dump in context when three fields are all the model needs.

raw = lookup_order(order_id)  # huge JSON
# Trim to what the model actually needs
tool_result = {
    "order_id": raw["id"],
    "status": raw["status"],
    "eta": raw["estimated_delivery"],
}
history.append({
    "role": "user",
    "content": [{"type": "tool_result", "tool_use_id": tu_id,
                 "content": json.dumps(tool_result)}],
})

Summarize to Stay in Budget

For long conversations, you can replace old turns with a compact progressive summary to keep the history small and under the window.

But beware: summarization makes numbers, percentages, and dates vague. The model rewrites "refund of $482.10 on 2026-03-14" into "a refund last spring."

The architect's fix: pull transactional facts into a separate verbatim "case facts" block kept outside the summary, so exact values never get blurred.

Lost in the Middle

A bigger context window is not a free pass. Models attend most strongly to the start and the end of the input, and least to the middle. This is the "lost-in-the-middle" effect.

So burying a critical instruction or fact in the middle of a giant history risks it being ignored — even though you paid full price to send it.

Keep key instructions and the current task near the edges; trim the bulky middle.

Batch API for Non-Blocking Jobs

One cost lever: the Message Batches API. It is about 50% cheaper than standard requests, with up to a 24-hour processing window.

The trade-offs: there is no latency SLA, and multi-turn tool calling is NOT supported. Use custom_id to correlate requests; re-submit only the failures.

Use Batch for overnight reports and large audits. Never use it for blocking, time-sensitive, or pre-merge checks — a user is waiting on those.

batch = client.messages.batches.create(requests=[
    {"custom_id": "doc-001", "params": {
        "model": "claude-sonnet-4-5", "max_tokens": 1024,
        "messages": [{"role": "user", "content": classify(doc_1)}]}},
    {"custom_id": "doc-002", "params": {
        "model": "claude-sonnet-4-5", "max_tokens": 1024,
        "messages": [{"role": "user", "content": classify(doc_2)}]}},
])  # ~50% cheaper, up to 24h, no latency SLA

Quick Check

A production support chatbot's per-conversation cost is climbing fast as sessions get longer, even though each user reply is short. What is the primary cause, and the right architect-grade fix?

Ответь в интерактивном уроке

Recap: Tokens, Context & Cost

Key takeaways:

The API keeps no state — you resend the full messages history every turn.
Billing is per token, split into input (system + tools + history) and output.
The context window caps input + output; resent history grows toward it and cost grows roughly with the square of conversation length.
Measure with usage and count_tokens; trim verbose tool output to relevant fields.
Summarize to stay in budget, but keep exact numbers/dates in a verbatim case-facts block; watch the lost-in-the-middle effect.
Batch API = ~50% cheaper for non-blocking jobs only — never for time-sensitive checks.

Можно начать бесплатно

Изучай Python с ИИ-репетитором — бесплатно

Пиши и запускай код прямо в браузере, получай мгновенную помощь от ИИ-репетитора 24/7 и продолжи учиться на сайте или в приложении.

Курсы: 26
Уроки: 104

Начать учиться бесплатно Посмотреть полный курс

Часто задаваемые вопросы

Урок «Токены, окна контекста и стоимость» бесплатный?

Да — полный текст урока «Токены, окна контекста и стоимость» бесплатно доступен здесь в веб-версии. Чтобы практиковать его интерактивно (встроенный редактор кода и ИИ-репетитор 24/7) и разблокировать остальной курс Claude Architect, подпишись на CoddyKit PRO. Курс Claude Architect содержит 4 уроков всего.

Чему я научусь в уроке «Токены, окна контекста и стоимость»?

Почему вся история отправляется при каждом ходе и во что это обходится Ты практикуешь Claude Architect с помощью реального кода, который запускаешь прямо в браузере, и ИИ-репетитор 24/7 отвечает на твои вопросы во время урока.

Нужен ли мне опыт, чтобы начать Claude Architect?

Предыдущий опыт не требуется. Claude Architect на CoddyKit структурирован для всех уровней — от новичков до продвинутых, поэтому ты можешь начать отсюда или с самого начала и учиться в своем темпе. Это урок 4 из 4.

Сколько времени занимает урок «Токены, окна контекста и стоимость»?

Большинство уроков CoddyKit занимают около 5–10 минут. Каждый из них компактный и интерактивный, поэтому ты постоянно делаешь прогресс и продолжаешь с того же места в веб-версии и приложении.

Можно ли писать и запускать код в этом уроке Claude Architect?

Да. Каждый урок Claude Architect включает встроенный редактор кода, поэтому ты пишешь и запускаешь реальный код прямо в браузере и получаешь моментальную обратную связь от AI — локальная установка не требуется.

Все уроки этого курса

← Назад к Claude Architect