CalcRecipe

AI Decision Platform

Context Planner

Decide whether your corpus fits a model window—and how to chunk when it does not.

Product 2026.07.5 · Catalog 2026.07.2 · Pricing pricing-2026.07.2 · Trust 2026.07.3 · Decision 2026.07.4 · Core 1.0.0

Corpus & model

Pricing basis

Pricing source: CalcRecipe Verified

Verified

Last verified: 2026-07-01

Dataset version: pricing-2026.07.2

https://ai.google.dev/pricing

Review recommended — pricing was verified 20 days ago.

This result is a planning estimate based on the latest pricing currently verified by CalcRecipe. Actual billing may differ because of taxes, regional pricing, usage tiers, promotions, routing, provider policy changes, or account-specific terms. Confirm final pricing with the provider before making a financial commitment.

Paste length or approximate characters.

If set, used when character size is empty (~1800 chars/page).

Context decision

Estimated tokens

33,333

Context usage

3.2%

Fits context

Yes

Recommended chunk

8,000

Suggested splits

1

Context window

1,048,576

Decision summary

  • • ~33,333 tokens @ 3.6 chars/token (markdown)
  • • 3.2% of 1,048,576 window
  • • Pricing source: verified

Assumptions

  • • Token estimates use content-type heuristics (chars/token), not a billed tokenizer.
  • • Fit leaves ~15% headroom for system prompts and output.
  • • Chunk guidance targets ~20% of the model window.

Planning estimate

This result is a planning estimate based on the latest pricing currently verified by CalcRecipe. Actual billing may differ because of taxes, regional pricing, usage tiers, promotions, routing, provider policy changes, or account-specific terms. Confirm final pricing with the provider before making a financial commitment.

Examples

  • Repo dump: Switch to code content type—token estimates rise vs plain text.
  • Long PDF: Enter pages only; planner expands to characters then tokens.

Frequently asked questions

Will this match provider billing tokens?
No—use it for architecture planning. Final bills follow each provider’s tokenizer.
Why can provider pricing change?
Providers update list prices, promotions, batch rates, cache rates, long-context tiers, and enterprise contracts without notice. CalcRecipe labels freshness so you can decide when to re-check.
When should I use custom pricing?
Use custom pricing when your invoice, aggregator markup, or negotiated contract differs from the public catalog. Custom inputs are labeled User Override and never shown as Verified.
How does CalcRecipe label pricing sources?
Verified, Estimated, Custom, Stale, or Unavailable. The source of every calculation stays visible in results and share snapshots.
Should I trust these numbers for contracts?
No. Always confirm official billing terms with the provider before financial commitments.

Planning context before you build

Context overflows destroy quality and inflate cost. Estimate tokens early against registry context windows.

Chunking guidance helps RAG and agent designs stay within reliable windows.

Provider list prices change often and may differ by region, channel, promotions, batch/cache rates, or enterprise contracts. CalcRecipe separates verified catalog rates from estimates and user overrides.

Custom pricing is browser or session state only—it is not public content and never silently replaces CalcRecipe Verified data.

Version history

  • 2026.07.3

    2026-07-20

    Added the AI Pricing Trust Layer with user overrides, freshness states, and transparent source labels.

    Catalog pricing can be incomplete or stale; builders must inject real rates without mislabeling them as verified.

  • 1.0.0

    2026-07-20

    Context Planner v1 — token estimates, fit checks, chunk guidance.

    Prevent context overflows before architecture lock-in.

Related AI planners

CalcRecipe Workshop Guides