claude-cost-optimizer

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #ai #typescript #llm #go #golang #android #machine-learning #rust #deep-learning #linux

claude-cost-optimizer

(★ 33)

Save 30-60% on Claude Code costs -- proven strategies, real benchmarks, copy-paste configs, and interactive tools

claude-cost-optimizer 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Claude Cost Optimizer

![GitHub stars](https://img.shields.io/github/stars/Sagargupta16/claude-cost-optimizer?style=flat-square&cacheSeconds=86400)
![GitHub forks](https://img.shields.io/github/forks/Sagargupta16/claude-cost-optimizer?style=flat-square&cacheSeconds=86400)
![License](https://img.shields.io/badge/License-MIT-blue?style=flat-square)
![Last Commit](https://img.shields.io/github/last-commit/Sagargupta16/claude-cost-optimizer?style=flat-square&cacheSeconds=86400)

> **Save 30-90% on Claude Code costs** with an installable skill, CLI tools, and 12 deep-dive guides.
>
> **30-60% is the typical result** for a mixed real workload. **Up to 90% is the ceiling** when you stack every lever -- prompt caching, Batch API, model routing, and context discipline -- against an unoptimized all-Opus baseline. Every number is sourced: see [How far can you actually go?](#how-far-can-you-actually-go).

## Install

**Claude Code (official plugin system):**

```bash
/plugin marketplace add Sagargupta16/claude-cost-optimizer
/plugin install cost-mode@claude-cost-optimizer
```

**Multi-agent (Cursor, Cline, Codex, 40+ agents):**

```bash
npx skills add Sagargupta16/claude-cost-optimizer
```

Then activate in any session:

```
/cost-mode              # Standard (40-60% output token reduction)
/cost-mode lite         # Professional brevity (20-40% output reduction)
/cost-mode strict       # Telegraphic, max savings (60-70% output reduction)
/cost-mode off          # Resume normal behavior
```

---

## What cost-mode Does

| Feature | How It Saves Tokens |
|---------|-------------------|
| **Strips filler** | Drops pleasantries, hedging, restating your question, trailing summaries |
| **Suggests cheaper models** | "Haiku handles this -- `/model haiku`" for simple tasks |
| **Suggests CLI tools** | "Use `prettier`/`eslint --fix` directly" instead of burning LLM tokens |
| **Session awareness** | Reminds to `/compact` after 20+ turns, fresh sessions for new tasks |
| **Minimal code gen** | Diffs over rewrites, no obvious comments, no speculative error handling |
| **Auto-deactivates** | Full clarity for security warnings, destructive ops, and when you're confused |

Technical accuracy is never sacrificed. Code in commits and PRs is written normally.

[Full skill documentation](skills/cost-mode/README.md)

---

## Rate your setup

### Locally, in 5 seconds (recommended)

`claude-rate` runs on your filesystem -- no signup, no GitHub upload, no network round-trip. Pick whichever runner fits your shell:

```bash
# curl one-shot (no Node, no install)
curl -sSL https://raw.githubusercontent.com/Sagargupta16/claude-cost-optimizer/main/tools/claude-rate/install.sh | sh -s -- .

# curl, persistent install
curl -sSL https://raw.githubusercontent.com/Sagargupta16/claude-cost-optimizer/main/tools/claude-rate/install.sh | sh -s -- --install
```

Add `--fix` to print copy-pasteable fix commands, `--strict` to fail CI when the grade drops below B, or `--json` for machine-readable output. See [tools/claude-rate/README.md](tools/claude-rate/README.md) for the full breakdown.

The local rater works on private and uncommitted repos and inspects things the web analyzer can't reach: `settings.local.json`, `.claudeignore` coverage gaps vs files actually on disk, and secrets in your working tree. The [web analyzer](https://sagargupta16.github.io/claude-cost-optimizer/analyzer) applies the same 7-category rubric (CLAUDE.md, .claudeignore, settings, MCP, hooks, security, skills/agents/commands) to any public repo.

### Public repos -- web tools

| Tool | What It Does |
|------|-------------|
| **[Repo Analyzer](https://sagargupta16.github.io/claude-cost-optimizer/analyzer)** | Paste a GitHub URL to get a cost audit, grade (A+ to F), and recommendations |
| **[Cost Calculator](https://sagargupta16.github.io/claude-cost-optimizer/calculator)** | Estimate monthly spend with interactive charts: per-turn cost curve, savings breakdown, model comparison |
| **[Badge Checker](https://sagargupta16.github.io/claude-cost-optimizer/badge)** | Score your setup and get a shields.io badge for your repo |

---

## Before vs After

Real project, 30-turn session, Opus 5 (identical math on Opus 4.8 -- same $5/$25):

```
BEFORE (no optimization):                 AFTER (5 minutes of setup):
  CLAUDE.md:        6,200 chars (truncated)  CLAUDE.md:        2,800 chars (under limit)
  .claudeignore:    missing                   .claudeignore:    12 patterns
  MCP servers:      6 active                  MCP servers:      2 active
  System prompt:    ~15,000 tokens/turn       System prompt:    ~5,500 tokens/turn
  Session cost:     $2.85                     Session cost:     $1.12
  Monthly (3x/day): $188.10                   Monthly (3x/day): $73.92

Savings: $114.18/month (61%)
```

---

## How Far Can You Actually Go?

Short answer: **30-60% is what a typical mixed workload saves. Up to ~90% is the ceiling** when every lever stacks against a naive all-Opus, no-cache, verbose baseline. The headline numbers below are each real and sourced -- but each one applies only to the *favorable slice* of your spend, so the compound rarely holds across an entire real workload. Treat 90% as a ceiling, not a promise.

| Lever | Published savings | Applies to | Source |
|-------|:-----------------:|------------|--------|
| **Prompt caching** | **up to 90%** cost, 85% latency | cached input only (cache hit = 0.1x input price) | [Anthropic: Prompt caching](https://claude.com/blog/prompt-caching), [pricing docs](https://platform.claude.com/docs/en/about-claude/pricing) |
| **Batch API** | flat **50%** off input **and** output, stacks with caching | any async (24h) work | [Anthropic: Message Batches API](https://claude.com/blog/message-batches-api), [batch docs](https://platform.claude.com/docs/en/build-with-claude/batch-processing) |
| **Model routing** | **~80%** (Opus->Haiku is a flat 5x ratio); RouteLLM up to 85% at 95% quality | tasks a cheaper model handles well | [RouteLLM (arXiv 2406.18665)](https://arxiv.org/pdf/2406.18665), [LMSYS](https://lmsys.org/blog/2024-07-01-routellm/) |
| **Context management** | **84%** fewer tokens in a 100-turn eval | long agentic sessions | [Anthropic: Context management](https://claude.com/blog/context-management) |
| **Subscription vs API** | **~90%+** for heavy users (Pro $20 / Max $100-200 flat) | power users vs pay-as-you-go | [ksred cost tracker](https://www.ksred.com/claude-code-pricing-guide-which-plan-actually-saves-you-money/) (n=1) |

### The honest read

- **"up to 90%" is a ceiling, not a typical result.** Anthropic itself publishes 90% for caching *alone*, and the levers genuinely multiply against an unoptimized baseline. But each 90% is a best case on its favorable slice (cached input for caching; conversational traffic for routing), so a whole mixed workload lands well below the sum.
- **Measured real-world totals cluster around 70-73%** when teams stack multiple levers -- e.g. a 6-person team cutting `$2,400 -> $680/mo` (72%). Those are individual case studies (n=1 each), not controlled measurements.
- **The cost-mode skill on its own delivers 30-60%** -- it does output-token reduction and model-routing hints, not batch/caching/subscription. The 90% ceiling needs the full playbook in the [guides](#guides), not just the skill.
- **Caching and batch are the firmest floors** (first-party Anthropic pricing; batch is a documented flat 50% that provably stacks with caching). Routing and subscription savings are the most workload-sensitive.

> Prices verified against the [pricing reference](#pricing-reference-verified-2026-07-25) below (2026-07-25). Cache hit = 0.1x base input across all current models; Batch = 50% off both input and output.

---

## Quick Start (5 Minutes, No Skill Needed)

Even without installing the skill, these 5 changes cut costs immediately:

| # | Strategy | Savings | Guide |
|---|----------|:-------:|-------|
| 1 | **Keep CLAUDE.md under 4,000 characters** -- content beyond 4K is silently truncated | 10-20% | [Context Optimization](guides/02-context-optimization.md) |
| 2 | **Use Haiku for simple tasks** (`--model haiku`) -- 5x cheaper than Opus | 20-40% | [Model Selection](guides/03-model-selection.md) |
| 3 | **Use Plan Mode before coding** -- prevents wasted iterative cycles | 15-25% | [Workflow Patterns](guides/04-workflow-patterns.md) |
| 4 | **Add `.claudeignore`** -- stop Claude from reading node_modules, dist, lock files | 5-15% | [Context Optimization](guides/02-context-optimization.md) |
| 5 | **Delegate to subagents** -- isolate expensive searches from main context | 20-40% | [Workflow Patterns](guides/04-workflow-patterns.md) |

Full walkthrough: **[Getting Started in 5 Minutes](guides/00-getting-started.md)**

---

## Skills Roadmap

cost-mode is the first skill. More are planned:

| Skill | Status | What It Does | Cost Impact |
|-------|:------:|-------------|:-----------:|
| **cost-mode** | Live | Concise responses, model routing suggestions, session awareness | 30-60% (skill alone) |
| **claudeignore-gen** | Planned | Auto-generates .claudeignore based on your project's tech stack | 5-15% input reduction |
| **context-compress** | Planned | Rewrites your CLAUDE.md to be shorter while keeping all essential info | 10-20% input reduction |
| **cache-optimizer** | Planned | Detects cache-busting patterns and suggests fixes to maximize prompt cache hits | 10-25% input reduction |
| **budget-guard** | Planned | Per-session and per-day spending limits with warnings before you blow past them | Prevents overspend |

Want to build one? Skills are just `SKILL.md` files -- see [CONTRIBUTING.md](CONTRIBUTING.md) and the [skills/cost-mode/](skills/cost-mode/) directory for the pattern.

---

## Guides

12 deep-dive guides covering every optimization area:

| Guide | What You'll Learn |
|-------|-------------------|
| [00 - Getting Started](guides/00-getting-started.md) | Zero to optimized in 5 minutes -- the essential setup |
| [01 - Understanding Costs](guides/01-understanding-costs.md) | How billing works, what costs the most, where money goes |
| [02 - Context Optimization](guides/02-context-optimization.md) | Reduce input tokens: CLAUDE.md, .claudeignore, file reads |
| [03 - Model Selection](guides/03-model-selection.md) | When to use Opus vs Sonnet vs Haiku (with decision tree) |
| [04 - Workflow Patterns](guides/04-workflow-patterns.md) | Plan mode, subagents, commands, batch operations |
| [05 - Team Budgeting](guides/05-team-budgeting.md) | Per-developer budgets, cost tracking, ROI calculation |
| [06 - Access Methods & Pricing](guides/06-access-methods-pricing.md) | Compare API vs Bedrock vs Vertex AI vs Claude Code pricing |
| [07 - MCP & Agent Cost Impact](guides/07-mcp-agent-costs.md) | MCP server overhead, subagent costs, Agent SDK patterns |
| [08 - Prompt Caching Deep Dive](guides/08-prompt-caching.md) | Cache mechanics, TTL economics, maximizing hit rates, ROI math |
| [09 - Subscription Plan Value](guides/09-subscription-value.md) | Choose the right plan, maximize allowance, upgrade/downgrade signals |
| [10 - Three-Tier Task Routing](guides/10-task-routing.md) | Skip the LLM for Tier 0 tasks, route cheap tasks to Haiku, save Opus for complex work |
| [11 - Speed vs Cost](guides/11-speed-vs-cost.md) | Make Claude faster without burning money -- free latency levers first, Fast Mode economics last |

Also: [Visual Diagrams](guides/diagrams.md) (Mermaid flowcharts) | [One-Page Cheatsheet](cheatsheet.md)

---

## Templates

Copy-paste configs that are already optimized:

**CLAUDE.md**: [Minimal](templates/CLAUDE.md/minimal.md) | [Standard](templates/CLAUDE.md/standard.md) | [Comprehensive](templates/CLAUDE.md/comprehensive.md) | [Monorepo](templates/CLAUDE.md/monorepo.md)

**By Stack**: [React+Vite](templates/CLAUDE.md/by-stack/react-vite.md) | [Next.js](templates/CLAUDE.md/by-stack/nextjs.md) | [FastAPI](templates/CLAUDE.md/by-stack/fastapi-python.md) | [MERN](templates/CLAUDE.md/by-stack/mern.md) | [Terraform](templates/CLAUDE.md/by-stack/terraform-aws.md) | [Go](templates/CLAUDE.md/by-stack/go.md) | [Rust](templates/CLAUDE.md/by-stack/rust.md) | [Django](templates/CLAUDE.md/by-stack/django.md) | [Rails](templates/CLAUDE.md/by-stack/rails.md) | [Spring Boot](templates/CLAUDE.md/by-stack/java-spring.md)

**Settings**: [Cost-Conscious](templates/settings/cost-conscious.json) | [Balanced](templates/settings/balanced.json) | [Performance-First](templates/settings/performance-first.json)

**Commands**: [/cost-check](templates/commands/cost-check.md) | [/budget-mode](templates/commands/budget-mode.md) | [/quick-fix](templates/commands/quick-fix.md) | [/optimize](tools/optimize-command/optimize.md)

---

## CLI Tools

7 tools for measuring, tracking, and reducing costs. [Full tools documentation](tools/README.md)

| Tool | What It Does |
|------|-------------|
| [Token Estimator](tools/token-estimator/) | Estimate token count and cost for any file |
| [Usage Analyzer](tools/usage-analyzer/) | Find cost hotspots across your sessions |
| [Badge Generator](tools/badge-generator/) | Grade your project config (A+ to F) from the CLI |
| [MCP Cost Server](tools/mcp-cost-server/) | In-session cost estimation via MCP |
| [VS Code Extension](tools/vscode-extension/) | Token count and cost in the status bar |
| [GitHub Action](tools/actions/claude-cost-audit/) | Automated cost audit on PRs |
| [Budget Hooks](hooks/) | Track tool calls, log costs, warn at thresholds |

---

## Pricing Reference (verified 2026-07-25)

| Model | Input / 1M | Output / 1M | Cache Hit / 1M | 5m Cache Write / 1M | 1h Cache Write / 1M | Context | Max Output | Min cacheable prompt |
|-------|:----------:|:-----------:|:---------------:|:-------------------:|:-------------------:|:-------:|:----------:|:--------------------:|
| **Fable 5** (highest capability) | $10.00 | $50.00 | $1.00 | $12.50 | $20.00 | 1M | 128K | 512 |
| Mythos 5 (limited, [Glasswing](https://anthropic.com/glasswing)) | $10.00 | $50.00 | $1.00 | $12.50 | $20.00 | 1M | 128K | 512 |
| **Opus 5** (Opus flagship) | $5.00 | $25.00 | $0.50 | $6.25 | $10.00 | 1M | 128K | **512** |
| Opus 4.8 (legacy) | $5.00 | $25.00 | $0.50 | $6.25 | $10.00 | 1M | 128K | 1,024 |
| Opus 4.7 | $5.00 | $25.00 | $0.50 | $6.25 | $10.00 | 1M | 128K | 2,048 |
| Opus 4.6 | $5.00 | $25.00 | $0.50 | $6.25 | $10.00 | 1M | 128K | 4,096 |
| Opus 4.5 | $5.00 | $25.00 | $0.50 | $6.25 | $10.00 | 200K | 64K | 4,096 |
| Opus 4.1 | $15.00 | $75.00 | $1.50 | $18.75 | $30.00 | 200K | 32K | 1,024 |
| **Sonnet 5** (Sonnet flagship) | $3.00 | $15.00 | $0.30 | $3.75 | $6.00 | 1M | 128K | 1,024 |
| Sonnet 4.6 | $3.00 | $15.00 | $0.30 | $3.75 | $6.00 | 1M | 64K | 1,024 |
| Sonnet 4.5 | $3.00 | $15.00 | $0.30 | $3.75 | $6.00 | 200K | 64K | 1,024 |
| Haiku 4.5 | $1.00 | $5.00 | $0.10 | $1.25 | $2.00 | 200K | 64K | 4,096 |
| Mythos Preview (retired 2026-06-30) | $25.00 | $125.00 | $2.50 | $31.25 | $50.00 | 1M | -- | 2,048 |

**Opus 5** (`claude-opus-5`, GA 2026-07-24) is the current Opus flagship and Anthropic's recommended default for complex agentic coding. It costs the **same $5/$25 as Opus 4.8**, so the upgrade is free at the posted rate -- see [what actually changes](#migrating-to-opus-5) before you flip the model string. **1M context** on Fable 5, Mythos 5, Opus 5, Opus 4.8, Opus 4.7, Opus 4.6, Sonnet 5, and Sonnet 4.6 bills at **standard rates** across the full window (no long-context premium). **Sonnet 5** (`claude-sonnet-5`, GA 2026-06-30) introductory pricing of **$2/$10 per MTok runs through 2026-08-31**, then standard **$3/$15** (table above shows standard rates). **Batch API**: 50% off both input and output -- Opus 5 batch is **$2.50/$12.50** (up to 300K output via the `output-300k-2026-03-24` beta). **Fast Mode** (research preview, **Opus 5 and Opus 4.8 only**): **2x** ($10/$50) on both, up to 2.5x output tokens/sec. **Regional endpoints** (Bedrock / Vertex AI / Claude API `inference_geo: "us"` for 4.6+ models): +10%. **Subscriptions**: Pro $20/mo (or **$200/yr ≈ $16.67/mo**, ~17% off), Max 5x $100/mo, Max 20x $200/mo. **Web search**: $10 per 1,000 searches plus token costs. **Web fetch**: free beyond token costs. **Code execution**: free with web search/fetch; otherwise 1,550 free hours/month then $0.05/hour per container. **Bash tool**: +325 input tokens on Opus 5 / 4.8 / 4.7 (+244 on Opus 4.6 and earlier). **Text editor tool**: +700 input tokens.

> **Minimum cacheable prompt is a real cost lever.** A `cache_control` block below the model's threshold is silently ignored -- you pay full input price every turn and see no error. Opus 5 halves the Opus 4.8 threshold from 1,024 to **512 tokens**, so system prompts and CLAUDE.md files that never cached on 4.8 start caching on 5. Haiku 4.5, Opus 4.6, and Opus 4.5 sit at 4,096, the worst of the current lineup.
>
> **Opus 5 / 4.8 / 4.7 tokenizer caveat**: The tokenizer introduced with Opus 4.7 may use **up to 35% more tokens** for the same fixed text. Effective per-task cost is higher than posted pricing suggests -- factor this into budgets, especially when comparing against Opus 4.6 / Sonnet 4.6.
>
> **Fast Mode (research preview)**: Now **Opus 5 and Opus 4.8 only**, via the `fast-mode-2026-02-01` beta header (`speed: "fast"`). Both are **2x** ($10/$50 per MTok). Up to 2.5x more output tokens/second; the speed gain is on output tokens/sec, not time-to-first-token. **Opus 4.7 now returns an error** on `speed: "fast"` with no fallback, and **Opus 4.6 silently runs at standard speed and standard rates** (`usage.speed` comes back `"standard"`) -- if you were paying 6x for Fast Mode on either, that option is gone. Claude API + Managed Agents only: not on Claude Platform on AWS, Bedrock, Vertex AI, Microsoft Foundry, Batch API, or Priority Tier. Switching speeds invalidates prompt cache. [Join the waitlist](https://claude.com/fast-mode).
>
> **Fable 5 / Mythos 5** (GA 2026-06-09): Anthropic's Mythos-class tier above Opus, at **2x Opus 5's price** ($10/$50). Same specs for both: 1M context at standard rates, 128K max output, always-on adaptive thinking (control depth with `effort`; `thinking: disabled` not supported), 4.7-generation tokenizer. **Fable 5 is GA everywhere** (Claude API, Claude Platform on AWS, Bedrock, Vertex AI, Microsoft Foundry) and includes safety classifiers that can decline requests -- a refusal returns HTTP 200 with `stop_reason: "refusal"`, **pre-output refusals are not billed**, and the beta `fallbacks` parameter plus fallback credit make retrying on another model cheap. **Mythos 5** is the same model without the classifiers, limited to approved [Project Glasswing](https://anthropic.com/glasswing) customers. No Fast Mode on either; Batch API supported ($5/$25). Requires 30-day data retention (no zero-data-retention option).
>
> **Mythos Preview**: superseded by Mythos 5 -- **retired 2026-06-30**. Was the invite-only defensive-cybersecurity research preview under Project Glasswing.
>
> **Looking for older model IDs and pricing?** See the [Legacy & Retired Models](#legacy--retired-models) section below for migration context.

### Migrating to Opus 5

Opus 5 is the same price as Opus 4.8, but it is not a drop-in swap of the model string. Four things change your bill or break your request:

| Change | Why it matters for cost |
|--------|-------------------------|
| **Thinking is ON by default** | Omit `thinking` and Opus 5 thinks adaptively. Reasoning tokens bill as **output** at $25/1M, and `max_tokens` is a hard cap on thinking **plus** text -- an unchanged `max_tokens: 4096` now gets eaten by thinking before your answer is written. Raise it to 64K+ if you run `xhigh`/`max` effort. |
| **`thinking: {type: "disabled"}` is effort-gated** | Legal only at effort `high` or below. Pairing it with `xhigh` or `max` returns a **400**, so a config that worked on 4.8 can hard-fail. |
| **Min cacheable prompt drops to 512 tokens** | Prompts too short to cache on 4.8 (1,024) now cache on 5. Free savings if you re-check your `cache_control` placement. |
| **Cybersecurity classifiers ship on Opus 5** | Security-adjacent work can hit `stop_reason: "refusal"`. Set the server-side `fallbacks` param (beta `server-side-fallback-2026-07-01`) to auto-retry on Opus 4.8 inside the same call rather than paying for a failed round-trip. |

Two prompt-level cleanups worth doing at the same time: Opus 5 writes **longer** output than 4.8 by default, so re-tune your verbosity instructions; and it self-verifies, so any "double-check your work before answering" instruction you carried over from an older model is now paying twice for the same behavior. New beta `mid-conversation-tool-changes-2026-07-01` also lets you change tool definitions between turns without invalidating the prompt cache -- previously a cache-busting move.

Full details: [Anthropic's Opus 5 migration guide](https://platform.claude.com/docs/en/about-claude/models/migrating-to-claude-opus-5).

---

## Legacy & Retired Models

> Reference only -- **don't use these for new work.** Kept for migration context if you're unwinding code that still pins old model IDs.

**Recently retired** (requests now fail):

| Model | Retired on | Migrate to |
|-------|:----------:|-----------|
| Claude Opus 3 (`claude-3-opus-20240229`) | 2026-01-05 | Opus 5 |
| Claude Sonnet 3.7 (`claude-3-7-sonnet-20250219`) | 2026-02-19 | Sonnet 5 |
| Claude Haiku 3.5 (`claude-3-5-haiku-20241022`) | 2026-02-19 (still on Bedrock + Vertex AI) | Haiku 4.5 |
| Claude Haiku 3 (`claude-3-haiku-20240307`) | 2026-04-20 | Haiku 4.5 |
| Claude Sonnet 4 (`claude-sonnet-4-20250514`) | 2026-06-15 | Sonnet 5 |
| Claude Opus 4 (`claude-opus-4-20250514`) | 2026-06-15 | Opus 5 |
| Claude Mythos Preview (`claude-mythos-preview`) | 2026-06-30 | Mythos 5 (Glasswing) |
| Claude Sonnet 3.5 v1 / v2, Sonnet 3, Claude 2.x, Claude 1.x, Instant 1.x | 2024-2025 | See deprecations page |

**Deprecated, retiring soon**:

| Model | Retirement date | Migrate to |
|-------|:---------------:|-----------|
| Claude Opus 4.1 (`claude-opus-4-1-20250805`) | **2026-08-05** | Opus 5 |

**Older snapshots still callable** (not retired, but not the headline tier):

| Snapshot | Pricing | Context | Earliest retirement | Why use |
|----------|:-------:|:-------:|:-------------------:|---------|
| Opus 4.8 | $5/$25 | 1M | 2027-05-28 | Previous flagship -- pin if prompts are tuned to it, or if you need thinking off at `xhigh`/`max` (Opus 5 rejects that combination). Also the fallback target for Opus 5 cyber refusals |
| Opus 4.7 | $5/$25 | 1M | 2027-04-16 | Pinned workloads. No Fast Mode -- `speed: "fast"` now errors |
| Opus 4.6 | $5/$25 | 1M | 2027-02-05 | Pinned workloads / older tokenizer. `speed: "fast"` silently runs standard |
| Opus 4.5 | $5/$25 | 200K | 2026-11-24 | Pinned workloads only |
| Opus 4.1 | $15/$75 | 200K | 2026-08-05 | Compatibility only -- 3x more expensive, deprecated |
| Sonnet 4.6 | $3/$15 | 1M | 2027-02-17 | Pinned workloads -- migrate to Sonnet 5 |
| Sonnet 4.5 | $3/$15 | 200K | 2026-09-29 | Pinned workloads only |

> Authoritative source: [platform.claude.com/docs/en/about-claude/model-deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations).
>
> The cheatsheet has a [more detailed legacy table](cheatsheet.md#legacy--retired-models-reference-only) including last-known pricing for every retired tier.

---

## Benchmarks & Case Studies

- [Task Comparison](benchmarks/task-comparison.md) -- same task, optimized vs not
- [Model Comparison](benchmarks/model-comparison.md) -- Opus vs Sonnet vs Haiku
- [Context Size Impact](benchmarks/context-size-impact.md) -- how CLAUDE.md size affects cost
- [Community Leaderboard](benchmarks/leaderboard.md) -- crowdsourced cost-per-task data
- [Case Studies](case-studies/README.md) -- real-world optimization stories

---

## Community

- **[GitHub Discussions](https://github.com/Sagargupta16/claude-cost-optimizer/discussions)** -- ask questions, share strategies
- **[Contributing](CONTRIBUTING.md)** -- from starring the repo to building new skills
- **[Issue Templates](https://github.com/Sagargupta16/claude-cost-optimizer/issues/new/choose)** -- tips, benchmarks, case studies

### Complementary Projects

| Project | What It Does | Savings |
|---------|-------------|:-------:|
| [caveman](https://github.com/JuliusBrussee/caveman) | Brevity skill -- strips filler from responses | 50-75% output |
| [claude-mem](https://github.com/thedotmack/claude-mem) | Compresses session context for handoff | Input reduction |
| [claudetop](https://github.com/liorwn/claudetop) | htop-style monitoring with cost tracking | Visibility |

---

## FAQ

<details>
<summary>How much does Claude Code actually cost?</summary>

With Pro ($20/mo or $200/yr ≈ $16.67/mo with annual billing -- 17% off), Max 5x ($100/mo), or Max 20x ($200/mo), you get included usage. Heavy users report $3-15/day without optimization, $1-5/day with it. Opus 5, 4.8, 4.7, and 4.6 at $5/$25 are 3x cheaper per token than Opus 4.1 ($15/$75) -- but the tokenizer introduced with Opus 4.7 can use up to 35% more tokens, so the effective gap is closer to ~2x.
</details>

<details>
<summary>Does this apply to the Claude API too?</summary>

Context optimization, model selection, and prompt engineering apply to both. The skill and commands are Claude Code-specific.
</details>

<details>
<summary>Will optimization reduce output quality?</summary>

No. These strategies eliminate waste (duplicate context, unnecessary file reads, expensive models for simple tasks). Quality stays the same or improves -- less noise means better reasoning.
</details>

<details>
<summary>What's the biggest single change I can make?</summary>

Install cost-mode (`npx skills add Sagargupta16/claude-cost-optimizer`) and switch to Haiku for routine tasks. Combined: 50-70% savings.
</details>

---

## Star History

If this repo helped you save money, consider giving it a star!

---

## More AI Developer Tools

If you found this useful, check out my other AI/Claude tools:

| Project | Description |
|---------|-------------|
| [claude-code-recipes](https://github.com/Sagargupta16/claude-code-recipes) | 50+ copy-paste recipes for Claude Code - commands, subagents, hooks, skills |
| [claude-skills](https://github.com/Sagargupta16/claude-skills) | Custom Claude Code plugin marketplace with dev-workflow, FARM stack, and more |
| [agent-recipes](https://github.com/Sagargupta16/agent-recipes) | AI agent workflows for real-world dev tasks - code review, testing, security |
| [ai-git-hooks](https://github.com/Sagargupta16/ai-git-hooks) | AI-powered git hooks - auto-review diffs, generate commit messages, security scanning |
| [mcp-toolkit](https://github.com/Sagargupta16/mcp-toolkit) | Production-ready middleware for MCP servers - auth, caching, rate limiting |

---

## License

[MIT](LICENSE) - use these strategies, templates, and tools however you want.

claude-cost-optimizer

claude-cost-optimizer 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

claude-cost-optimizer

claude-cost-optimizer 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README