This slug duplicates the ranking tracker. Numbers here were last written as June 2026.
Direct Answer (9 September 2026): Claude 3.5 Sonnet is retired. Current public Sonnet is Sonnet 5 at $2 / $10 per MTok. Current lineup is Fable 5.1, Opus 5.5 ($4 / $20 per MTok), Opus 5, Sonnet 5, Haiku 4.5. Live tracker: current Claude model version. Seat dollars: pricing hub.
Do not ship 3.5 Sonnet, Sonnet 4.6, or Opus 4.8 IDs in new work. Confirm the alias in the console.
Claude Code is Anthropic’s official CLI for Claude — a terminal-based agent you can point at any codebase and have it read, write, test, and ship code. It’s different from the Claude.ai chat interface in one key way: Claude Code can act, not just answer. It reads your actual files, runs your actual commands, and makes changes that stick.
This guide walks you through installation, first run, and the commands that cover 90% of what you’ll do daily.
Claude Code runs in your terminal. It gives Claude access to your local machine — file system, shell, and any MCP servers you configure — so it can do real engineering work: implement features, fix bugs, write tests, explain unfamiliar codebases, and run multi-step agentic workflows.
It is not a code autocomplete plugin (that’s what GitHub Copilot does). Claude Code is a conversational agent that works at the task level, not the token level. You describe what you want; it figures out the steps and executes them.
Claude Code requires Node.js 18 or later. Install via npm:
npm install -g @anthropic-ai/claude-codeVerify the install:
claude --versionThat’s the only dependency. Claude Code is a Node.js CLI — no Docker, no Python env, no platform-specific setup beyond Node.
The first time you run claude, it walks you through authentication. You have two options:
Option 1: Claude subscription (Pro, Max, Team, Enterprise)
Run claude, select “Login with Claude.ai,” and it opens a browser window to authorize. Your subscription covers Claude Code usage — no separate API billing.
Option 2: Anthropic API key
Set your API key as an environment variable before running:
export ANTHROPIC_API_KEY="sk-ant-..."
claudeOr on Windows:
$env:ANTHROPIC_API_KEY = "sk-ant-..."
claudeAPI key usage is billed per token at standard API rates. For heavy daily use, a Max subscription ($100–$200/month) is usually more economical than API billing.
Navigate to a project directory and start Claude Code:
cd ~/projects/my-app
claudeClaude Code reads your directory automatically. At the > prompt, describe what you want:
> What does this codebase do? Give me a 3-paragraph overview.
Claude reads the files it needs and responds. No configuration required for basic usage — Claude Code infers context from the directory you’re in.
claude — Start an interactive sessionclaudeLaunches the REPL (read-eval-print loop). This is where you spend most of your time. Claude has access to your current directory’s files, can run bash commands, and can call any MCP servers you’ve configured.
Within a session, you can:
/help to see available slash commands/clear to reset context without leaving the sessionEscape twice to interrupt a running taskclaude -p "prompt" — One-shot non-interactive modeclaude -p "What are all the API endpoints in this codebase?"Runs a single prompt and exits. No REPL. Good for scripting, CI pipelines, or quick one-off queries you don’t want to interrupt a workflow for. Output goes to stdout — pipe it wherever you need it.
claude -p "Summarize the changes in the last 10 commits" | pbcopyclaude mcp add — Connect an external toolclaude mcp add github -- npx -y @modelcontextprotocol/server-githubAdds an MCP server to your Claude Code configuration. After running this, Claude can call the server’s tools in any session. Common additions:
# File system access (scoped to a directory)
claude mcp add files -- npx -y @modelcontextprotocol/server-filesystem ~/Documents
# GitHub integration
claude mcp add github -- npx -y @modelcontextprotocol/server-github
# Web search
claude mcp add search -- npx -y @modelcontextprotocol/server-brave-searchThe GitHub and Brave Search servers need API tokens — set them as environment variables before the server starts, or pass them via the --env flag in the mcp add command.
claude -c — Continue the last conversationclaude -cResumes your most recent Claude Code conversation, including all prior context. Essential for multi-session work on a feature. If you closed the terminal mid-task, claude -c picks up exactly where you left off.
For a specific prior conversation:
claude --resume SESSION_IDclaude --model — Select the model for a sessionclaude --model claude-opus-4-8Claude Code defaults to the most capable available model for your plan. You can override this per session. Current options:
claude-fable-5 — Highest capability, complex tasks (2x cost vs Opus 4.8)claude-opus-4-8 — Default for most work, strong balance of quality and speedclaude-sonnet-4-6 — Faster responses, good for routine tasksclaude-haiku-4-5-20251001 — Fastest, lowest cost, short tasksWhile in a Claude Code session (> prompt), these slash commands are available:
| Command | What It Does |
|---|---|
/help | Show all available commands |
/clear | Clear conversation context (keep the session open) |
/compact | Compress prior context to save tokens while preserving essential memory |
/cost | Show token usage and estimated cost for the current session |
/model | Switch the model mid-session |
/review | Request a multi-agent code review of the current branch |
/init | Generate a CLAUDE.md file with project context for this repo |
/exit | End the session |
Drop a CLAUDE.md file in your project root and Claude Code reads it automatically at session start. Use it to encode project-specific context Claude shouldn’t have to re-derive every session:
# My Project
## Architecture
- Backend: FastAPI + PostgreSQL
- Frontend: React + TypeScript
- Deployed to: AWS ECS
## Development
- Tests: `pytest tests/`
- Local server: `./scripts/start-dev.sh`
- Database migrations: `alembic upgrade head`
## Rules
- Never modify migration files directly
- All API routes go in `src/routes/`
- Use `httpx` not `requests` for HTTP callsGenerate a starter CLAUDE.md for an existing project with /init.
Claude Code asks for confirmation before running bash commands, creating files, or making other changes — unless you grant it broader permissions. There are three ways to control this:
--dangerously-skip-permissions: Skip all confirmations. Use only in isolated environments (Docker containers, CI). Not for everyday use on your primary machine.For most work, the default confirmation behavior is the right trade-off — it keeps you in the loop on changes without requiring you to pre-define a permission policy.
Claude Code integrates with VS Code and JetBrains IDEs. Install the extension from each marketplace, then launch Claude Code from inside the IDE. This keeps the terminal panel visible alongside your editor without alt-tabbing between windows.
The IDE extensions also add shortcuts for common actions like opening Claude Code in the current file’s directory and running one-shot queries against the selected code.
Related on Tygart Media: Claude Code billing · Claude Code vs Cursor · Claude Code tutorial.
What’s the difference between Claude Code and Claude.ai?
Claude.ai is the web chat interface — good for questions, document analysis, and writing. Claude Code is a terminal CLI that can access your local files, run commands, and act autonomously on multi-step tasks. Claude.ai can’t modify files on your machine; Claude Code can.
Does Claude Code cost extra on top of my Claude subscription?
No. Claude Pro, Max, Team, and Enterprise subscriptions include Claude Code access. You use the same account. Heavy agentic usage counts toward the plan’s usage limits, but there’s no separate Claude Code fee.
Can Claude Code access the internet?
Not by default. Claude Code’s built-in WebFetch tool can fetch content from a specific URL when you provide it. For live web search, add the Brave Search or similar MCP server. Claude can’t browse freely without explicit tool access.
What does Claude Code do with my code?
Claude Code sends the file contents and context it needs to the Anthropic API for inference. Standard Anthropic API data policies apply — if you’re using an API key, you can configure zero data retention. If you’re using a subscription, default Anthropic retention policies apply. Review Anthropic’s privacy policy for current details.
Is Claude Code open source?
Claude Code itself (the CLI client) is not open source — it’s an Anthropic product. The MCP server ecosystem it connects to includes many open-source servers, and the MCP specification itself is open.
What version of Node.js do I need?
Node.js 18 or later. Run node --version to check. The Long-Term Support (LTS) version is always a safe choice.
Last verified: June 12, 2026. Claude Code is updated frequently — run npm update -g @anthropic-ai/claude-code to stay current.
Model Context Protocol (MCP) is the reason Claude can read your files, query your database, search the web, and push code to GitHub — all from inside a single conversation. Without it, Claude would be limited to whatever you paste in manually. With it, Claude connects to almost any external system.
Quick answer: MCP is an open standard developed by Anthropic that lets AI models securely connect to external tools, data sources, and services through a standard client-server architecture (MCP getting started). You install an MCP server for the system you want Claude to access. Claude becomes a client that calls that server. The server executes the action and returns results.
Before MCP, connecting an AI model to external data meant one of two things: either the AI company built a native integration (slow, expensive, proprietary), or you cobbled together a pipeline that passed data manually between systems.
Neither approach scales. If Claude natively supported every database, every API, every file format, and every SaaS tool on the planet, the model would be perpetually behind. And manual copy-paste workflows aren’t agentic — they require you to do all the coordination work the AI should be doing.
MCP solves this with a universal adapter layer. Instead of building individual integrations, Anthropic defined a standard. Now any developer can build an MCP server for any system, and any MCP-compatible AI client (like Claude) can use it automatically.
MCP uses a client-server model over two transport mechanisms:
The communication protocol underneath is JSON-RPC 2.0 — a lightweight, well-understood standard for calling methods and getting results.
Each MCP server exposes one or more of three primitives:
read_file(path), create_issue(title, body), run_query(sql). Claude decides when to call them based on context.When Claude sees a task that could benefit from an available tool, it calls the tool, receives the result, and incorporates it into the response. This happens automatically — you don’t have to tell Claude when to use MCP. Claude decides based on what the server exposes.
Both Claude Code (the CLI tool) and Claude Desktop support MCP, but they configure servers differently.
Claude Code has built-in MCP management via the claude mcp command family:
claude mcp add my-server -- npx -y @modelcontextprotocol/server-filesystem /path/to/directory
claude mcp list
claude mcp remove my-serverServers added with claude mcp add are stored in your Claude Code config (~/.claude.json or the project-level .claude/settings.json). Project-level configs let you commit MCP server setups to source control so the whole team gets them automatically.
Claude Code also ships with a set of built-in tools that behave like MCP servers but don’t require separate installation: file read/write/edit, bash execution, glob search, grep, web fetch, and the agent spawning tools you’re reading about in this article.
Claude Desktop reads MCP server configuration from a JSON file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonA typical config entry looks like this:
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/Users/you/Documents"]
},
"github": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-github"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_your_token_here"
}
}
}
}Restart Claude Desktop after editing the config. Each server you add appears in the Claude Desktop interface with a hammer icon, and Claude can access its tools in any conversation.
Anthropic maintains a reference set of official MCP servers. These are the ones worth knowing:
| Server | What It Does | Package |
|---|---|---|
| Filesystem | Read/write files and directories on your local machine | @modelcontextprotocol/server-filesystem |
| GitHub | Read repos, create issues, open PRs, push code | @modelcontextprotocol/server-github |
| PostgreSQL | Read-only SQL queries against a Postgres database | @modelcontextprotocol/server-postgres |
| SQLite | Read/write a local SQLite database file | @modelcontextprotocol/server-sqlite |
| Brave Search | Live web search via Brave’s Search API | @modelcontextprotocol/server-brave-search |
| Puppeteer | Headless browser — screenshot pages, scrape, fill forms | @modelcontextprotocol/server-puppeteer |
| Slack | Read channels, send messages, search workspace | @modelcontextprotocol/server-slack |
| Google Drive | Read and search Google Drive files | @modelcontextprotocol/server-google-drive |
| Git | Git operations — log, diff, commit, branch management | @modelcontextprotocol/server-git |
| Memory | Persistent key-value knowledge graph across conversations | @modelcontextprotocol/server-memory |
Beyond the official set, hundreds of community-built MCP servers cover everything from Notion and Linear to AWS and Docker. The MCP ecosystem grew faster than almost anyone expected after the November 2024 launch.
The fastest path is Claude Code with the filesystem server. This gives Claude read/write access to a directory you specify — useful for any project work.
Prerequisites: Node.js installed (the server runs via npx).
In your terminal:
claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem ~/Documents/projectsThat’s it. Open a Claude Code session. Claude can now list, read, write, and search files inside ~/Documents/projects. Try: “List all Python files in this directory and summarize what each one does.”
For Claude Desktop, edit the claude_desktop_config.json file directly (see format above), then restart the app.
A few things worth understanding before you build on MCP:
MCP servers don’t persist between conversations. Each Claude session starts fresh. If you need state persistence, you need a server with its own storage layer (the Memory server handles this specifically).
MCP doesn’t bypass Claude’s safety guidelines. Claude still decides whether to execute a tool call based on safety and ethics reasoning. Connecting a filesystem server doesn’t give Claude unlimited license to delete files — Claude will still confirm before destructive operations.
Subprocess MCP servers are local. The stdio transport runs servers on your machine. This means they only work when you’re running Claude Code locally. For remote or team-shared access, you need HTTP/SSE transport with a hosted server.
MCP servers have real permissions. The filesystem server can read and write files. The GitHub server can push code to your repos. The Postgres server can run SQL queries.
Apply the principle of least privilege:
/repo for private repos, not org-level admin).claude/settings.json — use env var references insteadMCP servers run with the permissions of the user running Claude. If something goes wrong with a tool call, it can have real consequences. The upside: everything runs locally and through your own credentials — there’s no MCP cloud intermediary with access to your data.
The full power of MCP shows up in Claude Code’s multi-step agentic mode. When Claude Code has access to git, a filesystem, a browser, and a search tool simultaneously, it can execute workflows like:
Each of these steps would require a separate tool in a traditional automation stack. With MCP, Claude orchestrates all of them within a single session, using whatever servers are available.
This is what makes MCP the infrastructure layer for agentic AI — not a feature, but the foundation that makes complex AI-driven workflows possible.
Related on Tygart Media: Claude MCP · Skills vs MCP vs plugins · how to use Claude.
What does MCP stand for?
Model Context Protocol. It’s an open standard for connecting AI models to external tools, data sources, and services through a standard client-server interface.
Who created MCP?
Anthropic created MCP and released it as an open standard in November 2024. The specification and reference servers are open-source on GitHub. While Claude is the primary client, other AI systems can implement MCP clients too.
Do I need to install MCP to use Claude?
No. Claude works without any MCP servers. MCP is an extension layer — you add servers when you want Claude to access specific external systems. Claude Code also ships with a set of built-in tools (file operations, bash, web fetch) that don’t require MCP installation.
Is MCP available on Claude.ai (the web app)?
MCP server support is primarily in Claude Desktop and Claude Code. The Claude.ai web interface has its own tool integrations (web search, document analysis) but doesn’t support custom MCP servers in the same way.
What’s the difference between MCP tools and Claude’s native tools in Claude Code?
Claude Code’s native tools (Read, Write, Bash, Glob, Grep, WebFetch, Agent) are built into the application and don’t require a separate server process. MCP servers are external — they run as subprocesses or network services that Claude Code connects to. Both expose tools that Claude can call; the mechanism for loading them is different.
How do I build my own MCP server?
Anthropic provides official SDKs for building MCP servers in TypeScript, Python, Go, and other languages. The TypeScript SDK (@modelcontextprotocol/sdk) is the most mature. Start with Anthropic’s MCP documentation and the reference server implementations on GitHub as templates.
Last verified: June 12, 2026. MCP specification and server ecosystem evolve quickly — check the official Anthropic MCP documentation for the current spec.
Anthropic released Claude Fable 5 on June 9, 2026 — and it’s the most capable model the company has ever made publicly available. After tracking every Claude release since the original 100K context window dropped, I can say this one is different. Fable 5 isn’t just an incremental update. It’s Anthropic’s Mythos-class model — the one they’d been keeping restricted — now opened up to anyone with an API key or a Claude subscription.
Here’s what you need to know: the pricing, the benchmarks, and the specific decision framework for when to use Fable 5 versus sticking with Opus 4.8.
Quick answer: Fable 5 costs $10/$50 per million input/output tokens (2x the cost of Opus 4.8). It outperforms Opus 4.8 significantly on complex coding, long-horizon tasks, and scientific research. Use Fable 5 when quality on hard problems justifies the cost. Use Opus 4.8 for high-volume, well-scoped, routine work.
Current lineup note (October 2026): Fable 5.1 is the current Fable SKU at the same $10/$50 headline rates (cache reads $0.25/MTok). Current Opus is Opus 5.5 at $4/$20; Opus 4.8 remains listed as legacy. The June 2026 comparisons below are the launch record for Fable 5.
Claude Fable 5 (claude-fable-5) is Anthropic’s first publicly available Mythos-class model. The Mythos line is Anthropic’s highest capability tier — models that were previously restricted to research and select enterprise partners because of their raw power. Fable 5 is the version Anthropic deemed safe enough to release broadly.
The name shift (from the Opus/Sonnet/Haiku tier naming) signals something intentional. Fable 5 sits above the Opus line entirely. It’s a new ceiling.
Key specs:
| Model | Input (per MTok) | Output (per MTok) | Context |
|---|---|---|---|
| Claude Fable 5 | $10.00 | $50.00 | 1M tokens |
| Claude Opus 4.8 | $5.00 | $25.00 | 1M tokens |
| Claude Sonnet 4.6 | $3.00 | $15.00 | 1M tokens |
| Claude Haiku 4.5 | $1.00 | $5.00 | 200K tokens |
Fable 5 costs exactly 2x Opus 4.8 on API. On subscription plans (Pro, Max, Team, Enterprise seat-based), Fable 5 is included at no extra cost through June 22, 2026.
The free-until-June-22 window matters if you’re evaluating whether to route your workloads to Fable 5. Use that window to benchmark it against your actual tasks before the 2x cost kicks in.
The benchmarks that matter most are the ones that measure what the model can do on real engineering work, not trivia:
| Benchmark | Claude Fable 5 | Claude Opus 4.8 | Delta |
|---|---|---|---|
| SWE-bench Verified | 95.0% | 88.6% | +6.4 pts |
| SWE-bench Pro | 80.0% | 69.2% | +10.8 pts |
| FrontierCode | 29.3% | 13.4% | ~2.2x |
| Senior Engineer benchmark | 91/100 | ~63/100 | +45% absolute |
The Senior Engineer benchmark is the one I find most telling. It’s designed to be hard for people who write code for a living — and Fable 5 scores 45 percentage points higher than Opus 4.8. That gap is significant enough that it changes the calculus for serious engineering work.
I’ve been routing tasks between models for long enough to have a framework. Here’s how I think about it:
Use Fable 5 when:
Use Opus 4.8 when:
The smart routing strategy: Fable 5 for the hard jobs, Opus 4.8 for the rest. Don’t use Fable 5 as your default model — the cost and latency delta aren’t worth it for routine tasks.
Two limitations that don’t get enough coverage:
1. Safety classifier routing. Fable 5 includes enhanced safety classifiers. For prompts touching cybersecurity, biology, chemistry, and distillation, those classifiers route the request to a Claude Opus 4.8 fallback. You pay Fable 5 API rates ($10/$50) but get Opus 4.8 output. If your use case is in these domains, Fable 5 is not the upgrade it appears to be.
2. Data retention requirement. Fable 5 carries a mandatory 30-day data retention policy — Anthropic needs retained prompts and outputs to operate the safety classifiers. Claude Opus 4.8 is available under zero data retention (ZDR). If your use case requires ZDR (healthcare, legal, finance with strict data handling), stick with Opus 4.8 until Anthropic updates Fable 5’s data policy.
Claude Fable 5 is generally available as of June 9, 2026 on:
claude-fable-5)Subscription access (free through June 22, 2026): Claude Pro ($20/mo), Max 5x ($100/mo), Max 20x ($200/mo), Team, and seat-based Enterprise plans all include Fable 5 access at no extra charge during the launch window. After June 22, the plan-tier access picture may change — check Anthropic’s pricing page for updates.
Before Fable 5, the Claude decision tree was straightforward:
Now it’s:
The introduction of a model tier above Opus 4.8 doesn’t replace the existing lineup — it creates a new ceiling for the work that genuinely needs it.
Related on Tygart Media: Fable 5 complete guide · Fable 5 firsthand · how to use Claude.
Is Claude Fable 5 better than Opus 4.8?
For complex coding, multi-stage tasks, and long-horizon work: yes, significantly. On SWE-bench Pro, Fable 5 scores 80.0% vs Opus 4.8’s 69.2% — a 10+ point gap. For routine, well-scoped tasks: the gap narrows enough that Opus 4.8’s 2x cost advantage makes it the smarter choice.
What is the Claude Fable 5 API model ID?
claude-fable-5. This is the API string you pass to model in your API calls.
Does Fable 5 cost more than Opus 4.8?
Yes — exactly 2x. Fable 5 is $10 input / $50 output per million tokens. Opus 4.8 is $5/$25. Through June 22, 2026, Fable 5 is included in Claude subscription plans at no extra cost.
Can I use Claude Fable 5 for free?
On Pro, Max, Team, and Enterprise subscription plans, yes — through June 22, 2026. API access is metered at $10/$50 per MTok from day one.
Does Claude Fable 5 support zero data retention (ZDR)?
No. Fable 5 carries a mandatory 30-day data retention requirement. If your use case requires ZDR, use Claude Opus 4.8, which supports it.
What’s the difference between Claude Fable 5 and Claude Mythos 5?
Mythos 5 is Anthropic’s fully restricted research model — not publicly available. Fable 5 is the Mythos-class model that Anthropic has prepared for general availability, with safety classifiers and the 30-day retention policy. You can think of Fable 5 as “Mythos for the real world.”
Last verified: October 5, 2026. Anthropic pricing and availability subject to change — check Anthropic’s pricing page for current rates.
Last verified: September 26, 2026 (Pacific Time)
Updated October 28, 2026: Made infographic diagrams clickable to open full-size images.
Direct Answer (September 2026): To obtain an Anthropic API key: 1) Register at console.anthropic.com, 2) Navigate to Settings > Plans & Billing and deposit $5+ for Tier 1 activation, 3) Go to ‘API Keys’, click ‘Create Key’, and copy your secure sk-ant-api03-... key token.
macOS / Linux:
export ANTHROPIC_API_KEY="sk-ant-YOUR_KEY_HERE"
Windows (PowerShell):
setx ANTHROPIC_API_KEY "sk-ant-YOUR_KEY_HERE"Replace YOUR_KEY_HERE with the key shown once at creation — Anthropic never shows it again.
An Anthropic API key is the secret token that authenticates your requests to Claude models over the API. It starts with sk-ant-, is created in the Anthropic Console at console.anthropic.com under API Keys → Create Key, and is displayed exactly once — requests only succeed after you add a payment method.
Official links:Create a key (console) · API docs · API rates · Help center
Quick answer: sign in at console.anthropic.com (it now redirects to the same developer console as platform.claude.com), add a payment method under Settings → Billing, click API Keys → Create Key, name it, and copy it immediately – Anthropic shows the key exactly once. Keys start with sk-ant-. The whole process takes about five minutes.
Below is the full walkthrough, where to put the key so it doesn’t leak, the newer no-static-key option most tutorials haven’t caught up with, and the errors that account for nearly every failed first request. For the full reference – pricing tiers, key rotation, security, and workspace and organization keys – see our Anthropic API key reference and management guide.
One distinction that confuses almost everyone: a Claude.ai subscription is not API access. Claude Pro, Max, and Team plans cover the Claude apps (web, desktop, mobile). The API is billed separately, by usage, through the developer console. You can have either one without the other – see our complete Claude pricing guide for how the two systems differ.
Go to console.anthropic.com – Anthropic’s developer console. (Both console.anthropic.com and platform.claude.com land in the same place in 2026; older tutorials treat them as different sites.) Sign up with email, Google, or SSO, and answer the brief onboarding questions about whether you’re an individual or an organization. For a tour of everything inside the console, see our Anthropic Console guide.
In the console, open Settings → Billing and add a credit card (self-serve accounts typically purchase prepaid usage credits). Skipping this step is the #1 reason a brand-new key returns errors – the key exists, but requests are rejected until the account can be billed.
Create the key in the console ?
Click API Keys in the left sidebar (direct link: platform.claude.com/settings/keys), then Create Key. Give it a descriptive name like my-app-dev – future you will thank present you when it’s time to rotate or revoke. If your organization uses multiple workspaces, note that keys are scoped to a workspace: the key only sees resources in the workspace it was created in.
The key is displayed exactly once. It starts with sk-ant- followed by a long string. Copy it straight into a password manager, a .env file, or your secrets manager. If you lose it, there is no way to view it again – you revoke it and create a new one (takes a minute, harms nothing).
Set it as an environment variable named ANTHROPIC_API_KEY – every official Anthropic SDK reads that variable automatically, so your code never contains the key:
export ANTHROPIC_API_KEY=sk-ant-...setx ANTHROPIC_API_KEY "sk-ant-..."client = anthropic.Anthropic() – no key argument neededconst client = new Anthropic() – sameNever hardcode the key in source files, never commit it to a repository, and never paste it into a system prompt or chat message. Leaked Anthropic keys get scraped and drained like any other credential.
Newer than most guides: Anthropic’s CLI can authenticate without any static key. Run ant auth login and a browser window authorizes a short-lived OAuth profile on your machine – the SDKs and Claude Code pick it up automatically, and there is no permanent secret to leak or rotate. For CI servers and production workloads, Workload Identity Federation serves the same purpose. If you’re setting up a personal development machine in 2026, this is arguably the better default; create a static key when you need one for a deployed service.
One request confirms everything works (Haiku keeps the test nearly free):
curl https://api.anthropic.com/v1/messages
-H "x-api-key: $ANTHROPIC_API_KEY"
-H "anthropic-version: 2023-06-01"
-H "content-type: application/json"
-d '{"model": "claude-haiku-4-5", "max_tokens": 32, "messages": [{"role": "user", "content": "Say hello"}]}'A JSON response with a content array means you’re live.
ANTHROPIC_API_KEY and ANTHROPIC_AUTH_TOKEN are set, the SDK sends both and the API rejects the request – unset one.retry-after header; official SDKs retry automatically. For tier details and fixes, see our Claude rate limits guide.Is the Anthropic API free? No – it’s usage-priced per million tokens with no permanent free tier (current rates in our Claude pricing guide and API token rates schedule, including the September 2026 lineup).
Where do I find my existing API key? You can’t – Anthropic shows keys only at creation. Revoke the old one and create a replacement.
Where is the API Keys page in console.anthropic.com? Sign in at console.anthropic.com, choose API Keys in the left navigation — or go straight to platform.claude.com/settings/keys — then click Create Key.
Does my Claude Pro or Max subscription include an API key? No. App subscriptions and API billing are separate systems; an API account starts at $0 and bills per token used.
Lineup currency (Sept 2026, verified): Sonnet 5 ($2/$10), Opus 5.5 ($4/$20), Haiku 4.5 ($1/$5), Fable 5.1 ($10/$50). Legacy (still listed): Opus 4.8 ($5/$25), Sonnet 4.6 ($3/$15).
>Part of the complete guide: Claude Pricing, Plans & Limits
Last verified: August 26, 2026 (Pacific Time)May 2026 edition covered the Opus 4.8 launch, the SpaceX compute deal, and Managed Agents memory features.
Direct Answer (August 2026 Update): Major mid-2026 Anthropic releases introduced Claude Fable 5, native Model Context Protocol (MCP) tool integration in Claude Desktop, extended 1M context beta on Vertex AI/AWS Bedrock, and decoupled Enterprise seat pricing.
June 2026 is one of the biggest months for Anthropic since the Claude 4 launch: a new top-tier model is generally available, two workhorse models retire in four days, and Managed Agents can now run inside infrastructure you control. Here is everything that changed, with dates and migration paths.
Anthropic released Claude Fable 5 on June 9, 2026 — the public version of what had been known as its Mythos-class model tier. It is positioned as a new tier above Opus, and it is Anthropic’s most capable generally available model. According to CNBC’s launch coverage, Fable 5 scored more than 10% higher than Claude Opus 4.8 on some benchmarks, with exceptional performance across software engineering and knowledge work. Anthropic credits new safeguards that block responses in specific high-risk areas for making a broad release possible.
The practical details developers need:
claude-fable-5temperature, top_p, top_k, and budget_tokens are not accepted, and unlike Opus 4.8, an explicit thinking: {type: "disabled"} returns a 400 error. Omit the thinking parameter entirely if you do not want it.For where Fable 5 sits against every other Claude model on price, see our continuously updated Claude AI pricing guide, and our complete Fable 5 guide for capabilities and use cases.
If you are still calling claude-opus-4-20250514 or claude-sonnet-4-20250514, those models retire from the Claude API on June 15, 2026. Requests after retirement return 404 errors. The drop-in replacements:
claude-opus-4-20250514 → claude-opus-4-8claude-sonnet-4-20250514 → claude-sonnet-4-6Note that both replacements use adaptive thinking rather than manual thinking budgets, and the 4.6+ models reject assistant-turn prefills — so this is a small migration, not just a string swap. Anthropic also deprecated Claude Opus 4.1 this month, with API retirement scheduled for August 5, 2026 — worth adding to your migration calendar now.
| Model | Model ID | Context | Max output | Input $/1M | Output $/1M |
|---|---|---|---|---|---|
| Claude Fable 5 | claude-fable-5 |
1M | 128K | $10.00 | $50.00 |
| Claude Opus 4.8 (legacy — still listed) | claude-opus-4-8 |
1M | 128K | $5.00 | $25.00 |
| Claude Opus 4.8 (legacy — still listed) | claude-opus-4-8 |
1M | 128K | $5.00 | $25.00 |
| Claude Sonnet 4.6 (legacy — still listed) | claude-sonnet-4-6 |
1M | 64K | $3.00 | $15.00 |
| Claude Haiku 4.5 | claude-haiku-4-5 |
200K | 64K | $1.00 | $5.00 |
Opus 4.7, 4.6, 4.5, and 4.1 and Sonnet 4.5 remain active for pinned workloads. We track which model is current at any moment in our current Claude model version reference.
Claude Managed Agents — Anthropic’s server-managed agent platform — can now execute tools inside a sandbox you control. The agent loop still runs on Anthropic’s orchestration layer, but bash commands, file operations, and code execution happen in your own container, behind your own firewall, with your own egress rules. Your worker long-polls Anthropic’s work queue over outbound-only connections; Anthropic never dials into your network. Managed Agents can also now connect to private MCP servers, which matters for any organization whose internal tools are not on the public internet.
For regulated industries — healthcare, finance, legal — this is the missing piece that lets you adopt hosted agents while keeping data residency: files and tool output never leave infrastructure you own.
Claude Code shipped a steady stream of updates in June: nested sub-agents (agents can now spawn their own sub-agents for deeper task decomposition), smarter model and region handling, a new plugin search, and improved Chrome, VS Code, and terminal workflows.
Anthropic released more than 20 new legal MCP connectors and 12 practice-area plugins, covering research, contracts, discovery, matter management, and legal aid. The pattern to note: Anthropic is increasingly shipping vertical integration bundles rather than leaving connector-building entirely to the ecosystem.
Anthropic announced Claude Corps, a $150 million fellowship program that will embed roughly 1,000 trained fellows inside nonprofit organizations for a year to help them use AI effectively. Applications and program details are rolling out through Anthropic’s newsroom.
Claude support is coming to Apple’s Foundation Models framework on iOS 27, iPadOS 27, macOS 27, and visionOS 27 — meaning third-party Apple developers will be able to call Claude through Apple’s native AI framework rather than integrating the API directly.
claude-opus-4-8 before then.💼 Deploying Claude or AI Infrastructure in Your Business?
At Tygart Media, we engineer custom Model Context Protocol (MCP) servers, multi-model content pipelines, and AI operational systems. Explore our Claude AI Team Implementation Services or check out our complete Restoration Operations & AI Kit.
Today was the kind of day where you can feel the road forking under your tires. Not because one thing happened — because eight things happened simultaneously, and if you squint at the pattern, they all point the same direction: AI just stopped being a product category and started being infrastructure. The plumbing layer. The thing you build on top of, not the thing you buy.
I’ve been building with Claude since the Haiku days. I run it 12 hours a day across 20+ WordPress sites, a five-site knowledge cluster on Google Cloud, and a custom schema engine I shipped yesterday. When the landscape shifts, I don’t read about it on TechCrunch — I feel it in the tooling. And today, the tooling lurched forward in a way that matters.
Here’s the daily signal.
Anthropic launched Claude Fable 5 yesterday — the first publicly available Mythos-class model, a tier above Opus. Pricing is $10 per million input tokens and $50 per million output tokens. It’s the most capable model Anthropic has ever released to the general public, state-of-the-art on nearly every benchmark, and it comes with a fascinating constraint: queries on certain topics automatically route to Opus 4.8 instead, triggering in less than 5% of sessions. Anthropic is essentially saying: here’s the most powerful thing we’ve ever built, and we’ve installed guard rails at the edge cases where power becomes risk.
For agencies and small business operators, the practical read is this: Fable 5 is included on Pro, Max, Team, and Enterprise plans through June 22 at no extra cost. After that, it comes off the subscription tiers. If you’re building workflows that depend on Mythos-class reasoning, you have 12 days to test whether the capability justifies the API cost — or whether Opus and Sonnet handle your actual use cases just fine.
The real signal isn’t the model itself. It’s that Anthropic also doubled Cowork limits at no charge and shipped Claude Managed Agents in public beta. They’re not just selling you a smarter model — they’re selling you an operating system for delegating work to AI. That’s a fundamentally different product than a chatbot.
While the tech press was writing headlines about Fable 5, I was elbow-deep in the kind of work that actually turns these models into business value. Yesterday, across a 14-hour session, my team — which at this point is me and a fleet of Claude instances — shipped three things that matter more to my clients than any benchmark score:
1. bcesg-knowledge-api v1.5.0 — a custom WordPress plugin I built and deployed across BCESG.org that outputs a JSON-LD @graph array containing Article, FAQPage, Organization, WebPage, BreadcrumbList, Person (author), and speakable schema — all generated from 13 custom meta fields. This isn’t a schema plugin you install from the WordPress directory. It’s a purpose-built schema engine designed for one thing: making every page on the site machine-readable enough that AI systems cite it as an authoritative source. That’s Generative Engine Optimization at the infrastructure level, not the content level.
2. WordPress 7.0 across the entire knowledge cluster. All five sites — bcesg.org, restorationintel.com, riskcoveragehub.com, continuityhub.org, and healthcarefacilityhub.org — upgraded from WP 6.9.4 to 7.0. Why does this matter? Because WordPress 7.0 ships the Abilities API: agent-to-agent communication endpoints. That means my Claude-powered content pipelines can now negotiate directly with WordPress about what they’re allowed to do, without me acting as the middleware. The cluster just became AI-native infrastructure.
3. The stack around it. RankMath SEO installed with the schema module deliberately disabled — because the custom plugin handles schema, and two schema systems fighting each other is worse than none at all. IndexNow for instant search engine notification on every publish and update. Microsoft Clarity for behavioral analytics so I can see what humans actually do when they land on AI-optimized content.
And here’s the detail that would have been impossible to explain six months ago: the peer review on the bcesg-knowledge-api plugin was done by Claude Fable 5 reviewing the code that Claude Opus wrote. AI reviewing AI’s code. In production. On a live WordPress cluster. That’s not a demo — that’s Tuesday.
OpenAI filed a confidential S-1 with the SEC. They’re going public. Meanwhile, Anthropic hit a $965 billion valuation. These two facts, side by side, tell you everything about where the money thinks AI is going: it’s going to be the most valuable infrastructure layer since cloud computing, and the market is pricing it that way before most businesses have figured out how to use it.
For small business owners and agency operators, this isn’t abstract finance news. It means the tools you’re using today — Claude, GPT, Gemini — are backed by companies with enough capital to keep shipping improvements for years. The platform risk isn’t that these companies disappear. The platform risk is that you don’t build on them fast enough and your competitors do.
A UC San Diego study published in PNAS confirmed that OpenAI’s GPT-4.5 and Meta’s Llama-3.1-405B both passed a standard three-party Turing test — with GPT-4.5 being identified as human 73% of the time when given a persona prompt, significantly more often than actual human participants. This has been treated as a milestone headline, and it is one, but the practical implication is more subtle than “AI can fool humans.”
What it actually means: the content quality bar just moved permanently. If AI can produce text that’s indistinguishable from a human expert, then the only content that wins is content with something AI can’t fake — lived experience, proprietary data, operational specifics, the kind of “I shipped this yesterday and here’s what happened” detail that no model can generate from training data. This is why I write The Signal as field notes, not as analysis. Analysis can be generated. Field notes from the arena cannot.
Google shipped the Chrome WebMCP API in Origin Trial for Chrome 149 through 156. The Model Context Protocol — the same protocol that lets Claude connect to external tools, databases, and APIs — is now a browser-native capability. Web applications can expose structured tool interfaces that AI models call directly.
This is a bigger deal than it sounds. Right now, when Claude interacts with a web application, it’s either through a dedicated MCP server or through browser automation (clicking pixels on a screen like a human would). WebMCP means any web app can define a structured API surface that AI agents consume natively. For agencies building client tools, this is the moment your internal dashboards and client portals become AI-ready without a full backend rewrite.
If you’re running WordPress sites — and 43% of the web is — this has direct implications for how AI agents interact with your content management layer. The gap between “website” and “AI-accessible knowledge base” just narrowed dramatically.
Elon Musk’s xAI, home of Grok, is increasingly looking less like an AI model company and more like a GPU real estate investment trust. They’re partnering with both Anthropic and Google to provide compute infrastructure. This is the clearest sign yet that the AI industry is stratifying into two distinct layers: model companies (who build the brains) and infrastructure companies (who build the data centers those brains run in).
For builders, this is good news. More compute supply means more pricing competition means lower API costs over time. The $10/$50 per million tokens for Fable 5 today will look expensive in 18 months.
HashiCorp announced Boundary for agentic AI — access security specifically designed for AI agents that need to authenticate across multiple systems. And MemPalace shipped a local-first AI memory system with 96.6% recall accuracy and 29 MCP tools for Claude Code.
These aren’t headline products. They’re infrastructure connective tissue. When AI agents can securely authenticate across your entire tool stack (HashiCorp Boundary) and maintain persistent memory across sessions (MemPalace), you stop using AI for one-off tasks and start using it as a persistent operational layer. That’s the transition my agency is making right now — from “Claude helps me write articles” to “Claude runs the content pipeline while I focus on strategy.”
Here’s the pattern I see when I lay these signals side by side:
Lane 1: The AI product lane. This is where most people are. They use ChatGPT to draft emails. They ask Claude to summarize documents. They treat AI as a productivity tool, like a faster Google or a better autocomplete. This lane is getting crowded, commoditized, and — with the Turing test results — increasingly indistinguishable from one provider to the next.
Lane 2: The AI infrastructure lane. This is where the alpha is. Custom schema engines. Agent-to-agent communication via the WordPress Abilities API. Browser-native MCP endpoints. Persistent AI memory. Secure multi-system authentication for autonomous agents. This lane is where you stop using AI and start building on AI — where it becomes the foundation layer of your operations, not an add-on.
The gap between these two lanes is widening every day. Today’s eight signals all point the same direction: toward a world where the businesses that win aren’t the ones that use AI tools the best, but the ones that build AI infrastructure the fastest.
I’m building in Lane 2. Yesterday it was a custom schema engine and a WordPress 7.0 cluster upgrade. Today it’s field-testing Fable 5 as a code reviewer. Tomorrow it’ll be whatever the next signal demands.
The question isn’t whether AI is going to transform your industry. That’s settled. The question is whether you’re in the arena building the infrastructure, or on the sidelines reading about people who are.
— Will Tygart, Tygart Media
Claude Fable 5 is Anthropic’s first publicly available Mythos-class AI model, released June 9, 2026. It sits a tier above Claude Opus in capability, priced at $10 per million input tokens and $50 per million output tokens. Fable 5 is state-of-the-art on nearly all tested benchmarks and includes built-in safeguards that route certain queries to Opus 4.8, triggering in less than 5% of sessions. It’s available free on subscription plans through June 22, 2026.
The Chrome WebMCP API, now in Origin Trial for Chrome versions 149 through 156, brings the Model Context Protocol natively into the browser. This allows web applications to expose structured tool interfaces that AI models can call directly — eliminating the need for dedicated backend integrations or browser automation. For businesses running web-based tools, dashboards, or WordPress sites, this means your existing applications can become AI-accessible without a full rebuild.
The WordPress 7.0 Abilities API provides agent-to-agent communication endpoints, allowing AI-powered systems to negotiate capabilities and permissions directly with a WordPress installation. This transforms WordPress from a content management system into AI-native infrastructure where automated pipelines can query what operations they’re authorized to perform without human middleware.
A UC San Diego study published in PNAS found that OpenAI’s GPT-4.5 and Meta’s Llama-3.1-405B both passed a standard three-party Turing test in 2026 — GPT-4.5 was identified as human 73% of the time with persona prompting. For content creators, this permanently raises the quality bar — the only content that wins is content with elements AI cannot fake: lived experience, proprietary data, operational specifics, and first-person field reports that no model can generate from training data alone.
Generative Engine Optimization is the practice of structuring web content so AI systems — including ChatGPT, Claude, Gemini, Perplexity, and Google AI Overviews — cite, reference, and recommend it. GEO involves entity enrichment, structured data (JSON-LD schema), authoritative citations, and machine-readable formatting. Unlike traditional SEO which targets search engine crawlers, GEO targets the large language models that increasingly mediate how users discover information.
Start by moving from Lane 1 (using AI as a productivity tool) to Lane 2 (building AI into your operational infrastructure). Practical first steps include implementing structured data and schema markup on your website, setting up AI-optimized content pipelines, ensuring your site is crawlable by AI systems via protocols like LLMS.txt, and testing agentic workflows where AI handles multi-step operational tasks autonomously rather than single-prompt interactions.
A custom schema engine is a purpose-built WordPress plugin that generates structured data (JSON-LD) tailored to specific business objectives — in this case, AI citation optimization. Unlike off-the-shelf schema plugins that generate generic markup, a custom engine outputs precisely the entity relationships, author signals, and speakable content markers that AI systems use when deciding which sources to cite. The bcesg-knowledge-api plugin generates a seven-type @graph array from 13 custom meta fields, providing a level of control that no general-purpose plugin offers.
When Claude Fable 5 peer-reviewed code written by Claude Opus for a production WordPress plugin, it demonstrated a mature AI development workflow where different model tiers serve different roles — one for generation, another for quality assurance. This mirrors human development practices (developer writes, senior reviews) but at machine speed and cost. It’s a practical example of how AI agent collaboration is already operational in real business infrastructure, not just research demos.
The Signal is published daily on Tygart Media by Will Tygart. Each edition distills the day’s most consequential AI, search, and technology developments into actionable intelligence for agencies, small business operators, and builders shipping real AI infrastructure.
Everything you need to know about Anthropic’s new frontier tier — pricing, context window, model comparisons, and how to route the right work to the right model.
Claude Fable 5 is Anthropic’s new frontier model tier — positioned above Opus in the lineup and designed for tasks where raw capability, extended reasoning depth, and massive context handling matter more than cost. Where Opus 4.8 set the bar for complex multi-step reasoning, Fable 5 raises it with a 1-million-token context window, enhanced agentic autonomy, and improved performance on long-horizon software engineering, research synthesis, and cross-domain analysis tasks.
The “Fable” naming signals a new generation of model architecture rather than an incremental update. Anthropic positions it as the model you reach for when a task exceeds what Opus can do reliably — not as a replacement for Opus, Sonnet, or Haiku in their respective cost tiers.
Here’s how the complete 2026 Claude lineup stacks up across every dimension that matters for production usage:
| Model | Input $/M | Output $/M | Context | Max Out | Vision | Tool Use | Extended Think | Best For |
|---|---|---|---|---|---|---|---|---|
| ◆ Fable 5 | $10 | $50 | 1M | 32K | ✓ | ✓ | ✓ Deep | Max-capability tasks, 1M+ context |
| ◆ Opus 4.8 | $5 | $25 | 200K | 32K | ✓ | ✓ | ✓ | Complex reasoning, agentic workflows |
| ◆ Sonnet 4.6 | $3 | $15 | 200K | 16K | ✓ | ✓ | ✓ | Production apps, content at scale |
| ◆ Haiku 4.5 | $1 | $5 | 200K | 8K | ✓ | ✓ | — | High-volume, latency-sensitive tasks |
Prices are per million tokens. Cache read is 90% cheaper than standard input across all models. Batch API provides an additional 50% discount on both input and output.
| Capability | Fable 5 | Opus 4.8 | Sonnet 4.6 | Haiku 4.5 |
|---|---|---|---|---|
| Full codebase analysis (>500K tokens) | ✓ Native | ⚠ Chunked | ✗ | ✗ |
| Extended thinking / chain-of-thought | ✓ Deep | ✓ | ✓ | ✗ |
| Multi-step agentic orchestration | ✓ Best | ✓ | Good | Limited |
| Computer use | ✓ | ✓ | ✓ | ✗ |
| MCP tool integration | ✓ | ✓ | ✓ | ✓ |
| Prompt caching | ✓ | ✓ | ✓ | ✓ |
| Batch API (50% discount) | ✓ | ✓ | ✓ | ✓ |
| PDF / document analysis | ✓ | ✓ | ✓ | Limited |
| Real-time streaming | ✓ | ✓ | ✓ | ✓ |
| Structured JSON output | ✓ | ✓ | ✓ | ✓ |
Estimate your monthly API spend across the full model lineup. Enter your token volumes below — the calculator models prompt caching and Batch API discounts automatically.
Answer three questions to get a model recommendation tailored to your use case.
These are real production workflows mapped to the right tier — built from running Claude in content operations, publishing automation, and knowledge management at scale. No hypotheticals.
Smart model routing is where API costs get controlled. Here’s a real-world comparison of a mixed content-and-automation workload at scale — routed vs running everything on Fable 5.
| Workload | Monthly Volume | Routed Model | Routed Cost | All-Fable 5 Cost | Savings |
|---|---|---|---|---|---|
| SEO metadata batch refresh | 750 posts/mo | Haiku 4.5 + Batch | $1.20 | $18.75 | 93% less |
| Article drafting | 90 articles/mo | Sonnet 4.6 | $8.10 | $67.50 | 88% less |
| Agentic worker runs | 200 runs/mo | Opus 4.8 | $22.50 | $45.00 | 50% less |
| Full-site portfolio audits | 4 audits/mo | Fable 5 | $24.00 | $24.00 | — |
| Total | — | Routed | $55.80 | $155.25 | 64% less |
Two discount mechanisms compound independently:
See our Claude context window guide for more on how to structure prompts to maximize cache hit rates.
claude-fable-5-20260101 (check the Anthropic documentation for the exact identifier). It supports the same API surface as the rest of the Claude family — streaming, tool use, prompt caching, vision, the Batch API, and MCP server integration. Access requires an Anthropic API account with Fable 5 enabled on your usage tier.
We run Claude in production every day. These are the guides that come from using it, not just writing about it.
Related on Tygart Media: Claude Fable 5 overview · Fable 5 firsthand · Claude pricing.
Direct Answer (9 September 2026): Claude Cowork is the desktop workspace in the Claude app. It works on local files and apps you approve. It is not Chat and it is not the Chrome extension. Use Chat when the job is a conversation. Use Cowork when the job is a folder, a document, or a multi-step desktop workflow. It ships on Pro, Max, Team, and Enterprise — not Free.
Claude Cowork lets Claude work on the machine, not just talk about the work. Last verified 9 September 2026.
These belong here and on the limits desk:
In the desktop app Claude can read folders you grant, write documents, run Skills, and call MCP tools. Actions ask for approval. It is not a silent screen-scraper.
File management, document creation (DOCX, XLSX, PPTX, PDF), data cleanup, and cross-app handoffs you approve. It is not a replacement for Claude Code on a repo.
Code is the terminal path for developers. Cowork is the visual path for operators. Both sit on Pro / Max / Team / Enterprise. Matrix: Cowork vs Code vs Agent SDK.
Install the Claude desktop app. Open a Cowork session. Grant the folder. Describe the job. Approve the first file write before you let it run a batch.
Desktop workspace in the Claude app for files and local workflows.
Yes. Pro, Max, Team, Enterprise. Not Free.
Only apps and folders you grant.
No.
Related: Chrome extension · limits and errors · pricing · reference hub.
Updated November 2, 2026 — added direct answers on Claude Pro vs Claude Max pricing and limits, sourced from Anthropic’s published pricing.
Last verified: October 2, 2026 (Pacific).
Updated October 28, 2026: Made infographic diagrams clickable to open full-size images.
Claude Pro costs $20/month. Claude Max costs $100 or $200/month. The question everyone asks: is 5x or 20x the price actually worth it? The answer depends entirely on how you use Claude. This comparison breaks down the real differences — not the marketing bullet points — so you can make an informed decision.
Pro at $20/month ($17/month annual) includes Claude Code, Claude Cowork, unlimited Projects, Research mode, access to additional models, and Claude for Microsoft 365 and Outlook. The usage allowance is described as “more usage” compared to Free — in practice, this means you can have sustained conversations throughout a workday without hitting limits under normal use. Most professionals who use Claude as a daily tool — a few hours of active conversation per day — find Pro sufficient.
Max comes in two tiers. The $100/month tier gives approximately 5x the usage of Pro. The $200/month tier gives approximately 20x. Beyond the usage multiplier, Max adds three concrete features: higher output limits for all tasks (longer responses, more complex code generation), early access to advanced Claude features before they reach Pro users, and priority access during high-traffic periods (you skip the queue).
Direct answer: Max is now the only individual plan that includes Anthropic’s Fable models. On Pro, every Fable token runs on usage credits; on Max 5x and 20x, Fable is included up to half the weekly usage pool. If your work benefits from Fable — long-horizon agent loops with heavy cache reuse — this alone can decide the plan. Our Fable 5 pricing guide breaks down the $10/$50 headline rates and the 75% cache-read cut that Fable 5.1 brought on September 1.
Heavy Claude Code users: If you spend 4+ hours per day actively using Claude Code for development — not just coding, but running extended agent sessions, multi-file refactoring, and complex debugging — you’ll likely hit Pro limits. Max 5x removes this friction. Content production teams: If you’re producing 10+ pieces of content per day through Claude, the usage adds up fast. Researchers and analysts: Extended research sessions with multiple deep-dive conversations consume significant tokens. Anyone who hits Pro limits regularly: If you see the “usage limit reached” message more than once or twice per week, Max pays for itself in recovered productivity.
Most individual professionals: If you use Claude for 1-3 hours per day with normal conversation patterns, Pro is plenty. Occasional users: If Claude is one of many tools in your workflow rather than the central one, Pro is more than enough. Budget-conscious users: At $20/month, Pro delivers extraordinary value. The jump to $100/month should be justified by measurable productivity gains. Users who haven’t hit Pro limits: If you’ve never seen the usage limit message, you don’t need Max.
One newer mechanic worth knowing before you upgrade: when a paid plan hits its usage limit, usage credits keep Claude working at standard API rates instead of making you wait for the 5-hour reset window. Credits are pay-as-you-go on top of the subscription — the middle path for spiky weeks where one heavy project doesn’t justify a whole tier upgrade. If you hit Pro limits twice a month rather than twice a week, credits are usually cheaper than Max.
Max 5x costs $80/month more than Pro. If that additional usage saves you 2+ hours per week of productivity (waiting for limits to reset, or time spent on tasks you could have delegated to Claude), and your time is worth $40+/hour, Max pays for itself. Max 20x at $200/month ($180 more than Pro) needs to save roughly 4.5 hours/week to break even at $40/hour. The early access and priority features are hard to quantify financially — they matter most for users who need Claude reliably during peak demand.
Before upgrading to Max, consider whether your usage patterns can be optimized on Pro. Use Projects to maintain context instead of repeating background in every conversation. Be concise in prompts — verbose prompts consume more tokens. Use the appropriate model (Haiku for simple tasks, Sonnet for standard work, Opus for complex reasoning). Close conversations you’re done with rather than continuing indefinitely. If you’re hitting limits despite these optimizations, Max is the right move.
Claude usage limits reset on a rolling five-hour window, and paid plans add weekly limits on top of that. There is no fixed number of messages.
On claude.com/pricing, checked October 2, 2026, Free covers everyday questions. Pro includes at least 5x more usage per five-hour session than Free. Max includes 5x or 20x more usage per five-hour session than Pro. The Max card lists the plan from $100 per month and lets you choose the 5x or 20x option. Chat on the web, the desktop app, mobile, and Claude Code all draw from the same pool.
What spends the allowance is the work itself. A longer conversation, a heavier model, file creation, or research uses more of the window than a short question. Anthropic also says it may apply weekly or monthly caps, or limits on a specific model or feature, so one account does not crowd out everyone else. On the plan table, Fable is unavailable on Free, listed as usage credits on Pro, and listed as 50% of weekly limits on both Max options.
When a limit hits, the same page gives three moves: wait for the reset, move to a higher plan, or, on a paid plan, turn on usage credits and keep working at standard API rates. Settings, then Usage, shows the current status. Team seats use a different meter. A standard seat includes more usage than Pro, at $20 per seat per month billed annually or $25 billed monthly. A premium seat includes 5x the usage of a standard seat, at $100 per seat per month billed annually or $125 billed monthly.
Pricing checked October 2, 2026. Source: claude.com/pricing.
A Claude API bill is input tokens plus output tokens, and output costs more than input on every current model. Prices below are US dollars per million tokens. Pricing checked October 2, 2026.
The official table also lists older and retired models. Those rows are omitted here. Sonnet 5 is the same $2 input and $10 output as Sonnet 5.5, and Anthropic says the increase to $3 and $15 that had been scheduled for September 1, 2026 will not happen.
The model and the length of the reply do most of the damage. Output is five times the input price on each model above, so an agent that writes a long diff costs more than one that only reads. Three other switches change the same rates. The Batch API takes 50% off input and output when the job can wait: Fable 5.1 batch is $5 and $25, Opus 5.5 is $2 and $10, Sonnet 5.5 is $1 and $5, and Haiku 4.5 is $0.50 and $2.50. US-only inference on Claude 4.6 and later multiplies input, output, cache writes, and cache reads by 1.1. Fast mode, still a research preview, prices Opus 5.5 at $8 input and $40 output, and Opus 5 or Opus 4.8 at $10 and $50. Fast mode does not run on the Batch API.
Claude 4.6 and later include the full 1 million token context window at that same per-token rate. A 900,000-token request is billed at the same rate per token as a 9,000-token request. Claude 4.7 and later, and Mythos Preview, use a newer tokenizer that produces about 30% more tokens for the same text, so an unchanged document can cost more after a model move. Sonnet 4.6 and earlier use the previous tokenizer.
Tools add their own lines. The pricing page lists web search at $10 per 1,000 searches, separate from the tokens used to process the request. Code execution includes 50 free hours a day per organization, then $0.05 per hour per container.
Pricing checked October 2, 2026. Sources: Claude platform pricing and claude.com/pricing.
For full per-model token rate cards, batch processing discounts, and token rate limit schedules, see our complete guide to Claude API pricing, token costs, and rate limits.
Prompt caching saves money when the same long prefix is sent again inside a short window. You pay extra to store that prefix, then a fraction of the normal input price each time a later request reads it.
Anthropic’s docs, checked October 2, 2026, price a 5-minute cache write at 1.25 times the base input price and a 1-hour cache write at 2 times. A cache hit on most models costs 10% of the standard input price. The docs say 5-minute caching pays for itself after one cache read, and 1-hour caching pays for itself after two cache reads. Two current models are cheaper on the read: Fable 5.1 and Mythos 5.1 hits are $0.25 per million tokens, which is 2.5% of base input, and Opus 5.5 hits are $0.20 per million tokens, which is 5% of base input. On the standard table, a 5-minute write is $12.50 for Fable 5.1, $5 for Opus 5.5, $2.50 for Sonnet 5.5, and $1.25 for Haiku 4.5. A 1-hour write on those models is $20, $8, $4, and $2.
The buyers who come out ahead repeat a prefix: a long system prompt, a tool list, a standing document, or an agent loop that reloads the same context every turn. A one-off short chat has nothing to reuse. Cache writes are charged when the prefix is first stored. Cache reads are charged when a later request retrieves it, and a read also refreshes the entry. Those multipliers stack with the Batch API discount and with the 1.1x US-inference multiplier.
Pricing checked October 2, 2026. Source: Claude platform pricing.
At the everyday paid chat tier, Claude Pro and ChatGPT Plus are both $20 a month. Above that, compare the usage multiple on the plan, and price the API separately from the subscription.
Checked October 2, 2026. Claude lists Free at $0, Pro at $20 a month or $17 a month when $200 is billed up front for the year, and Max from $100 a month with a choice of 5x or 20x more usage than Pro per five-hour session. OpenAI’s Help Center lists ChatGPT Plus at $20 a month, billed monthly, and two Pro tiers: $100 for 5x the usage of Plus, and $200 for 20x the usage of Plus. The Plus article says API usage is billed separately. ChatGPT Go appears as a lower plan; a current Go dollar price was not on the pages read for this check.
The meters differ even when the monthly price lines up. Claude draws web, desktop, mobile, and Claude Code from one pool, on a rolling five-hour window, with weekly limits added on paid plans. OpenAI’s Pro article says models can have separate allowances, and reaching one model’s allowance does not by itself end the plan. Pick the product whose limit matches the work.
API rates below are the standard paid tier, in US dollars per million tokens, from the same October 2, 2026 check. Where a vendor publishes a short-context rate and a long-context rate, both are included.
The useful comparison is the shape of the bill. On all three, output tokens cost more than input tokens. OpenAI’s flagship models and Gemini 3.1 Pro Preview raise the per-token rate once a prompt crosses their long-context line. Claude’s current models keep one rate inside the 1 million token window. A repeated prefix is discounted on each platform under that platform’s own cache rules.
Pricing checked October 2, 2026. Sources: claude.com/pricing, Claude API pricing, ChatGPT Plus, ChatGPT Pro tiers, OpenAI API pricing, and Gemini API pricing.
Related on Tygart Media: Claude AI pricing guide · Fable 5 pricing, cache rates & plan access · Claude Code pricing 2026 · Claude Team pricing · How much does Claude cost.
The primary difference between Claude Pro and Claude Max is capacity, monthly usage headroom, and bundled developer credits on identical underlying models. Anthropic prices Claude Pro at $20 per month (or $17 per month when billed annually at $200 upfront). Claude Max is priced at $100 per month, delivering an official 5x usage multiplier over Pro across both the 5-hour rolling session window and the weekly account cap.
Beyond session headroom, Claude Max includes $100 per month in Claude Platform API credits, priority access during peak network traffic times, early access to new Claude features, and included access to Anthropic’s flagship Fable model up to half your weekly allowance. For extreme workloads, Anthropic also offers an Ultra tier at $200 per month, providing 10x weekly usage, $200 per month in API credits, and no 5-hour limit for verified accounts.
Workload fit determines the right tier: Claude Pro fits solo professionals, writers, and analysts working 1 to 3 hours per day with moderate prompt lengths. Claude Max fits full-time developers, engineering leads running continuous Claude Code sessions, and power users who regularly hit Pro’s 5-hour rolling limits mid-task.
Claude Pro costs $20 per month when billed monthly, or $17 per month when billed annually ($200 billed upfront). Anthropic’s published terms confirm that Pro provides substantially more usage than the Free tier across both the 5-hour session window and weekly cap, access to advanced models (Sonnet and Opus), Projects for context management, Claude Code, Claude Science, Claude Dashboards (beta), and priority bandwidth during high-traffic periods.
For daily coding, Claude Max is worth the investment if you write software full-time and frequently run into Pro’s session-based rate limits. In daily developer workflows involving continuous terminal interactions, multi-file diffs, and iterative debugging in Claude Code, each prompt re-submits previous code turns and file context. On Claude Pro, intensive coding sessions often hit the 5-hour rolling cap within 60 to 90 minutes of active development.
The financial math on Max for coding is straightforward: Max costs $100 per month, an $80 monthly premium over Pro. That plan includes an official 5x usage multiplier across 5-hour and weekly windows, plus $100 per month in API credits to build on the Claude Platform. If avoiding interrupted coding sessions saves you just 2 hours per week of downtime, and your professional developer time is valued at $40 or more per hour, Claude Max pays for itself within the first week.
Pay-as-you-go API usage beats a Claude Max subscription when your workloads are automated, bursty, or integrated directly into developer environments rather than open-ended conversational web chats. Instead of paying a flat $100 or $200 monthly subscription fee for personal seat headroom, direct API access bills only for the exact tokens your tasks consume at standard published rates (such as Claude Sonnet 5.5 at $2.00 per million input tokens and $10.00 per million output tokens, or Haiku 5.5 at $0.10 input and $0.50 output).
For programmatic scripting, IDE extensions, or scheduled batch jobs, typical developer consumption often totals $15 to $40 per month in API charges—well below the $100 per month cost of a Max seat. Furthermore, API usage unlocks prompt caching (reducing input token costs up to 90% on cached prefix reads) and Message Batches (providing an automatic 50% discount for asynchronous turnaround within 24 hours). For a detailed structural analysis of when to buy per-user seats versus consuming raw tokens, see our analysis of Seats vs API — the question models get wrong.
If you regularly hit Pro usage limits — especially heavy Claude Code users, content producers, or researchers — Max pays for itself in recovered productivity. If you’ve never hit Pro limits, stay on Pro.
Max 5x ($100/month) gives 5x the usage of Pro. Max 20x ($200/month) gives 20x. Both include higher output limits, early feature access, and priority. Most users who need Max find 5x sufficient.
Yes. You can upgrade from Pro to Max or downgrade from Max to Pro at any time. Changes take effect on the next billing cycle.
Yes. Both Pro and Max include Claude Code. Max gives you more usage capacity for Claude Code sessions.
Yes — Max is the only individual plan that includes Fable models, up to 50% of the weekly usage pool. On Pro, Fable usage runs on usage credits from the first token.
Pay-as-you-go tokens billed at standard API rates that keep you working when a paid plan hits its limit, instead of waiting for the reset window. Ideal for occasional spike weeks.
No. Max 5x and Max 20x are monthly billing only. Pro is the plan with an annual option — $17/month billed yearly ($200 up front).
Manage it all from the Anthropic Console — API keys, billing, and a token-to-dollar cost estimator for your actual usage.
The Signal — Tygart Media's weekly brief. What we actually ran, what it measured, and what it means for a restoration shop.