Tag: Claude AI

  • Claude Enterprise Pricing & Procurement Guide (2026)

    Claude Enterprise Pricing & Procurement Guide (2026)

    Updated November 13, 2026 — added direct answers on Claude Enterprise pricing and contract structure, sourced from Anthropic’s published pricing.

    Updated October 28, 2026: Made infographic diagrams clickable to open full-size images.

    Claude Enterprise pricing works differently from the individual and Team plans. Instead of a fixed per-seat fee that includes unlimited usage, Enterprise charges a base seat cost of $20/seat with additional usage billed at API rates. This model gives large organizations more flexibility but requires understanding how usage translates to cost. Here’s the complete breakdown for decision-makers evaluating Claude Enterprise in 2026.

    Last refreshed: November 13, 2026 (Pacific) — verified against claude.com/solutions/enterprise, claude.com/pricing, and platform.claude.com pricing.

    Direct Answer (November 13, 2026): Claude Enterprise starts at $20/seat/month billed annually (20-seat minimum on self-serve annual terms) for identity governance (SSO, SCIM, audit logs, Compliance API, zero training by default, HIPAA-ready BAA), with model token consumption billed separately at standard API rates — led by current flagship Fable 5.2 ($8/$40 MTok) alongside Opus 5.5 ($4/$20), Sonnet 5.5 ($2/$10), and Haiku 5.5 ($0.10/$0.50 ≤100K).

    TAKEAWAY PDF & MARKDOWN TWIN

    Claude Enterprise Pricing & Procurement Guide (2026) — Takeaway PDF

    Edition of November 13, 2026 — facts verified November 13, 2026. For AI: read the markdown edition.

    How Enterprise Pricing Works

    Decision map from daily chat, shipping products, or buying for a company to Free/Pro, API, or Team/Enterprise
    How Claude Enterprise pricing works — recheck this breakdown whenever Anthropic changes seat fees or API rates (last verified October 2026).

    The pricing structure has two components. First, a per-seat fee of $20/month per user. This covers access to the Claude interface and all Enterprise features. Second, usage-based charges at API rates that scale with which model each user interacts with and how much they use it. When an Enterprise user chats with Claude, token costs follow current API rates. Anthropic’s current top-tier flagship, Claude Fable 5.2, lists at $8/MTok input and $40/MTok output (cache read $0.20), Opus 5.5 lists at $4/$20 (cache read $0.20), Sonnet 5.5 lists at $2/$10 (cache read $0.10), and Haiku 5.5 lists at $0.10/$0.50 for prompts ≤100K tokens ($0.50/$2.50 >100K). Legacy models remain listed for transition: Fable 5.1 ($10/$50), Opus 5 / 4.8 ($5/$25), Sonnet 4.6 ($3/$15), and Haiku 4.5 ($1/$5, 200K context).

    This means actual costs per user vary significantly. A light user who sends a few messages per day might cost $20-30/month total. A power user running Claude Code and extended research sessions could cost $150-500+/month. Administrators can set per-user and organizational spending limits to maintain budget predictability.

    Two Paths to Enterprise

    Infographic ladder of Claude plans: Free, Pro, Max, Team, and Enterprise
    Two paths to Enterprise.

    Anthropic now offers two ways to get on the Enterprise plan. The self-serve path lets organizations sign up directly at claude.ai/create/enterprise without contacting sales. This is designed for teams that want enterprise security features but want to move fast. You get SSO, domain verification, central billing, admin controls, usage analytics, and the ability to add seats on demand. The sales-assisted path is for organizations that need custom contracts, MSAs, purchase orders, usage commitments, tiered incentives on committed spend, non-standard terms, trials, or consultation. Contact sales through claude.com/contact-sales.

    Enterprise-Only Features

    Enterprise includes everything in the Team plan plus several capabilities only available at this tier. Admin-set spend limits let administrators control costs at both user and organization levels. Role-based access with fine-grained permissioning controls who can access what. SCIM (System for Cross-domain Identity Management) automates user provisioning and deprovisioning. Audit logs provide detailed records of user activity. Compliance API enables observability and monitoring. Custom data retention controls let you set how long data is stored. Network-level access control and IP allowlisting restrict where Claude can be accessed from. HIPAA-ready offering is available for healthcare and regulated industries. Claude Security (currently in beta) provides AI-powered vulnerability scanning.

    Enterprise vs Team: When to Upgrade

    Three cards for fast volume, daily workhorse, and deep flagship Claude seats
    Enterprise vs Team — when to upgrade.

    The Team plan caps at 150 users and uses fixed per-seat pricing ($20-125/seat depending on seat type). Enterprise has no user cap and uses the seat-plus-usage model. Upgrade to Enterprise when you need more than 150 seats, when you require SCIM for automated provisioning, when compliance requirements demand audit logs and a compliance API, when you need custom data retention or HIPAA readiness, or when the usage-based model would actually cost less than Team Premium seats for your usage patterns.

    Current Enterprise Promotion

    As of June 2026, Anthropic ran a promotion offering $1,000 in Claude Code and Cowork credits (Cowork has since been integrated directly into core Claude) for Enterprise seats activated by July 2, 2026 — that promotional window has closed.

    Evaluating Enterprise ROI

    To evaluate whether Claude Enterprise justifies the cost, consider time savings per employee (if each user saves 5 hours/week at $50/hour effective cost, that’s $1,000/month in productivity per person), reduction in tool sprawl (replacing multiple SaaS subscriptions), code velocity improvements (engineering teams using Claude Code report 20-40% productivity gains in published case studies), and compliance cost avoidance (audit logs, SCIM, and HIPAA readiness may replace other compliance tools).

    What does Claude Enterprise cost?

    There is no single published flat rate for Claude Enterprise; total pricing is structured around a base platform seat fee plus variable usage charges and negotiated contract terms. On Anthropic’s official published self-serve terms, the Enterprise plan starts at $20 per seat per month (billed annually, with a 20-seat minimum), while all token and model usage is billed separately at standard API rates based on consumption.

    For sales-assisted agreements covering larger deployments, seat minimums and volume discounts are established during the enterprise sales conversation rather than fixed by a public rate card. Total enterprise cost is governed by several core commercial factors: total seat count, annual billing commitments, token consumption across models (such as Sonnet and Opus), and organizational requirements for enterprise governance capabilities. These include Single Sign-On (SSO), automated user provisioning via SCIM, comprehensive audit logs, Compliance API observability, custom data retention policies, IP allowlisting, and HIPAA-ready configurations.

    Frequently Asked Questions

    How much does Claude Enterprise cost per user?

    $20/seat/month base plus usage at API rates. Actual per-user costs depend on usage — light users might total $25-30/month, while heavy users could reach $200+/month.

    Can I start Claude Enterprise without talking to sales?

    Yes. Anthropic offers a self-serve Enterprise option at claude.ai/create/enterprise. You can sign up, add seats, and start using Enterprise features immediately.

    Is Claude Enterprise HIPAA compliant?

    Anthropic offers a HIPAA-ready Enterprise option. Organizations in healthcare and regulated industries should contact sales to discuss specific compliance requirements and BAA arrangements.

    What is the minimum number of seats for Enterprise?

    Self-serve annual Enterprise carries a 20-seat minimum at $20/seat/month plus usage at API rates. Larger sales-assisted agreements have custom seat minimums and volume commitments.

    TAKEAWAY PDF & MARKDOWN TWIN

    Keep This Guide: Claude Enterprise Pricing & Procurement Guide (2026) (PDF)

    Edition of November 13, 2026 — facts verified November 13, 2026. For AI: read the markdown edition.

    Related: Claude AI Pricing (2026) — every plan, API rate, and the cost calculator

    💼 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.

  • Who Owns Claude AI? Anthropic’s Founders, Funding, Structure, and Mission Explained

    Who Owns Claude AI? Anthropic’s Founders, Funding, Structure, and Mission Explained

    Updated November 13, 2026 — verified against SEC Form S-1/A (Reg. No. 333-299633, filed November 10, 2026) and official Anthropic disclosures.

    Claude AI is owned and developed by Anthropic, an artificial intelligence safety company headquartered in San Francisco. Anthropic was founded in 2021 by Dario Amodei (CEO) and Daniela Amodei (President), along with several other former members of OpenAI. The company is structured as a public benefit corporation — a legal structure that allows it to balance profit with its stated mission of AI safety.

    Direct Answer (November 13, 2026): Claude is developed by Anthropic, PBC, a Delaware Public Benefit Corporation founded in early 2021 by seven former OpenAI leaders led by Dario Amodei (CEO) and Daniela Amodei (President). Under SEC Form S-1/A (Reg. No. 333-299633) and Anthropic’s November 10, 2026 roadshow launch, Anthropic has filed to list Class A stock on Nasdaq (ticker ANT, 825,000,000 shares at $70.00–$78.00 plus a concurrent $26.0B Class N placement). At $78.00, equity value is ~$1.02 trillion on 13.09B shares outstanding (and ~$1.4 trillion fully diluted per Reuters), with pricing expected, as reported Nov 18 and debut Nov 19. Founders hold 50.1% general voting power via Class F stock, while the independent Long-Term Benefit Trust elects a Board majority via Class T. See the Anthropic History Hub and Anthropic IPO tracker.

    The Founders: Dario and Daniela Amodei

    Abstract milestone timeline from early Claude eras through today without version numbers
    Founders and the Anthropic origin story.

    Dario Amodei served as VP of Research at OpenAI before co-founding Anthropic. His sister Daniela Amodei was VP of Operations at OpenAI. They left in 2021 along with a group of researchers who shared concerns about the direction of AI development and the importance of safety-first research. Several founding team members had published influential work on AI alignment, interpretability, and the scaling properties of large language models.

    Funding and Investors

    Anthropic has raised more private capital than any AI lab in history. In February 2026 it closed a $30 billion Series G at a $380 billion post-money valuation; three months later it raised $65 billion in Series H funding at a $965 billion post-money valuation — surpassing OpenAI’s $852 billion mark and making Anthropic the most valuable private AI company in the world. Amazon remains the largest strategic investor: beyond its earlier commitments, Amazon invested a further $5 billion ahead of the Series H with the door open to another $20 billion tied to commercial milestones, while Anthropic pledged more than $100 billion of AWS spend over ten years. Alphabet’s filings imply its Anthropic stake is now carried at roughly $124 billion. Earlier investors include Google, Spark Capital, and Salesforce Ventures. Following its $65 billion Series H at $965B post-money (where Anthropic disclosed run-rate revenue crossed $47 billion in May 2026), Anthropic’s SEC Form S-1/A reported audited FY2025 GAAP revenue of $4,585 million and nine-month 2026 GAAP revenue of $33,242 million ($1,260M nine-month operating loss; >$131B cash and short-term investments), driven by enterprise Claude API, Claude Code, and integrated Cowork adoption. Earlier pre-S-1 press reports floating a mid-September $100B run rate (New York Times, unverified in SEC filings) have been superseded by Form S-1/A GAAP numbers.

    The IPO & S-1/A Ownership Disclosure

    Following its June 1 confidential draft, Anthropic filed a public Form S-1 on October 26, 2026 and launched its roadshow on November 10, 2026 via Amendment No. 2 (Form S-1/A, Reg. No. 333-299633). Filed terms specify 825,000,000 Class A shares (801,351,354 primary; 23,648,646 selling stockholders) plus a 123,750,000-share underwriter option at $70.00–$78.00 per share on Nasdaq (ticker ANT), alongside a concurrent $26.0 billion non-voting Class N private placement backed by AMD, Broadcom, Google, Micron, Microsoft, NVIDIA, and TSMC Partners. Based on 13,086,672,593 common shares outstanding post-IPO, $78.00 implies roughly $1.02 trillion (~$1.4 trillion fully diluted, per Reuters). Pricing is expected, as reported November 18, 2026, and trading November 19, 2026. Earlier September press rumors of a ~$2 trillion valuation or $100 billion raise were superseded by the S-1/A terms. Final post-IPO percentage stakes in the S-1’s Principal and Selling Stockholders table settle at pricing in the 424(b)(4) prospectus; in Class N stock, SEC disclosures detail Amazon’s 12% cap and Alphabet’s 14.99% cap (both >5% strategic holders).

    Share ClassVoting PowerHolder & S-1/A Governance Role
    Class A1 vote / sharePublicly offered Nasdaq: ANT shares (825,000,000 offered in IPO)
    Class NNon-voting (general)Strategic backers (incl. Amazon 12% cap, Alphabet 14.99% cap, $26.0B placement); converts to Class A on unaffiliated sale
    Class F50.1% general vote1 share held by Founder LLC (excl. Class T Board elections); non-economic
    Class TElects Board majority1 share held by independent Long-Term Benefit Trust (LTBT)
    Class ELimited votingNon-economic governance shares for eligible employees

    Corporate Structure: Public Benefit Corporation

    Five-step path: account, API keys, billing, usage, workspaces
    Corporate structure: public benefit corporation.

    Anthropic is incorporated as a public benefit corporation (PBC) in Delaware. This corporate structure legally requires the company to consider the impact of its decisions on all stakeholders — not just shareholders. The PBC structure is central to Anthropic’s identity: it creates a legal framework that supports the company’s commitment to AI safety even when that commitment might conflict with short-term profit maximization.

    Anthropic also has a Long-Term Benefit Trust (LTBT) — a governance mechanism designed to ensure that the company’s safety commitments are maintained over time, even as leadership changes. The LTBT elects a majority of Anthropic’s Board through its Class T share; current named trustees listed on anthropic.com/company are Dr. Ben Bernanke, Richard Fontaine, Neil Buddy Shah, and Dr. Christopher Stubbs. On October 18, 2026, Anthropic also announced the Anthropic Public Benefit Fund (committing 5% initial shares subject to stockholder approval, adding to founders’ 80% pledges and employee matching for ~20% dedicated to public benefit).

    The Safety Mission

    Five security domains: identity, data, code governance, audit, agents
    The safety mission shapes product decisions.

    Anthropic’s stated mission is “the responsible development and maintenance of advanced AI for the long-term benefit of humanity.” This mission is embedded in the company’s corporate structure, not just its marketing. Key safety initiatives include the Responsible Scaling Policy (RSP), which sets thresholds for when more rigorous safety evaluations are required as models become more capable. Constitutional AI, the training methodology that gives Claude a set of principles to follow. Extensive red-teaming and safety testing before model releases. Published research on AI interpretability — understanding what happens inside neural networks. Transparency reports on model capabilities and limitations.

    Anthropic’s Global Presence

    While headquartered in San Francisco, Anthropic has expanded globally. The company has offices in multiple countries and has established a significant presence in the Asia-Pacific region, including offices in Tokyo, Bengaluru (India), Sydney, and Seoul. India has become Anthropic’s second-largest market globally, with partnerships including a major deal with Infosys for regulated AI deployment.

    Key Partnerships

    Anthropic’s major partnerships include Amazon Web Services (compute infrastructure and investment), Google Cloud (Vertex AI distribution and investment), Snowflake ($200M partnership for enterprise data integration), and Microsoft (Claude available through Azure and Microsoft Foundry). Claude is also available through third-party platforms like OpenRouter and various enterprise integrations.

    Frequently Asked Questions

    Who owns Claude AI?

    Claude AI is owned by Anthropic, a public benefit corporation founded by Dario and Daniela Amodei. Anthropic’s major investors include Amazon and Google.

    Is Anthropic owned by Amazon or Google?

    No. Amazon and Google are major investors in Anthropic, but Anthropic operates independently. It is a public benefit corporation with its own leadership, board, and decision-making authority.

    Who is the CEO of Anthropic?

    Dario Amodei is the CEO of Anthropic. He co-founded the company in 2021 after serving as VP of Research at OpenAI.

    Is Anthropic a nonprofit?

    No. Anthropic is a for-profit public benefit corporation (PBC). The PBC structure means it legally balances profit with its stated mission of AI safety, but it is not a nonprofit organization.

    Did the founders of Anthropic come from OpenAI?

    Yes. Dario Amodei (VP of Research) and Daniela Amodei (VP of Operations) both left OpenAI in 2021 to found Anthropic, along with several other former OpenAI researchers.

    Is Anthropic publicly traded?

    Not yet as of November 13, 2026, though it is in its public IPO roadshow. Anthropic filed Form S-1/A (Reg. No. 333-299633) on November 10, 2026 for Nasdaq ticker ANT (825M Class A shares at $70.00–$78.00), with pricing expected, as reported November 18 and debut trading expected November 19. See the Anthropic IPO 2026 tracker and History Hub.

    What is Anthropic worth?

    Anthropic’s May 2026 Series H priced at $965 billion post-money. At the S-1/A $78.00 top of range across 13,086,672,593 post-IPO shares outstanding, equity valuation is approximately $1.02 trillion (~$916B at $70.00), or ~$1.4 trillion fully diluted per Reuters. Earlier unverified September press reports citing ~$2 trillion are superseded by the SEC S-1/A terms.


    💼 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.

    ANTHROPIC IPO FACT BOOK · PDF & MARKDOWN TWINS

    Download the Anthropic IPO Fact Book (Nasdaq: ANT)

    Edition of November 13, 2026 — verified SEC Form S-1/A (Reg. No. 333-299633) terms, GAAP revenue, ownership structure, sourced timeline, and live Claude pricing. For AI: read the markdown edition · Return to History Hub.
  • Is Claude AI Free? Everything You Get Without Paying and When Upgrading Makes Sense

    Is Claude AI Free? Everything You Get Without Paying and When Upgrading Makes Sense

    Updated October 28, 2026: Made infographic diagrams clickable to open full-size images.

    Yes, Claude AI is free. Not “free trial” free or “free for 7 days” free — genuinely, permanently free with no credit card required. But “free” comes with boundaries. This guide covers exactly what you get on Claude’s free tier, where the limits hit, and at what point upgrading to a paid plan actually saves you time or money.

    What the Free Tier Includes

    At-a-glance board comparing Free, Pro, Max, and Team Claude tiers by chat, limits, priority, and admin controls
    What the Free tier includes.

    Claude’s free tier is more capable than most people realize. You get full access to chat on web (claude.ai), iOS, Android, and the desktop app. You can search the web directly within conversations — Claude will find current information and cite sources. Memory works across conversations, so Claude remembers context you’ve shared previously. You can create files and execute code — Claude will write Python, JavaScript, or other code and run it in a sandbox. Desktop extensions let you connect Claude to your local environment. You can connect Slack and Google Workspace services through connectors. Remote MCP (Model Context Protocol) integrations let Claude access external tools and data sources. Extended thinking allows Claude to reason through complex multi-step problems.

    That’s a substantial feature set for $0. The free tier in June 2026 includes features that were Pro-only just a year ago.

    Where the Free Tier Limits Hit

    Decision diagram: hitting Free limits, needing a shared workspace, or shipping on the API
    Where Free-tier limits hit — and when to stay.

    The primary limitation is usage volume. Free users get a limited number of messages per time period — when you hit the limit, you’ll see a message telling you to wait or upgrade. During high-traffic periods, free users may experience slower response times or temporary unavailability while paid users get priority access. You also don’t get access to Claude Code (the terminal-based coding agent), Claude Cowork (the desktop automation tool), Research mode, unlimited Projects, or Claude for Microsoft 365/Outlook. You can’t access all model variants — some premium models are reserved for paid subscribers.

    When to Stay on Free

    The free tier works well if you use Claude a few times per day for quick questions, writing assistance, or light coding. If you’re a student, casual user, or someone evaluating Claude before committing, the free tier gives you a genuine experience of what Claude can do. You won’t hit limits if your usage is moderate and spread throughout the day rather than concentrated in heavy sessions.

    When to Upgrade to Pro ($20/month)

    Upgrade when you hit rate limits regularly — when you find yourself waiting to continue conversations during your workday. Upgrade when you need Claude Code for programming projects. Upgrade when you want Research mode for deep investigation tasks. Upgrade when you use Claude for professional work and the interruptions from usage limits cost you more than $20/month in lost productivity.

    When to Upgrade to Max ($100-200/month)

    Max is for users who spend multiple hours per day working with Claude — running extended Claude Code sessions, producing large volumes of content, or conducting marathon research sessions. If you consistently hit Pro limits, Max removes that friction. The $100/month tier gives 5x Pro usage, and the $200/month tier gives 20x. Max also provides early access to new features and priority during peak demand.

    Claude Free vs ChatGPT Free vs Gemini Free

    Two subscription cards on a desk labeled Claude seat and ChatGPT seat for side-by-side comparison
    Claude Free vs ChatGPT Free vs Gemini Free.

    All three major AI platforms offer free tiers, but the feature sets differ. Claude’s free tier includes web search, code execution, memory, desktop extensions, and extended thinking. ChatGPT’s free tier offers GPT-4o access with usage limits and web browsing. Gemini’s free tier provides access to Gemini models with Google Workspace integration. Claude’s free tier is arguably the most feature-complete of the three, particularly with its inclusion of desktop extensions and remote MCP integrations at the free level.

    Related on Tygart Media: Claude pricing · Pro vs Max · how to use Claude.

    Frequently Asked Questions

    Is Claude AI completely free?

    Claude has a permanently free tier with no credit card required and no trial expiration. You get chat, web search, code execution, memory, and more — with usage limits. Paid plans ($20-200/month) remove usage limits and add features like Claude Code.

    Do I need a credit card to use Claude for free?

    No. You can sign up and use Claude’s free tier without providing any payment information.

    What happens when I hit the free tier limit?

    You’ll see a message indicating you’ve reached your usage limit. You can wait for the limit to reset (typically within hours) or upgrade to a paid plan for immediate access and higher limits.

    Can I use Claude Code on the free plan?

    No. Claude Code requires at least a Pro subscription ($20/month). The free tier includes the chat interface with code execution but not the terminal-based Claude Code agent.

  • Claude API Pricing & Token Rates Schedule (2026)

    Claude API Pricing & Token Rates Schedule (2026)

    Updated October 28, 2026: Made infographic diagrams clickable to open full-size images.

    Updated November 2, 2026 — added direct answers on token pricing schedules and input versus output calculations, sourced from Anthropic’s published pricing.

    Claude’s API pricing is token-based: you pay for the tokens you send (input) and the tokens Claude generates (output). Rate limits, service tiers, prompt caching, batch processing, and feature-specific charges all affect your actual bill. Last refreshed: November 13, 2026 (Pacific) against platform.claude.com pricing and Haiku 5.5. Seat prices did not move. This page includes current Fable 5.2 ($8/$40), Opus 5.5 ($4/$20), Sonnet 5.5 ($2/$10), and Haiku 5.5 ($0.10/$0.50 up to 100K tokens) rates.

    Direct Answer (November 13, 2026): Official first-party list: Fable 5.2 $8 / $40 per MTok (5m/1h cache writes $10/$16, cache hits $0.20, batch $4/$20); Opus 5.5 $4 / $20 (cache writes $5/$8, cache hits $0.20); Sonnet 5.5 $2 / $10 (cache writes $2.50/$4, cache hits $0.10); Haiku 5.5 $0.10 / $0.50 for prompts ≤100K tokens and $0.50 / $2.50 >100K (cache hits $0.01/$0.05; batch $0.05/$0.25). Legacy tiers still listed for transition include Fable 5.1 ($10/$50, cache read $0.25), Opus 5 / 4.8 ($5/$25), Sonnet 4.6 ($3/$15), and Haiku 4.5 ($1/$5). Batch API is 50% off. Do not average Haiku 5.5’s two prompt-length bands.

    TAKEAWAY PDF & MARKDOWN TWIN

    Claude API Pricing & Token Rates Schedule (2026) — Takeaway PDF

    Edition of November 13, 2026 — facts verified November 13, 2026. For AI: read the markdown edition.

    Per-Token Pricing by Model

    Workshop fuel gauge and metal tokens pouring into an API hopper, metaphor for pay-per-token pricing
    Per-token pricing by model — no sticky dollars.

    All prices are per million tokens (MTok), verified November 13, 2026. Claude Fable 5.2 leads at $8 input / $40 output (cache reads $0.20). Claude Opus 5.5 is $4 / $20 with cache reads at $0.20. Claude Sonnet 5.5 is $2 / $10 with cache reads at $0.10. Claude Haiku 5.5 lists $0.10 / $0.50 up to 100,000 prompt tokens and $0.50 / $2.50 above that. Legacy references still listed: Fable 5.1 ($10/$50, cache reads $0.25), Opus 5 / 4.8 ($5/$25), Sonnet 4.6 ($3/$15), and Haiku 4.5 ($1/$5, 200K).

    How much does the Claude API cost per million tokens?

    ModelStandard Input (per MTok)Standard Output (per MTok)Cache Read (per MTok)Batch Input (per MTok)Batch Output (per MTok)
    Claude Haiku 5.5 (prompts ≤ 100K tokens)$0.10$0.50$0.01$0.05$0.25
    Claude Haiku 5.5 (prompts > 100K tokens)$0.50$2.50$0.05$0.25$1.25
    Claude Haiku 4.5$1.00$5.00$0.10$0.50$2.50
    Claude Sonnet 5.5$2.00$10.00$0.10$1.00$5.00
    Claude Sonnet 4.6$3.00$15.00$0.30$1.50$7.50
    Claude Opus 5.5$4.00$20.00$0.20$2.00$10.00
    Claude Fable 5.2$8.00$40.00$0.20$4.00$20.00
    Claude Fable 5.1 (legacy)$10.00$50.00$0.25$5.00$25.00
    Current Claude API token pricing per million tokens across standard, cached, and batch tiers (sourced from Anthropic published pricing).

    What’s the difference between input and output token pricing on Claude?

    Input tokens represent the prompt text, system instructions, tool declarations, and context history transmitted to Claude, while output tokens represent the new text Claude generates in response. Across all flagship tiers, Anthropic prices output tokens at exactly 5x the cost of input tokens (for example, Sonnet 5.5 is $2.00 input vs. $10.00 output; Haiku 5.5 is $0.10 input vs. $0.50 output; Opus 5.5 is $4.00 input vs. $20.00 output). Output tokens carry a 5x multiplier because text generation requires sequential autoregressive inference—each token must be predicted and computed one step at a time—which is substantially more compute-intensive than parallelized input processing.

    Worked Calculation: Why Output-Heavy Workloads Dominate Spend
    Consider 10,000 API calls per day on Claude Sonnet 5.5 ($2.00/MTok input, $10.00/MTok output):

    • Workload A (Input-heavy analysis / summarization): 4,000 input tokens + 200 output tokens per call.
    – Daily Input: 40 MTok × $2.00 = $80.00
    – Daily Output: 2 MTok × $10.00 = $20.00
    – Total Spend: $100.00/day (Output accounts for only 20% of cost).

    • Workload B (Output-heavy generation / scaffolding): 500 input tokens + 3,500 output tokens per call.
    – Daily Input: 5 MTok × $2.00 = $10.00
    – Daily Output: 35 MTok × $10.00 = $350.00
    – Total Spend: $360.00/day (Output accounts for 97.2% of cost).

    Even though Workload B processes fewer total tokens per request than Workload A (4,000 vs. 4,200), it costs 3.6x more because 87.5% of its tokens fall into the 5x output pricing tier.

    Prompt Caching Pricing

    5-minute cache write is 1.25x input. 1-hour cache write is 2x input. Cache read is 0.05x on Sonnet 5.5 and Opus 5.5, 0.1x on Sonnet 5 and Haiku 4.5. Fable 5.2 uses $10 5-minute write / $16 1-hour write / $0.20 cache read (0.025x on legacy Fable 5.1 is $0.25/MTok). Haiku 5.5 cache reads are $0.01 / $0.05 (under / over 100k). Haiku 5.5 cache writes are $0.125 / $0.625. Opus 5.5 cache writes $5 / 1-hour $8 / reads $0.20. Opus 5 cache writes $6.25 / reads $0.50. Sonnet 5.5 cache writes $2.50 / reads $0.10. Sonnet 5 cache writes $2.50 / reads $0.20. Sonnet 4.6 cache writes $3.75 / reads $0.30. Haiku 4.5 cache writes $1.25 / reads $0.10.

    Batch Processing: 50% Off

    The Batch API processes requests asynchronously at half the standard rate. Haiku 5.5 batch is $0.05 / $0.25 under 100k tokens and $0.25 / $1.25 over. Sonnet 5.5 and Sonnet 5 batch list is $1 / $5. Sonnet 4.6 batch list is $1.50 / $7.50. Opus 5.5 batch is $2 / $10. Opus 5 batch is $2.50 / $12.50. Fable 5.2 batch is $4 / $20 (legacy Fable 5.1 batch is $5 / $25).

    How to Calculate Your Monthly Bill

    To estimate your monthly Claude API bill, calculate your expected daily token volume—multiplying daily requests by average input tokens (at the model’s input rate per million) plus daily requests by average output tokens (at the model’s output rate per million)—multiply that daily sum by 30 days, and deduct applicable discounts for prompt caching (up to 90% off cached inputs) or batch processing (50% off total spend). Here is how that calculation works in practice:

    Example at Sonnet 5.5 list ($2 / $10): 2,000 input tokens and 500 output tokens × 10,000 requests/day = 20 MTok input ($40) + 5 MTok output ($50) = $90/day, about $2,700/month before cache or batch. Same volume on Opus 5.5 at $4 / $20 is $180/day before cache. Same volume on Haiku 5.5 at the under-100k band ($0.10 / $0.50) is $4.50/day before cache.

    Same volume with caching on Sonnet 5.5: at a 90% cache-hit rate, 18 of those 20 MTok re-read from cache at $0.10/MTok ($1.80) instead of $2/MTok ($36) — input drops from $40 to $5.80/day. The cache line, not the input line, is usually what separates the sticker price from the real bill. That example used $0.20 before October 7.

    Service Tiers and Rate Limits

    Priority, Standard, and Batch tiers still apply. US-only inference (inference_geo: "us") on Claude 4.6 and later is 1.1x. Fast mode on Opus 5.5 is $8 / $40. Fast mode on Opus 5 / Opus 4.8 is $10 / $50. Haiku 5.5 is the exception on long-context pricing: prompts over 100,000 tokens use the higher band. Other Claude 4.6 and later models keep one per-token rate through the 1M window. Check live limits in the Claude Console; published RPM/ITPM figures move by spend tier. Confirm five-hour windows in Settings > Usage, not from a screenshot.

    Current subscription monthly API credits: Max ($100/mo) includes $100/mo in API credits, Ultra ($200/mo, formerly Max 20x) includes $200/mo in API credits, and Team includes up to $500/mo pooled (Pro includes $0 API credits). That is an announced credit, not a seat-price change. Confirm in the Help Center article before you book it as included usage.

    Frequently Asked Questions

    How much does Claude API cost for a small project?

    A small project making 100–500 API calls per day with Haiku 5.5 on the under-100k band is cheaper than the same volume on Haiku 4.5 ($1 / $5). Sonnet 5.5 at the same volume is cheaper than Sonnet 4.6 because the list is $2 / $10, not $3 / $15.

    Is there a free tier for the Claude API?

    Anthropic does not offer a permanent free API tier. You need to add a payment method and load credits. The October 7 Max and Team credit is a subscriber allowance, not a public free tier.

    What’s the cheapest way to use the Claude API?

    Use Haiku 5.5 on prompts under 100,000 tokens ($0.10/MTok input), enable prompt caching, and batch non-real-time work (50% off). Haiku 4.5 remains $1 / $5 if a workload is pinned to that SKU. For mid-tier quality, prefer Sonnet 5.5 at $2 / $10 over Sonnet 4.6 at $3 / $15 unless you need the 4.6 SKU specifically. For Opus-class work, prefer Opus 5.5 at $4 / $20 over Opus 5 at $5 / $25 unless you are pinned to the older SKU.

    How do Claude API costs compare to OpenAI?

    This page’s prior OpenAI pair was gpt-6.1-sol at $2 / $10 short-context and GPT-5 at $1.25 / $10. Those OpenAI rows were not re-verified on this pass. Sonnet 5.5 at $2 / $10 is unchanged. Haiku 5.5 at $0.10 / $0.50 under 100k is the new cheap Claude band. Compare the exact SKU pair, not the family name.

    What happens when I hit a Claude API rate limit?

    The API returns HTTP 429. Back off and retry with exponential backoff; if you hit limits regularly, request a higher spend tier in the Claude Console. Our Claude rate limits guide covers the RPM/TPM tiers and the full 429 playbook.

    Do cached tokens cost the same as fresh input?

    No. Cache reads run 0.025×–0.10× the input price depending on model — $0.10/MTok on Sonnet 5.5, $0.20 on Sonnet 5 and Opus 5.5, $0.20 on Fable 5.2 ($0.25 on legacy Fable 5.1), $0.01 on Haiku 5.5 under 100k, $0.10 on Haiku 4.5. On cache-heavy workloads the read line sets your bill, not the input line.

    Related: Claude AI pricing guide · Fable 5 pricing, cache rates & plan access · Claude rate limits & tiers · How to get an Anthropic API key · How much does Claude AI cost

    TAKEAWAY PDF & MARKDOWN TWIN

    Keep This Guide: Claude API Pricing & Token Rates Schedule (2026) (PDF)

    Edition of November 13, 2026 — facts verified November 13, 2026. For AI: read the markdown edition.
  • Claude in Chrome: Setup, Use Cases & Limits (2026)

    Claude in Chrome: Setup, Use Cases & Limits (2026)

    Last refreshed: November 13, 2026 — primary: Get started with Claude in Chrome (Claude Help Center). Plan matrix re-checked against claude.com/pricing.

    TAKEAWAY PDF & MARKDOWN TWIN

    Claude in Chrome — Takeaway PDF

    Edition of November 13, 2026 — facts verified November 13, 2026. For AI: read the markdown edition.

    Direct Answer (6 October 2026): The Claude in Chrome extension lets Claude read the page you have open and work in a side panel — it reads the live DOM, clicks, fills forms, and downloads files, all inside the browser. It is distinct from desktop scheduled tasks (formerly called Cowork, now built into Claude) and Claude Code. On the claude.com/pricing comparison (verified November 13, 2026), Claude in Chrome is No on Free and Yes on Pro, Max ($100/mo, 5× Pro), Ultra ($200/mo, formerly Max 20x — 10× Pro weekly usage with no 5-hour limit for verified accounts), Team, and Enterprise. Permission claims (passwords, history, autofill) were not re-checked against the Chrome Web Store on this date.

    Claude in Chrome is a browser extension that brings Claude into the tab you already have open. Rather than copying the page into a chat, the extension lets Claude see the page and answer next to it. This guide is built from documented operational use across eight previously separate guides — setup, use cases, profiles, web-app automation, the API decision, the Cowork comparison, LinkedIn workflows, and a production video pipeline — merged into one canonical reference. (Note: Anthropic has since unified standalone Cowork directly into Claude.)

    TAKEAWAY PDF & MARKDOWN TWIN

    Claude in Chrome — Takeaway PDF

    Edition of November 13, 2026 — facts verified November 13, 2026. For AI: read the markdown edition.

    What Claude in Chrome actually is

    Claude in Chrome is a browser extension — separate from claude.ai web chat and desktop scheduled tasks (formerly Cowork) — that connects Claude to your active Chrome tab. Once installed and connected, Claude gains browser-native tools it doesn’t have in a standard chat session:

    • Reading page content — text, links, form fields, and interactive elements on the current tab
    • Clicking — buttons, links, checkboxes, and UI controls (with your permission per action)
    • Filling forms — with explicit approval per action
    • Scrolling and navigating between your open tabs
    • Downloading files through the browser

    The key technical distinction: Claude in Chrome works through DOM access, not screenshots. That makes it faster and more precise for web tasks than screenshot-based computer use — it reads the page structure directly rather than looking at pixels. It has no awareness of your desktop, no filesystem access, and cannot open applications outside the browser. If you close Chrome, Claude in Chrome stops.

    How to install Claude in Chrome

    1. Search the Chrome Web Store for the official Anthropic Claude extension.
    2. Click Add to Chrome, then sign in.
    3. Click the toolbar icon to open the side panel.
    4. Click Connect to link the extension to your chat session.

    Plan availability verified November 13, 2026 against claude.com/pricing: No on Free; Yes on Pro, Max ($100/mo), Ultra ($200/mo, formerly Max 20x), Team, and Enterprise. Usage draws from the same seat pool as claude.ai — a rolling five-hour window, plus weekly limits on paid plans. The install steps and permission claims above were not re-checked against the Chrome Web Store on this date.

    What it can do — and what it can’t

    It can: summarize articles and long docs, extract HTML tables, draft replies against a visible thread, walk a pricing or docs page, research a LinkedIn profile (read-only), fill forms with your approval, and operate web apps that have no API.

    It cannot: see a page you aren’t authenticated to. Heavy iframe / SPA pages can fail. It does not get your history, passwords, or autofill data. It does not submit purchases without you confirming. It is not a bulk scraper — it works one page at a time, in your session. And it cannot run on a schedule or while you’re away: every session needs you present and a manual click to connect.

    Claude in Chrome vs Desktop Tasks (formerly Cowork) vs Chat vs API

    Four tools, four jobs. The decision rule that holds up in practice:

    • Use Chat when the work is text in a conversation.
    • Use Chrome when the source is a live web page and you’re present.
    • Use Claude desktop & scheduled workflows (formerly standalone Cowork, now built into Claude) when the work is files on the desktop or needs to run on a schedule while you’re asleep.
    • Use the API first whenever one exists for what you need — Chrome is the fallback, not the default.

    The API-first rule. An API call is deterministic — same endpoint, same payload, same result. A Chrome UI interaction depends on the current state of a live webpage, and web pages change. Chrome automation runs at human browsing speed, needs a running logged-in browser, and typically needs maintenance when sites redesign. Expect roughly 80-90% reliability per run versus 99%+ for a good API integration. So: API first; Claude in Chrome when the API doesn’t exist, doesn’t expose what you need, or the task is genuinely one-off. The cleanest architectures use both — API for everything it can reach, Chrome for the UI-only edges.

    One question resolves most cases: do you need it to run while you’re asleep? If yes, that is Claude desktop scheduled workflow territory (formerly Cowork). If no, Chrome with you present.

    Practical use cases

    Research and summarization

    Long docs, papers, vendor pages, competitive pricing pages — open the URL and ask for a comparison against your offer, or a summary with the numbers pulled out. Tables come out clean because Claude reads the DOM, not a screenshot.

    Email in the browser

    Draft against the thread you can still see. Claude reads the email context in Gmail and drafts the reply next to it.

    LinkedIn: assist, don’t automate

    The genuinely useful LinkedIn jobs are read-and-prepare: summarizing a prospect’s profile before a call, researching a company page, scanning a feed for the day’s relevant threads, drafting a DM or comment for your approval. The standout use case is paste-assist for long-form Articles — schedulers can only push short feed posts through the official API, so native Articles stay a manual copy-paste, and a guided in-browser assist turns that tedium into minutes.

    What to never do: automated feed posting, bulk connection requests, or bulk messaging. Networks detect automation, it violates terms of service, and accounts get throttled or suspended. The browser is an assistant, not a posting robot. Keep a human on the trigger for anything that publishes or sends.

    Automating web apps without an API

    The pattern that works: Claude Chat writes the work order; Claude in Chrome executes it. You describe the task to Chat; Chat writes precise step-by-step instructions (what page, what to click, what to fill, what to confirm); you paste that into the Chrome session; it executes. Documented uses include cloud console navigation, DNS updates through a registrar UI, posting through scheduling tools whose API tier lacked the endpoint, and operating browser-based AI tools that have no API at all.

    A good work order is sequential, specific about UI elements, anticipates surprises (login screens, MFA prompts, CAPTCHAs — which Chrome cannot solve), and ends with a confirmation step. Pre-login matters: Claude can only touch services you’re already logged into in that profile. And never leave it running on high-stakes actions — payments, publishing, deletions — without reviewing first. There is no undo button.

    Multiple Chrome profiles

    Each Chrome profile is its own island — separate logins, extensions, sessions. Claude in Chrome connects to one profile at a time via your manual click. The extension must be installed separately on each profile. When Claude needs a different profile mid-session it calls switch_browser; you click Connect in the right window. Practical ceiling: two to three profiles per session before the manual clicks get tedious. Keep personal tabs in a profile you never connect.

    The production pattern: scheduled pipelines

    One documented production pipeline shows how far the pattern goes: two staggered desktop scheduled tasks (originally built under Cowork, now native to Claude) use Claude in Chrome to operate a browser-based notebook tool with no API — creating notebooks from article URLs, triggering video generation, harvesting finished videos, and drafting WordPress watch pages. The architecture (trigger, wait, harvest, log) generalizes to any browser-only tool. The real failure modes, documented from production: generation timeouts (most common), Chrome tab closures killing a run, and daily per-account generation limits handled by rotating accounts across profiles. Posts go up as drafts — a human spot-check before publishing is intentional.

    Privacy

    The extension only sends page content when you invoke it. It sees visible page content you share — not passwords, history, or autofill. Team and Enterprise default to no training on that content. Review permissions at install, and use judgment with regulated or confidential data: page content is processed by Anthropic’s systems under your plan’s privacy settings.

    Frequently asked questions

    Is Claude in Chrome free?

    No. Not on the Free plan per claude.com/pricing. Pro, Max, Ultra, Team, and Enterprise are Yes.

    Does it work on Edge or Brave?

    Official support is Chrome. Chromium forks sometimes work; don’t count on it for production.

    Can it see my passwords?

    No. Visible page content you share only.

    Can Claude in Chrome run overnight or on a schedule?

    No. It needs an active session and a manual connection per session. Scheduled, unattended runs belong to Claude’s native desktop scheduled tasks (formerly called Cowork).

    Can it switch Chrome profiles by itself?

    No. Every profile switch needs your click on Connect. Deliberate design, not a limitation to work around.

    Is it safe to use while logged in to sensitive accounts?

    Use a dedicated work profile for Claude sessions and keep personal or sensitive tabs in a profile that’s never connected. Claude can see and interact with any tab open in the connected profile.

    What happens when a site redesigns and breaks my workflow?

    Claude reports it couldn’t find the expected element and stops — it won’t guess or click something random. Update the work order to match the new UI. Writing instructions in terms of intent (“find the button that saves the record”) is more resilient than describing exact pixels, but no wording survives every redesign.

    How is this different from Claude for Microsoft 365?

    Chrome is any website in the browser. Microsoft 365 is Word, Outlook, and Teams.

    Sources: Claude Help Center, Get started with Claude in Chrome; claude.com/pricing (plan availability verified 6 October 2026); documented operational use across eight Tygart Media guides (May–September 2026). Install-step and permission claims were not re-checked against the Chrome Web Store on the verification date. Cowork desktop capabilities have since been integrated directly into core Claude.

    TAKEAWAY PDF & MARKDOWN TWIN

    Keep This Guide: Claude in Chrome (PDF)

    Edition of November 13, 2026 — facts verified November 13, 2026. For AI: read the markdown edition.
  • How Much Does Claude AI Cost? The Plain-English Pricing Breakdown for 2026

    How Much Does Claude AI Cost? The Plain-English Pricing Breakdown for 2026

    Updated October 28, 2026: Made infographic diagrams clickable to open full-size images.

    Last verified: November 13, 2026 (Pacific) against claude.com/pricing, platform.claude.com pricing, and Anthropic’s Ultra plan guide.

    Direct Answer (November 13, 2026): Claude costs $0 on Free (up to 5 Projects); Pro is $20/month ($17/month billed annually at $200); Max is $100/month (5× Pro usage + $100/mo API credits); Ultra is $200/month (formerly Max 20x — 10× Pro weekly usage, no 5-hour session limit for verified accounts + $200/mo API credits); Team Standard is $20–$25/seat; Team Premium is $100–$125/seat (5× Standard usage, up to $500/mo pooled API credits); Enterprise is $20/seat/mo annual (20-seat min) plus API usage. Current API list rates (1M context): Fable 5.2 $8/$40 ($0.20 read), Opus 5.5 $4/$20 ($0.20 read), Sonnet 5.5 $2/$10 ($0.10 read), Haiku 5.5 $0.10/$0.50 ≤100k tokens ($0.50/$2.50 over).

    TAKEAWAY PDF & MARKDOWN TWIN

    How Much Does Claude AI Cost? The Plain-English Pricing Breakdown… — Takeaway PDF

    Edition of November 13, 2026 — facts verified November 13, 2026. For AI: read the markdown edition.

    If you searched “how much is Claude AI” or “Claude AI cost,” here is the straight list — seat plans first, then API token rates. Numbers below are verified November 13, 2026.

    The Free Tier: $0

    Infographic ladder of Claude plans: Free, Pro, Max, Team, and Enterprise
    Plan ladder — Free through Enterprise (no sticky dollars on graphic).

    Claude’s free tier is $0 — no credit card required. Chat on web, mobile, and desktop, web search, memory, file creation, and code execution are included. Claude Code is not. Usage limits are tighter than paid seats.

    Claude Pro: $20/Month

    Pro costs $20/month billed monthly or $17/month if you pay annually ($200 upfront). Official claude.com copy includes Claude Code, Design/Slides/Docs, projects, more models, and Claude for Microsoft 365.

    Claude Max & Ultra: $100 and $200/Month

    Anthropic split the former Max 5x/20x tiers into two distinct plans: Max ($100/month) delivers 5x Pro usage per 5-hour session and weekly plus $100/month in Claude Platform API credits, while Ultra ($200/month, formerly Max 20x) delivers 10x Pro weekly usage, no 5-hour limit for verified accounts (temporary 5-hour limits apply if unverified), and $200/month in API credits (Ultra plan docs). Both include Fable 5.2 up to 50% of weekly limits and are monthly billing only.

    Claude Team: From $20/Seat/Month

    Official claude.com Team seats (USD): Standard $20/seat annual or $25 monthly; Premium $100/seat annual or $125 monthly. Premium is 5× Standard usage. Enterprise on the same page is $20/seat plus usage at API rates, billed annually. Monthly Claude Platform API credits now accompany paid plans: Pro $0, Max $100/month, Ultra $200/month, and Team up to $500/month pooled per team (Enterprise requires a 20-seat minimum). That is an API credit allowance, not a lower seat price.

    Claude API: Pay Per Token

    API access is separate from seats. You pay per million tokens (MTok) for input and output. Current first-party list (November 13, 2026):

    ModelInput / MTokOutput / MTokNotes
    Fable 5.2$8$40Current flagship (1M/128K); cache reads $0.20
    Opus 5.5$4$20Daily driver (1M/128K); cache reads $0.20
    Sonnet 5.5$2$10Current Sonnet (1M/128K); cache reads $0.10
    Haiku 5.5$0.10 / $0.50$0.50 / $2.50Current Haiku (≤100k / >100k, 1M context)
    Fable 5.1 (legacy)$10$50Legacy; cache reads $0.25
    Opus 5 / 4.8 (legacy)$5$25Legacy SKUs still listed; cache reads $0.50
    Sonnet 5 (legacy)$2$10Legacy SKU; cache reads $0.20
    Sonnet 4.6 / Haiku 4.5 (legacy)$3 / $1$15 / $5Legacy SKUs (Haiku 4.5 is 200K context)

    Batch API is 50% off input and output. Prompt caching: 5-minute write 1.25× input, 1-hour write 2×. Cache reads are 0.05× on Sonnet 5.5 and Opus 5.5, 0.1× on Sonnet 5 and Haiku 4.5, and $0.01 / $0.05 on Haiku 5.5. Full schedule: Claude API pricing & token rates.

    Quick Cost Comparison Table

    ProductPriceBest for
    Free$0Light chat, no Claude Code
    Pro$20/mo ($17 annual)Daily chat + Claude Code
    Max$100/mo5× Pro usage + $100/mo API credits
    Ultra (formerly Max 20x)$200/mo10× Pro weekly + no 5h limit (verified) + $200/mo API credits
    Team Standard$20–$25/seatShared workspace, light seats
    Team Premium$100–$125/seatPower seats (5× Standard)
    Enterprise$20/seat + usageAdmin, SSO, usage billing
    API (Haiku 5.5 → Fable)$0.10–$10 input / MTokApps, automation, CI

    Seat vs API: which bill are you on?

    If you…You pay…Read next
    Chat in Claude.ai / use interactive Claude CodeSeat plan usage limitsClaude Code billing & credit pools
    Run claude -p, Agent SDK, or GitHub Actions on a subscriptionSeparate Agent SDK monthly creditDual-bucket billing
    Build on an API keyPay-per-token API ratesAPI token rates

    How Claude usage limits actually work

    The seat price buys a usage window, not a fixed number of messages. Limits reset on a rolling five-hour session, and paid plans add a weekly cap on top.

    On claude.com/pricing, checked November 13, 2026, Free covers everyday questions. Pro includes at least 5x more usage per five-hour session than Free. Max includes 5x Pro usage; Ultra (formerly Max 20x) provides 10x Pro weekly usage with no 5-hour limit for verified accounts. Chat on the web, the desktop app, mobile, and Claude Code draw from one pool. The Max plan Help Center article says the weekly limit resets on a fixed day and time for the account. Settings, then Usage, shows the session meter and the weekly reset.

    When the meter runs out, wait for the reset, move to a higher plan, or turn on usage credits and the extra work bills at standard API rates.

    Claude API pricing, by model

    The API is a separate bill from the seat. You pay per million tokens, and on every current model the output line costs more than the input line.

    Current modelInput / MTokOutput / MTok
    Haiku 5.5 (≤100k / >100k)$0.10 / $0.50$0.50 / $2.50
    Sonnet 5.5$2$10
    Opus 5.5$4$20
    Fable 5.2$8$40

    Haiku 4.5 remains $1 and $5. Sonnet 5 remains $2 and $10. Sonnet 4.6 remains $3 and $15. Opus 5 remains $5 and $25. The Batch API takes 50% off: Haiku 5.5 batch is $0.05 and $0.25 under 100k, Sonnet 5.5 is $1 and $5, Opus 5.5 is $2 and $10, Fable 5.2 is $4 and $20 (legacy Fable 5.1 is $5 and $25). US-only inference on Claude 4.6 and later is 1.1x. Fast mode prices Opus 5.5 at $8 and $40. Haiku 5.5 is the model that raises the rate above 100,000 prompt tokens. Other Claude 4.6 and later models keep one rate through the 1M window.

    When prompt caching saves money

    A 5-minute cache write is 1.25 times base input and a 1-hour write is 2 times. A cache hit on Sonnet 5.5 is $0.10 per million tokens, down from $0.20 on October 7. Opus 5.5 hits stay $0.20. Fable 5.2 hits are $0.20 (legacy Fable 5.1 is $0.25). Haiku 5.5 hits are $0.01 under 100k and $0.05 over. A 5-minute write is $0.125 for Haiku 5.5 under 100k, $2.50 for Sonnet 5.5, $5 for Opus 5.5, and $10.00 for Fable 5.2 ($16.00 for 1-hour write).

    Frequently Asked Questions

    How much does Claude AI cost per month?

    Free is $0 (up to 5 Projects). Pro is $20 monthly or $17/month billed annually. Max is $100/month (5x Pro + $100/mo API credits), and Ultra (formerly Max 20x) is $200/month (10x Pro weekly, no 5h cap for verified accounts + $200/mo API credits). Team starts at $20/seat annual ($25 monthly) for Standard or $100/seat ($125 monthly) for Premium. Enterprise is $20/seat/mo annual (20-seat minimum) plus API usage. API bills separately per token.

    Related on Tygart Media: API rates · Haiku 5.5 list.

    TAKEAWAY PDF & MARKDOWN TWIN

    Keep This Guide: How Much Does Claude AI Cost? The Plain-English Pricing Breakdown… (PDF)

    Edition of November 13, 2026 — facts verified November 13, 2026. For AI: read the markdown edition.

    Part of the complete guide: Claude Pricing, Plans & Limits

  • Claude Team Pricing: Standard vs Premium Seats (2026)

    Claude Team Pricing: Standard vs Premium Seats (2026)

    Updated November 13, 2026: Verified Team Standard ($20 annual / $25 monthly) and Premium ($100 annual / $125 monthly) per-seat pricing, 5× Standard capacity ratio, and pooled API credits ($20 Standard / $100 Premium, capped at $500/mo) against claude.com/pricing; removed unverified Pro multipliers and updated desktop workflow integration wording.

    Free 1-Page Reference

    Claude Plans & Limits Cheat Sheet (PDF)

    Every tier compared side-by-side: pricing anchors, 5-hour rolling usage pools, Claude Code inclusion, and model access in one printable sheet.

    This page covers Claude Team seat pricing — Standard vs. Premium per-seat rates, annual vs. monthly billing, seat-mix budgeting, and pooled API credits — while our Claude Team plan usage limits guide explains rolling 5-hour windows, weekly caps, and usage capacity mechanics.

    Direct Answer (November 13, 2026): Claude Team pricing offers two options (2-seat minimum, 150-seat cap): Standard Team ($20/seat/mo annual or $25 monthly) with shared workspaces and admin controls, and Premium Team ($100/seat/mo annual or $125 monthly) with 5× the per-seat usage of a Standard seat. Each seat also contributes monthly Claude Platform API credits to the team’s shared pool — $20 per Standard seat and $100 per Premium, pooled and capped at $500/month.

    Team Plan Pricing Overview

    Infographic ladder of Claude plans: Free, Pro, Max, Team, and Enterprise
    Team plan seat overview.

    The Team plan uses per-seat pricing across two mix-and-match tiers (2 to 150 seats). Standard seats cost $20/seat/month billed annually ($25/seat/month monthly) with $20/seat in pooled API credits. Premium seats cost $100/seat/month billed annually ($125/seat/month monthly) with 5× Standard seat usage and $100/seat toward the $500/month team API credit pool. For how those seat allowances burn across rolling 5-hour and weekly windows, see the Claude Team usage limits guide.

    For a 10-person team on annual billing with 7 Standard and 3 Premium seats, the monthly cost would be (7 × $20) + (3 × $100) = $440/month, or $5,280/year. That same mix also pools $440/month in API credits (7 × $20 + 3 × $100), under the $500 pool cap. Compare that to putting all 10 on Standard ($200/month) or all 10 on Premium ($1,000/month) to see why the mix-and-match model matters.

    Free 1-Page Reference

    Claude Plans & Limits Cheat Sheet (PDF)

    Every tier compared side-by-side: pricing anchors, 5-hour rolling usage pools, Claude Code inclusion, and model access in one printable sheet.

    What Standard Seats Include

    Three cards for fast volume, daily workhorse, and deep flagship Claude seats
    What Standard seats include.

    Standard seats include full chat access across web, iOS, Android, and desktop (Anthropic does not publish a numeric Pro multiplier for Standard seats; see our usage limits guide for capacity details). Standard seat holders receive Claude Code alongside integrated Claude workspace workflows (built directly into Claude / Claude Desktop), Microsoft 365 and Slack integrations, Enterprise search, SSO, centralized billing, admin controls, and commercial zero-training defaults.

    Team Plan vs Individual Pro/Max Plans

    The question many organizations face: should each person just buy their own Pro or Max subscription? The Team plan adds several capabilities that individual plans lack. Central billing means one invoice instead of individual expense reports. SSO and domain capture ensure that everyone in your organization uses the managed account. Admin controls let you manage connectors and desktop app deployment centrally. Content is not used for model training by default — individual free and Pro accounts have an opt-out option, but Team accounts are opted out by default. Enterprise search lets team members search across organizational knowledge.

    Team Plan vs Enterprise Plan

    The Team plan caps at 150 users. If you need more, or if you need features like SCIM provisioning, audit logs, compliance API, custom data retention, HIPAA readiness, IP allowlisting, or role-based access with fine-grained permissions, you need Enterprise. Enterprise is published at $20/seat/month plus API-rate usage on annual billing (20-seat minimum; self-serve or through Anthropic sales).

    How to Choose Between Standard and Premium Seats

    Decision map from daily chat, shipping products, or buying for a company to Free/Pro, API, or Team/Enterprise
    How to choose between Standard and Premium seats.

    Start with Standard seats for everyone and monitor usage. If specific team members consistently hit rate limits — especially developers using Claude Code heavily or analysts running extended research sessions — upgrade those individuals to Premium seats. The mix-and-match model means you don’t need to over-provision. A typical pattern for a 20-person team might be 4-5 Premium seats for heavy users and 15-16 Standard seats for everyone else.

    Frequently Asked Questions

    What is the minimum team size for Claude Team?

    The Claude Team plan requires a minimum of 2 seats. You can mix Standard and Premium seats within that minimum.

    Can I switch between Standard and Premium seats?

    Yes. Administrators can upgrade individual seats from Standard to Premium or downgrade from Premium to Standard. Changes take effect on the next billing cycle.

    Does Claude Team include Claude Code?

    Yes. Both Standard and Premium Team seats include access to Claude Code alongside integrated Claude workspace and desktop workflows (formerly Cowork, now built directly into Claude).

    Is my team’s data used for training on the Team plan?

    No. Content is not used for model training by default on the Claude Team plan.


    Related: Claude AI Pricing (2026) — every plan, API rate, and the cost calculator

    💼 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.

    The Next Step · Research Verdict

    Which Claude path makes sense for you?

    For business teams of 2 to 150 seats, Claude Team Standard ($20–$25/seat) delivers essential shared workspaces, user administration, and strict zero-data-training privacy. Choose Team Premium ($100–$125/seat) only for dedicated engineering squads executing intensive, non-stop Claude Code sessions.

    Keep the full comparison on your desk Download our free 1-page PDF cheat sheet covering all Claude tiers, limits, and pricing anchors.

    Part of the complete guide: Claude Pricing, Plans & Limits

  • Anthropic Console: Developer Quickstart Guide (2026)

    Anthropic Console: Developer Quickstart Guide (2026)

    The Anthropic Console at platform.claude.com is where developers manage everything related to the Claude API. Whether you’re generating your first API key, tracking token usage, setting spend limits, or managing team workspaces, the console is your control center. This guide walks through every section of the console as it exists in June 2026.

    What Is the Anthropic Console?

    The Anthropic Console — also called the Anthropic Developer Console — is the web-based dashboard at platform.claude.com where you manage your Claude API access. It is separate from claude.ai, which is the consumer chat interface. The console handles API key generation, billing and payment, usage monitoring, workspace and team management, rate limit visibility, and access to developer documentation. Think of claude.ai as where you use Claude, and platform.claude.com as where you build with Claude.

    Getting Started: Creating an Account

    Five-step path: account, API keys, billing, usage, workspaces
    Console path: account → keys → billing → usage → workspaces.

    Navigate to platform.claude.com and sign up with your email or Google account. You’ll need to add a payment method before you can make API calls. Anthropic uses a prepaid credit system — you load credits onto your account and API calls draw from that balance. New accounts start with a default spending limit that increases as you build usage history.

    API Keys: Creating and Managing

    Desk with laptop, checklist notebook, and billing card ready before creating an Anthropic API key
    API keys: create, name, store once — never paste into chat logs.

    API keys are generated in the console under the API Keys section. Each key begins with “sk-ant-” and should be treated as a secret credential. Best practices include creating separate keys for different applications or environments (development, staging, production), naming keys descriptively so you can identify which application uses which key, rotating keys periodically, and never committing keys to source control. If a key is compromised, you can revoke it immediately from the console without affecting your other keys.

    Billing and Usage Monitoring

    The billing section shows your current credit balance, spending history, and usage breakdown by model. You can view costs broken down by Opus, Sonnet, and Haiku usage, see daily and monthly spending trends, set up automatic credit top-ups, and configure spending alerts. Usage is reported in tokens — both input tokens (what you send to Claude) and output tokens (what Claude generates). The console shows real-time and historical usage data with charts that break down costs by model, feature, and time period.

    Workspaces and Team Management

    For organizations, the console supports workspace-level management. You can invite team members with specific roles, set per-user or per-workspace spending limits, view aggregated usage across your organization, and manage API keys at the workspace level rather than individually. This is particularly useful for agencies or development teams where multiple people need API access but you want centralized billing and usage controls.

    Rate Limits and Service Tiers

    Infographic with three panels: protect the service, fair share, and cost control explaining rate limits
    Rate limits and tiers live next to billing — watch both.

    The console displays your current rate limits, which depend on your service tier. Anthropic offers three service tiers: Priority for when time, availability, and predictable pricing matter most; Standard as the default tier for both piloting and scaling everyday use cases; and Batch for asynchronous workloads processed together at 50% off. Rate limits increase as your account matures and your spending history grows. The console shows your current limits for requests per minute and tokens per minute across each model.

    Developer Documentation Access

    The console links directly to Anthropic’s developer documentation at platform.claude.com/docs, which includes API reference with endpoint specifications, SDK guides for Python and TypeScript, prompt engineering best practices, tool use and function calling documentation, vision and multimodal capabilities, and integration guides for AWS Bedrock, Google Cloud Vertex AI, and Microsoft Foundry.

    Console vs Claude.ai: Key Differences

    A common point of confusion: the Anthropic Console (platform.claude.com) is not the same as Claude.ai. Claude.ai is the consumer-facing chat interface where individuals and teams interact with Claude through conversation. The console is the developer-facing dashboard for API management, billing, and infrastructure. You can have accounts on both — your Claude.ai subscription (Free, Pro, Max, Team, Enterprise) is separate from your API credits on the console.

    Related on Tygart Media: API quickstart · Message Batches · how to use Claude.

    Frequently Asked Questions

    How do I access the Anthropic Console?

    Go to platform.claude.com and sign in with your Anthropic account. If you don’t have one, you can create a free account and add billing information to start making API calls.

    Is the Anthropic Console free to use?

    The console itself is free. You only pay for API usage based on the tokens consumed. There is no monthly fee for console access — you pay per token as you use the API.

    What is the difference between the Anthropic Console and the Anthropic Developer Console?

    They are the same thing. “Anthropic Console” and “Anthropic Developer Console” both refer to the dashboard at platform.claude.com where developers manage API keys, billing, and usage.

    Can I set spending limits on the Anthropic Console?

    Yes. The console allows you to set both per-workspace and per-user spending limits. You can also configure automatic credit top-ups and spending alerts to stay within budget.


    >Part of the complete guide: Working with the Anthropic API

  • Connect Claude Code to Postgres via MCP: The Right Way (2026)

    Connect Claude Code to Postgres via MCP: The Right Way (2026)

    The most useful thing you can wire into Claude Code isn’t a new model or a clever prompt — it’s your actual database. When Claude Code can read your schema, it stops guessing at table names, column types, and relationships. It starts writing queries that work the first time.

    This is the practical walkthrough for connecting Claude Code to a Postgres database via MCP: the command, the credential setup, the safety pattern, and what the workflow actually looks like once it’s running.

    Last refreshed: October 20, 2026 (Pacific)

    What the Postgres MCP server does

    Flow from app/IDE through MCP to servers and data APIs
    What the Postgres MCP server does.

    The official @modelcontextprotocol/server-postgres package (maintained in the MCP reference implementations repo) gives Claude Code four tools: schema inspection, query execution inside a read-only transaction, table detail lookup, and relationship traversal. The server cannot write data — it’s read-only by design in the reference implementation, though third-party variants like postgres-mcp-pro add configurable write access if you need it.

    For the majority of development workflows — debugging, writing migrations, generating queries — read-only is exactly what you want. Claude Code can see the shape of your data without being able to touch it.

    The fastest path: single command setup

    Side-by-side cards defining what Claude Code is and is not
    Fastest path — single command setup.

    If you just want it running against a local database:

    claude mcp add postgres -- npx -y @modelcontextprotocol/server-postgres "postgresql://USER:PASSWORD@localhost:5432/mydb"

    The -y flag on npx auto-accepts the package install so the command doesn’t hang on first run. Verify with:

    claude mcp list

    You should see postgres with a connected status. That’s it — Claude Code now has schema access in the current project.

    Don’t do this for a production database. The connection string above is hardcoded. It goes into ~/.claude.json as plaintext. Use a dedicated local or staging database during development, and use env vars for anything that matters.

    The right way: env vars and a read-only user

    Five security domains: identity, data, code governance, audit, agents
    Right way — env vars and a read-only user.

    Two things to do before connecting to any real database:

    1. Create a read-only Postgres user:

    CREATE USER claude_readonly WITH PASSWORD 'your-password-here';
    GRANT CONNECT ON DATABASE your_db TO claude_readonly;
    GRANT USAGE ON SCHEMA public TO claude_readonly;
    GRANT SELECT ON ALL TABLES IN SCHEMA public TO claude_readonly;
    ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT SELECT ON TABLES TO claude_readonly;

    This user can see everything in public and do nothing else. If something goes wrong — a rogue tool call, a compromised session — blast radius is zero.

    2. Reference the connection string via env var in .mcp.json:

    {
      "mcpServers": {
        "db": {
          "type": "stdio",
          "command": "npx",
          "args": ["-y", "@modelcontextprotocol/server-postgres"],
          "env": {
            "POSTGRES_CONNECTION_STRING": "${DATABASE_URL}"
          }
        }
      }
    }

    Set DATABASE_URL in your shell environment or in a .env file (not committed). Add .mcp.json to the repo — everyone on the team gets the same server config — but the actual connection string lives in each developer’s local environment. This is the same pattern you already use for application config. It’s the right pattern here too.

    Add the server at project scope so it’s committed:

    claude mcp add --scope project --transport stdio db -- npx -y @modelcontextprotocol/server-postgres

    Then edit .mcp.json to replace the hardcoded connection string with the ${DATABASE_URL} env var reference shown above.

    What Claude Code can actually do with schema access

    Once the server is connected, the workflow changes significantly. A few real examples:

    Schema exploration: Ask Claude Code “what tables are in this database and how are they related?” and it traverses foreign keys, describes join paths, and builds a mental model of your data layer. No more copy-pasting \dt output.

    Query generation: “Write a query that finds users who signed up in the last 30 days but haven’t completed onboarding” produces accurate SQL because Claude Code knows your actual column names. With a generic prompt and no schema access, you’d get plausible-looking SQL that fails because user_status is actually onboarding_state.

    Migration drafting: “I need to add a last_login_at column to users — show me the migration and check for existing timestamp patterns in the schema.” Claude Code inspects the schema first, matches your existing column naming conventions, and produces a migration that fits your codebase.

    Debugging: “This query is returning the wrong count — here’s the query, check it against the schema.” Claude Code can spot that you’re joining on a nullable column, missing a filter on a soft-delete flag, or aggregating before filtering.

    Neon and cloud Postgres

    If you’re on Neon, there’s a first-party MCP server with additional capabilities: branch management, database creation, and schema migrations via Neon’s branching model. Set it up with:

    npx neonctl mcp add

    This runs OAuth through your browser and configures Claude Code automatically. The Neon MCP server is intended for local development and IDE workflows — not production automation — same caution applies.

    Debugging when it doesn’t connect

    Three commands for when the server shows as disconnected:

    claude mcp list          # check registered servers and status
    claude mcp test db       # test a specific server
    claude --debug           # tail logs including MCP stderr output

    Most connection failures are either a wrong connection string, a missing env var, or Node version issues with npx. The debug log shows the exact error from the server process — read it before assuming the problem is Claude Code.

    The practical baseline

    Five minutes to set up. The productivity delta on any codebase larger than a few tables is immediate — Claude Code stops making column-name mistakes and starts being genuinely useful for data-layer work. Wire up the read-only user, commit the .mcp.json, and add DATABASE_URL to your team’s .env.example. Done.

    The model doing the work in a typical Claude Code session is claude-sonnet-5-5 (workhorse) — it handles schema-aware query generation well without burning through Opus 5.5 credits on every lookup.

    Related Reading

    Frequently Asked Questions

    How do I connect Claude Code to a Postgres database via MCP?

    Run: claude mcp add postgres — npx -y @modelcontextprotocol/server-postgres “postgresql://USER:PASSWORD@localhost:5432/mydb”. The -y flag auto-accepts the package install so the command doesn’t hang. Then run claude mcp list and confirm postgres shows a connected status. Use a local or staging database for this quick path, not production.

    Is the Postgres MCP server read-only?

    Yes. The official @modelcontextprotocol/server-postgres package is read-only by design — it exposes schema inspection, query execution inside a read-only transaction, table detail lookup, and relationship traversal. It cannot write data. Third-party variants like postgres-mcp-pro add configurable write access if you need it.

    What’s the safe way to connect Claude Code to a production database?

    Create a dedicated read-only Postgres user (GRANT SELECT only), and reference the connection string through an environment variable in .mcp.json using ${DATABASE_URL} rather than hardcoding it. Commit .mcp.json so the team shares the server config, but keep the actual connection string in each developer’s local .env. If a session is ever compromised, the blast radius is zero.

    Why does schema access make Claude Code more accurate?

    With schema access, Claude Code reads your real table names, column types, and relationships, so it writes queries that work the first time instead of guessing. Without it, you get plausible-looking SQL that fails because user_status is actually onboarding_state. It also improves migration drafting and query debugging by matching your existing conventions.

    How do I debug a Postgres MCP server that won’t connect?

    Use three commands: claude mcp list to check registered servers and status, claude mcp test db to test a specific server, and claude –debug to tail logs including MCP stderr. Most failures are a wrong connection string, a missing env var, or a Node version issue with npx — the debug log shows the exact server error.

  • How to Connect Any Tool to Claude with MCP: Complete Setup Guide

    How to Connect Any Tool to Claude with MCP: Complete Setup Guide

    Last verified: October 8, 2026 (Pacific)

    MCP (Model Context Protocol) is how you give Claude hands. Out of the box Claude can talk; with an MCP server connected, it can read your files, query a database, hit an API, or drive a browser. This guide covers the two places you actually wire servers up: the claude_desktop_config.json file for the Claude Desktop app, and the claude mcp add command for Claude Code (the terminal/IDE tool). It ends with the troubleshooting section the official docs skip: path problems, JSON syntax traps, servers that silently never load, and the Windows quirks that cost people an afternoon.

    Everything below is checked against the current Claude Code MCP docs and tested commands. If you want the wider picture of how MCP fits into a working setup, see the AI operator’s stack.

    What is MCP and what is an MCP server?

    Flow from app/IDE through MCP to servers and data APIs
    What MCP is — and what an MCP server is.

    MCP transport options at a glance

    TransportUse caseConfig locationWorks with
    stdioLocal tools, CLIs, scriptsclaude_desktop_config.json or claude mcp addClaude Desktop, Claude Code
    SSE (HTTP)Remote servers, cloud servicesURL in configClaude Desktop, Claude Code
    Streamable HTTPProduction remote MCPURL in configClaude Desktop, Claude Code

    MCP is an open standard for connecting AI models to external tools and data. An MCP server is a small program that exposes a set of tools (functions Claude can call) over that protocol. Claude is the client; the server is the thing that actually does the work, like reading a Postgres table or creating a GitHub issue.

    There are two transport types you will deal with in practice:

    • stdio (local): the server runs as a process on your machine. Claude talks to it over standard input/output. Best for filesystem access, local databases, and custom scripts. This is what most “install this MCP server” instructions mean.
    • HTTP (remote): the server lives on the internet at a URL. Best for cloud services (Notion, Sentry, Stripe, GitHub). Often uses OAuth. SSE is the older remote transport and is now deprecated; use HTTP for new remote servers.

    The same server can usually be added to both Claude Desktop and Claude Code. The mechanics differ: Desktop uses a JSON file you edit by hand, Claude Code gives you a CLI that writes the config for you.

    How do I add an MCP server to Claude Desktop?

    Five-step path: account, API keys, billing, usage, workspaces
    Add an MCP server to Claude Desktop.

    For local stdio servers, Claude Desktop still reads a single JSON file — you edit it, fully quit the app, and reopen. The config file remains the source of truth for anything that runs on your own machine. Remote servers are a different story: Claude Desktop now offers an in-app route (Settings > Connectors > Add custom connector) that adds a remote server by URL and handles OAuth for you.

    Where is claude_desktop_config.json?

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json (paste that into the File Explorer address bar; it expands to C:\Users\YOU\AppData\Roaming\Claude\)

    The fastest way to open it: in Claude Desktop go to Settings > Developer > Edit Config. That button creates the file if it does not exist and opens the folder. If the file is brand new it may be empty or just {}.

    The config file structure

    Everything lives under a top-level mcpServers object. Each key is a name you choose; each value describes how to launch the server. Here is a complete, working file with a local filesystem server and a remote Notion server:

    {
      "mcpServers": {
        "filesystem": {
          "command": "npx",
          "args": [
            "-y",
            "@modelcontextprotocol/server-filesystem",
            "C:\\Users\\YOU\\Documents"
          ]
        },
        "notion": {
          "command": "npx",
          "args": ["-y", "@notionhq/notion-mcp-server"],
          "env": {
            "NOTION_TOKEN": "secret_your_token_here"
          }
        }
      }
    }

    Three fields do all the work:

    • command the executable to run (npx, node, python, uvx, or an absolute path to a binary).
    • args an array of arguments. Each flag and value is its own array element. "--port 8080" as a single string will not work; use "--port", "8080".
    • env an object of environment variables (API keys, tokens). Optional.

    After saving, completely quit Claude Desktop (on Windows, right-click the system tray icon and choose Quit; closing the window is not enough) and reopen it. You should see a tools/connector indicator in the chat input. For a full Notion walkthrough including the token, see connecting Notion to Claude with MCP.

    How do I add an MCP server to Claude Code (CLI)?

    Side-by-side cards defining what Claude Code is and is not
    Add an MCP server to Claude Code CLI.

    Claude Code does not make you hand-edit JSON. The claude mcp command manages servers for you and writes to the right file. This is the part people get wrong most often, so here is the exact, verified syntax.

    claude mcp add

    The general form for a local (stdio) server is:

    claude mcp add [options] <name> -- <command> [args...]

    The -- is load-bearing. Everything before it is for Claude Code; everything after it is the command that launches your server. Real examples:

    # Local filesystem server
    claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem ~/Documents
    
    # Local server with an environment variable
    claude mcp add --env AIRTABLE_API_KEY=YOUR_KEY airtable -- npx -y airtable-mcp-server
    
    # Remote HTTP server
    claude mcp add --transport http notion https://mcp.notion.com/mcp
    
    # Remote HTTP server with an auth header
    claude mcp add --transport http github https://api.githubcopilot.com/mcp/ --header "Authorization: Bearer YOUR_PAT"

    Option ordering matters. All flags (--transport, --env, --scope, --header) must come before the server name. Put a flag after the name and you will get a confusing parse error or the flag will be passed to your server instead of to Claude Code.

    Scopes: local, project, user

    The --scope flag decides where the config is written and who sees it:

    • local (the default) loads only in the current project, private to you. Stored in ~/.claude.json keyed by the project path.
    • project loads in the current project and is shared with your team. Stored in a .mcp.json file at the project root that you commit to git.
    • user loads across all your projects, private to you. Also stored in ~/.claude.json.
    # Available across all your projects
    claude mcp add --scope user --transport http sentry https://mcp.sentry.dev/mcp
    
    # Shared with your team via .mcp.json in the repo
    claude mcp add --scope project filesystem -- npx -y @modelcontextprotocol/server-filesystem .

    When the same server name exists at multiple scopes, local wins over project, which wins over user. The whole entry from the winning scope is used; fields are not merged.

    claude mcp list, get, and remove

    # List every configured server and its connection status
    claude mcp list
    
    # Show the full config for one server
    claude mcp get github
    
    # Remove a server
    claude mcp remove github

    claude mcp list is your first diagnostic. It shows each server as connected, pending, or failed. Project-scoped servers from a .mcp.json you have not approved yet show as Pending approval until you run claude interactively and accept them.

    Other useful commands

    # Add from a raw JSON blob (handy when copying from a server's README)
    claude mcp add-json weather '{"type":"stdio","command":"npx","args":["-y","weather-mcp"]}'
    
    # Import everything you already set up in Claude Desktop (macOS / WSL)
    claude mcp add-from-claude-desktop

    Inside a running Claude Code session, type /mcp to see live server status, tool counts, and to trigger OAuth login for remote servers that need it.

    Troubleshooting: the errors the docs skip

    Most MCP failures are not exotic. They are paths, quoting, and the app not restarting. Work this list top to bottom.

    Server not loading / no tools appear

    1. Did you actually restart? Claude Desktop only reads the config at launch. Fully quit (tray icon > Quit on Windows, Cmd+Q on macOS) and reopen. In Claude Code, run claude mcp list to see the real status instead of guessing.
    2. Is the command on PATH? The single most common stdio failure is npx, node, python, or uvx not being found by the app. GUI apps often have a narrower PATH than your terminal. Fix it by using an absolute path. Find it with which npx (macOS/Linux) or where npx (Windows), then put that full path in command.
    3. Read the logs. Claude Desktop writes per-server logs. macOS: ~/Library/Logs/Claude/. Windows: %APPDATA%\Claude\logs\. Look for mcp-server-NAME.log. The actual error (missing module, bad token, wrong path) is almost always sitting right there.

    spawn ENOENT or “command not found”

    This means the OS could not find the executable named in command. It is a PATH problem, not a Claude problem. Use the absolute path (see above). On Windows specifically, see the npx note below.

    JSON syntax errors (the silent killer)

    If claude_desktop_config.json has a single syntax error, Claude Desktop loads zero servers and usually says nothing. The usual culprits:

    • Trailing commas. JSON forbids a comma after the last item in an object or array. "args": ["a", "b",] is invalid.
    • Smart quotes. If you edited the file in a word processor, curly quotes (the slanted kind) break the parser. Use a code editor and straight quotes only.
    • Unescaped Windows backslashes. In JSON, \ is an escape character, so every backslash in a Windows path must be doubled: C:\\Users\\YOU\\Documents. A single backslash silently corrupts the string.

    Paste the whole file into any JSON validator before restarting. Thirty seconds there saves an hour of staring.

    Claude Code: flag passed to the wrong place

    If claude mcp add behaves strangely, you almost certainly put a flag after the server name or forgot the --. Reread the order: claude mcp add [flags] NAME -- COMMAND ARGS. The -- separates Claude Code’s flags from your server’s command.

    Windows quirks

    • npx needs a wrapper in some setups. If a bare "command": "npx" fails on Windows, launch it through cmd: "command": "cmd" with "args": ["/c", "npx", "-y", "the-server-package"]. This resolves a class of “npx works in my terminal but not in Claude” failures.
    • Use the right config root. It is %APPDATA%\Claude\ (which is AppData\Roaming), not AppData\Local. Mixing these up means you are editing a file the app never reads.
    • Git Bash mangles paths. If you run commands through Git Bash, it can rewrite paths like /c/Users or absolute paths inside arguments. Prefer PowerShell or cmd for claude mcp add, or pass paths exactly as Windows expects them.
    • WSL is a separate world. A server installed inside WSL is not visible to a Windows-native Claude Desktop, and vice versa. Keep both on the same side.

    Remote server returns 401 / 403

    The server needs authentication. In Claude Code, run /mcp and complete the OAuth flow in your browser. If you hardcoded an Authorization header and it is rejected, the token is wrong for that endpoint; remove the header and let OAuth handle it instead.

    Frequently asked questions

    What is an MCP server in one sentence?

    A small program that exposes tools (functions like read-file or query-database) to Claude over the Model Context Protocol, so Claude can take real actions instead of only producing text.

    What is the difference between Claude Desktop and Claude Code for MCP?

    Claude Desktop is the chat app and you configure servers by hand-editing claude_desktop_config.json, then restarting. Claude Code is the terminal/IDE tool and you configure servers with the claude mcp add command, which writes the config for you.

    Where is the Claude Desktop config file?

    macOS: ~/Library/Application Support/Claude/claude_desktop_config.json. Windows: %APPDATA%\Claude\claude_desktop_config.json. The quickest way to open it is Settings > Developer > Edit Config inside the app.

    Why is my MCP server not showing up?

    In order of likelihood: you did not fully restart the app, the command is not on the app’s PATH (use an absolute path), or there is a JSON syntax error such as a trailing comma, a smart quote, or an unescaped Windows backslash. Check the per-server log in the Claude logs folder for the exact error.

    What does the double dash do in claude mcp add?

    The -- separates Claude Code’s own flags from the command that launches your server. Flags like --transport and --env go before it; the actual launch command (npx -y some-server) goes after it.

    What is the default scope for claude mcp add?

    local. The server loads only in the current project and stays private to you. Use --scope user to make it available in every project, or --scope project to share it with your team via a committed .mcp.json.

    Is SSE or HTTP the right transport for remote servers?

    HTTP. SSE still works but is deprecated. Use --transport http for any new remote server unless its documentation specifically requires SSE.

    How do I remove an MCP server?

    In Claude Code, run claude mcp remove NAME. In Claude Desktop, delete that server’s entry from the mcpServers object in claude_desktop_config.json and restart the app.

    Where to go next

    Once your servers connect cleanly, the leverage comes from using them well. For how this fits a daily workflow, read the AI operator’s stack; if you are choosing between coding environments, see Claude Code vs Cursor. And if you want a concrete first server to wire up, the Notion MCP setup is a clean, high-value place to start.

    Frequently Asked Questions

    What is MCP and why does it matter for Claude?

    MCP (Model Context Protocol) is an open standard that lets Claude connect to external tools, databases, APIs, and services. Without MCP, Claude can only work with text in the conversation window. With an MCP server connected, Claude can read your files, query a live database, hit an API, or control a browser — turning it from a chat interface into an autonomous agent.

    How do I add an MCP server to Claude Desktop?

    Edit the claude_desktop_config.json file (found at ~/Library/Application Support/Claude/ on Mac, %APPDATA%/Claude/ on Windows). Add your server under the ‘mcpServers’ key with a ‘command’, ‘args’, and optional ‘env’ block. Save the file and restart Claude Desktop. The server appears in Claude’s tool list if it loaded correctly.

    How do I add an MCP server to Claude Code?

    Run ‘claude mcp add [args…]’ from your terminal. For a remote SSE server use ‘claude mcp add –transport sse ‘. List configured servers with ‘claude mcp list’. Servers added this way are scoped to your user profile unless you use the –project flag.

    Why does my MCP server connect but Claude can’t see my data?

    The most common cause is scope or permission gaps. For Notion, verify your integration has been granted access to the specific pages/databases — the connection succeeds even without page access. For file servers, check that the path in your config resolves correctly from the shell Claude launches (not your interactive shell). For OAuth servers, re-authorize and confirm token scopes.

    What is the difference between stdio and SSE MCP transports?

    stdio runs the MCP server as a local subprocess — Claude launches the command you specify and communicates over stdin/stdout. This is used for local tools and CLIs. SSE (Server-Sent Events) connects to a remote HTTP server. Use stdio for local tools like filesystem access or database clients; use SSE or Streamable HTTP for cloud services or shared team servers.

    Which MCP servers should I start with?

    The highest-value first connections are: filesystem (read/write your local files), a database client for your primary DB, and a service you interact with daily (Notion, Slack, GitHub, Linear). The Notion MCP server is a clean first project — see the dedicated setup guide on this site for the exact config and common errors.