Faundr
DocsPTSign in

Anthropic

API for the Claude models, strong at writing, code, long documents and agents that use tools.

AI models
Website Official pricing
Price
Sonnet 5.5: $2 input / $10 output per million tokens
Free plan
No
Setup
Needs a developer
Up and running
An afternoon for the first answer in your app; no approval needed, just a card and credits.

What Anthropic is for

If your product needs to read, write or reason (summarize a contract, answer customers, run an agent that clicks through your own tools), you rent that brain from an AI company instead of building one. Anthropic's API gives your app the Claude models: you send text, it sends an answer back, and you pay per word processed, in dollars.

How it plugs into your product

  1. 1Create an organization in the Claude Console and add a card.
  2. 2Buy prepaid credits (or turn on auto-reload); the API only runs while there is balance.
  3. 3Create an API key and keep it on your server, never in the browser or the mobile app.
  4. 4Call the model from your backend and set a spend limit on the Billing page so a bug can't drain your balance.

Does it fit your idea?

It fits if

  • Your core feature is an assistant that reads long PDFs, contracts or spreadsheets and answers questions about them.
  • You're building an agent that calls your own functions (create an order, look up a customer) on its own.
  • You charge a subscription big enough to absorb about $0.01 per chat on Sonnet, or want Haiku for cheap high-volume tasks.

Look elsewhere if

  • You want to validate with real users at zero cost: there's no free API tier. Start on the Gemini free tier.
  • You also need image generation or voice in the same account: Claude doesn't generate images. Look at OpenAI.
  • You want to compare Claude, GPT and Gemini with one key and one bill: use OpenRouter.

What people only find out after building

Read this before you build on it. Each item links to the official page that says so.

  • Each usage tier has a monthly spend cap ($500 on Start, $1,000 on Build). Hit it and the API stops answering until the 1st of next month, unless you request a higher tier. New accounts may start on an Evaluation tier with even lower limits.

    Official source: platform.claude.com

  • Prepaid credits expire one year after purchase, the date can't be extended, and purchases are non-refundable. Don't top up a year's budget at once.

    Official source: support.claude.com

  • Models get retired, with at least 60 days' notice. After that, calls to the old model name fail. Claude Sonnet 4.5, for example, retires on November 30, 2026.

    Official source: platform.claude.com

  • Prices and credits are in US dollars, so if you charge your customers in euros or pounds, your cost moves with the exchange rate.

    Official source: claude.com

Price

Sonnet 5.5: $2 input / $10 output per million tokens

No free API tier; you pay for usage in dollars.

Price per million tokens (main model)
Sonnet 5.5: $2 in / $10 out
Models
Claude Fable, Opus, Sonnet, Haiku
Free tier
No free tier

Checked on Oct 28, 2026 · official pricing

What it costs in practice

Estimate: 1,000 users × 30 chats a month × about 2,000 tokens per chat (1,500 in, 500 out) = 45M input and 15M output tokens. On Sonnet 5.5 ($2 in / $10 out per million): 45 × $2 + 15 × $10 ≈ $240/month, under the Start tier's $500 cap. The same volume on Haiku 5.5 ($0.10 / $0.50) is about $12/month.

Estimate from the official price. Check it before you decide.

At a glance

  • Free plan: no
  • Open source: no

“Not stated” means the official site doesn’t say.

Alternatives

Compare side by side

Faundr

Picked your tools? Build it with AI, safely.

Faundr keeps your project’s memory, blocks what can’t be undone and tells you if it’s safe to launch, inside Claude Code and Codex.

Get started free