TollNode

Claude Opus 5.5 API and MCP for AI agents

TollNode gives Claude, Cursor or any AI agent Claude Opus 5.5, Anthropic's most capable model for hard reasoning, long documents, code review and careful writing, paid per call with no API key, from $0.067 per call.

Ask in plain words, like 'find the bug in this function and fix it', and get the written answer back.

No subscription · Sign-up optional · From $0.067 per call · Charged only when it works · No Anthropic account needed

Claude Code

Why is my average function off by one? return xs.reduce((a, b) => a + b) / xs.length - 1

TollNode · Anthropic · quick$0.067 · 1 answer · quick

FindingDetail
BugDivision binds tighter than subtraction, so the result is off by exactly one
FixRemove the stray - 1
AlsoGive reduce an initial value so empty arrays don't throw

Real result, shortened.

Works in Claude Code, Cursor, Codex, VS Code and any MCP agent.

What your agent gets from a call

Every result is structured JSON your agent can sort, filter, summarize or turn into a spreadsheet.

What people ask their AI to do with it

Use it as a Claude Opus 5.5 MCP server in Claude, Cursor or Codex

Connect once. Then just ask.

Paste this into Claude Code, Cursor or Codex. It connects TollNode and gives your agent a small wallet. Add a few dollars of USDC and you're done.

terminal
npx agentcash add https://tollnode.com

Copy for your AI agent

Paste this into your agent so it knows what this node does and how to call it.

prompt
You can use TollNode's Claude Opus 5.5 node. Call POST https://tollnode.com/api/v1/nodes/claude-opus-5-5 with length (optional), prompt (required), system (optional). The price depends on length (quick, standard, long; default quick) and is charged only when a result is returned. Over MCP, call the "claude-opus-5-5" tool; use list_models to see prices. Return results as tables when I ask for lists.

Price

from $0.067

per call

The price depends on the length you choose. If you don't choose, you get quick.

quickdefault$0.067 per call
standard$0.265 per call
long$0.658 per call

Charged only when a call returns a result. Failed or empty calls cost $0.

Claude Opus 5.5 without an Anthropic account

FAQ

Is this the official Anthropic API?
No. TollNode is an independent service. It gives your agent access to Claude Opus 5.5 through its own API and MCP server, paid per call, with no Anthropic account.
Can I use it as a Claude Opus 5.5 MCP server in Claude?
Yes. Add https://tollnode.com/mcp in Claude Code, Claude Desktop or Cursor, and the "claude-opus-5-5" tool appears with its fields and price.
How much text can I send?
It depends on the length option. quick takes about 10,000 characters and writes about 750 words, standard about 40,000 and 3,000 words, long about 140,000 and 6,000 words.
How is it different from Claude Sonnet 5?
Opus 5.5 is Anthropic's most capable model, for hard reasoning, long documents and careful work. Sonnet 5 costs less per call, which suits routine text. Both use the same length options.
Does it remember earlier calls?
No. Each call is independent, so include any earlier text in the prompt. Use system for instructions you want applied every time.
What if nothing comes back?
You're not charged. TollNode only collects payment when a usable result is returned, and your agent can try a different input.
How do I pay for Claude Opus 5.5?
Your agent sends the request, gets an HTTP 402 with the exact price (from $0.067 per call), signs a USDC payment on Base and retries. Or use an account balance with an API key. Either way you are charged only when a result comes back.

Ready in a minute

Connect your AI
For developers: endpoint, inputs and an example response

POST https://tollnode.com/api/v1/nodes/claude-opus-5-5

Input

FieldTypeNotes
lengthenumquick: up to ~3,000 tokens in (about 10,000 characters) and ~750 words out. standard: ~12,000 in (40,000 characters) and ~3,000 words out. long: ~40,000 in (140,000 characters) and ~6,000 words out. Default quick (quick, standard, long)
prompt*stringWhat you want Claude to do, with any text it needs
systemstringOptional instructions that frame every answer, e.g. 'You are a senior engineer. Be concise.'

Example response

{
  "text": "The bug is operator precedence: …"
}

Also described in the OpenAPI file and llms.txt. Setup for every app: Agents & MCP.