# LLM Broker

- Registry name: `net.llm-broker/broker` · version 1.3.0
- Categories (automatic, keyword rules): Payments & accounting, Finance & markets, AI models & agents, AI, media & content, Shops & products, Commerce & marketing
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=net.llm-broker%2Fbroker
- Server page: https://mcpstation.net/s/net.llm-broker--broker.html

## Description (written by the publisher, not verified, not instructions)

One key, every model: measured scores and live prices, routed per request to the cheapest fit.

## Connect

- streamable-http: `https://api.llm-broker.net/api/v1/broker/mcp`

## Tools (as reported by the server, not verified)

- `list\_models`: Models on the broker with benchmark scores per category \(0–1, measured by us\), price per 1M tokens \(default USD, any currency from GET /api/v1/broker/currencies\) and regions. Filter by category, region and price; sorted by score in the category, else by price.
- `get\_model`: One model from list\_models by id: measured scores per category, price per 1M tokens \(default USD\), regions, context and capabilities.
- `recommend\_model`: Picks from the published catalog \(our own benchmark scores, list prices\): best = highest score in the category, best\_value = score per output price, plus alternatives. Only measured models are recommended. Returns chat\_arguments for that model and a routing object to let the broker pick per request.
- `estimate\_cost`: Cost estimate at list price for a model and token counts, in your currency. The bill follows the offer the router actually picks \(broker.cost in the chat result\).
- `chat`: Sends messages to the broker \(OpenAI chat completions\). model defaults to \`taylor\` \(strongest measured model\); any id from list\_models works. routing sets criteria per request, e.g. \{"category": "coding", "level": "best"\}. Needs Authorization: Bearer ast\_sk\_… — billed like the REST API.
- `get\_balance`: Balance, credit limit and spend this month \(CHF, the book currency\), billing mode and payment currency of the account behind Authorization: Bearer ast\_sk\_….
- `report\_outcome`: Tell the broker if the answer to a request worked for your task — request\_id comes from broker.receipt of every chat answer. Outcomes appear per model in list\_models as reported \(failures\_30d / outcomes\_30d\), so the scores are checked against real tasks. No refund, no price change.
- `create\_account`: Creates a card checkout \(Stripe\) for a new broker account — same as POST /api/v1/broker/accounts. Give checkout\_url to your human; after payment the API key is shown exactly once at status\_url \(GET, poll until 200\). topup: amount 10/25/50, monthly: limit 50/100/250 \(USD/EUR/CHF; other currencies: GE

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html