LLM Broker
One key, every model: measured scores and live prices, routed per request to the cheapest fit.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"broker": {
"url": "https://api.llm-broker.net/api/v1/broker/mcp"
}
}
}Remote endpoints
https://api.llm-broker.net/api/v1/broker/mcpstreamable-httpWhat it can do
Tool inventory
Tools (8)
🟢list_models(category, limit, currency, region, max_price_per_mtok)
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.
Input Schema
{
"type": "object",
"properties": {
"category": {
"type": "string",
"enum": [
"coding",
"instruction_following",
"math",
"reasoning"
]
},
"limit": {
"default": 10,
"maximum": 50,
"type": "integer",
"minimum": 1
},
"currency": {
"type": "string",
"description": "ISO 4217 code, default USD"
},
"region": {
"type": "string",
"enum": [
"ch",
"eu",
"us",
"asia",
"global"
]
},
"max_price_per_mtok": {
"type": "number",
"description": "Max output price per 1M tokens, in currency"
}
}
}🟢get_model(id, currency)
One model from list_models by id: measured scores per category, price per 1M tokens (default USD), regions, context and capabilities.
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"currency": {
"type": "string",
"description": "ISO 4217, default USD"
}
},
"required": [
"id"
]
}🟢recommend_model(category, currency, region, capabilities, min_score, ...)
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.
Input Schema
{
"type": "object",
"properties": {
"category": {
"type": "string",
"enum": [
"coding",
"instruction_following",
"math",
"reasoning"
]
},
"currency": {
"type": "string",
"description": "ISO 4217, default USD"
},
"region": {
"type": "string",
"enum": [
"ch",
"eu",
"us",
"asia",
"global"
]
},
"capabilities": {
"type": "array",
"items": {
"type": "string",
"enum": [
"reasoning",
"structured_output",
"tools",
"vision"
]
}
},
"min_score": {
"maximum": 1,
"type": "number",
"minimum": 0
},
"max_price_per_mtok": {
"type": "number",
"description": "Max output price per 1M tokens, in currency"
}
},
"required": [
"category"
]
}🟢estimate_cost(currency, model, input_tokens, output_tokens)
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).
Input Schema
{
"type": "object",
"properties": {
"currency": {
"type": "string",
"description": "ISO 4217, default USD"
},
"model": {
"type": "string"
},
"input_tokens": {
"default": 0,
"type": "integer",
"minimum": 0
},
"output_tokens": {
"default": 0,
"type": "integer",
"minimum": 0
}
},
"required": [
"model"
]
}🟢chat(messages, prompt, model, max_tokens, routing)
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.
Input Schema
{
"type": "object",
"properties": {
"messages": {
"type": "array",
"items": {
"type": "object"
}
},
"prompt": {
"type": "string",
"description": "Shortcut for a single user message"
},
"model": {
"default": "taylor",
"type": "string"
},
"max_tokens": {
"type": "integer",
"minimum": 1
},
"routing": {
"type": "object"
}
}
}🟢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_….
Input Schema
{
"type": "object",
"properties": {}
}🟢report_outcome(reason, request_id, 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.
Input Schema
{
"type": "object",
"properties": {
"reason": {
"type": "string",
"maxLength": 500
},
"request_id": {
"type": "string"
},
"outcome": {
"type": "string",
"enum": [
"success",
"failure"
]
}
},
"required": [
"request_id",
"outcome"
]
}🟡create_account(level, category, limit, currency, amount, ...)
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: GET /api/v1/broker/currencies). Omit category and level to choose per request.
Input Schema
{
"type": "object",
"properties": {
"level": {
"type": "string"
},
"category": {
"type": "string",
"description": "optional, with level: a fixed performance promise"
},
"limit": {
"type": "integer",
"description": "monthly credit limit in currency"
},
"currency": {
"default": "USD",
"type": "string"
},
"amount": {
"type": "integer",
"description": "topup amount in currency"
},
"billing": {
"type": "string",
"enum": [
"topup",
"monthly"
]
}
},
"required": [
"billing"
]
}Community
Evidence