Pay-per-call LLM API for agents: model catalog, pricing, unpaid x402/MPP quotes, how-to-pay.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Returns prices: fixed per-call prices of the nano, small and brief routes, and per-token prices of the catalog. With a model and token counts it also returns an estimated cost and the minimum charge per rail.
Catalog model id.
Returns prices: fixed per-call prices of the nano, small and brief routes, and per-token prices of the catalog. With a model and token counts it also returns an estimated cost and the minimum charge per rail.
| Argument | Type | Description |
|---|---|---|
| model | string | Catalog model id. |
| input_tokens | integer | |
| output_tokens | integer |
{
"type": "object",
"properties": {
"model": {
"type": "string",
"maxLength": 64,
"description": "Catalog model id."
},
"input_tokens": {
"type": "integer",
"maximum": 2000000,
"minimum": 0
},
"output_tokens": {
"type": "integer",
"maximum": 200000,
"minimum": 0
}
},
"additionalProperties": false
}Sends one unpaid request to a paid route and returns the 402 payment requirements (amount, currency, network, payee, protocol). No payment is made and no credential is sent; the response is the quote for that exact request body.
| Argument | Type | Description |
|---|---|---|
| body* | object | JSON request body the quote is computed for (messages or prompt; for /v1/chat/completions also model and max_tokens). |
| route* | string | Paid route path. /v1/* accepts MPP, /x402/* accepts x402. |
{
"type": "object",
"required": [
"route",
"body"
],
"properties": {
"body": {
"type": "object",
"description": "JSON request body the quote is computed for (messages or prompt; for /v1/chat/completions also model and max_tokens)."
},
"route": {
"enum": [
"/v1/chat/nano",
"/v1/chat/small",
"/v1/brief",
"/v1/chat/completions",
"/x402/chat-nano",
"/x402/chat-small",
"/x402/brief"
],
"type": "string",
"description": "Paid route path. /v1/* accepts MPP, /x402/* accepts x402."
}
},
"additionalProperties": false
}Returns the payment flow for a rail: endpoint URL, required headers, the client nonce format, and client commands. Payment is produced by the caller's own wallet tooling; this server holds no keys.
| Argument | Type | Description |
|---|---|---|
| rail | string | Payment rail; all rails when omitted. |
{
"type": "object",
"properties": {
"rail": {
"enum": [
"mpp",
"x402",
"package",
"card"
],
"type": "string",
"description": "Payment rail; all rails when omitted."
}
},
"additionalProperties": false
}Returns the public catalog: model ids, context windows, maximum output tokens, price per million input and output tokens, accepted payment rails and prepaid packs that can be bought now.
| Argument | Type | Description |
|---|---|---|
| tier | string | Optional filter by catalog tier. |
{
"type": "object",
"properties": {
"tier": {
"enum": [
"open",
"frontier"
],
"type": "string",
"description": "Optional filter by catalog tier."
}
},
"additionalProperties": false
}