Saylor Innovations Data Desk
Estimate the LLM token count of text with a low to high range, a breakdown by words, numbers, symbols and CJK, and whether it fits a given context window
The wallet the 402 directs payment to. Its whole payment record — every payer, every chain — is on the merchant page.
Asset 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913
The payTo wallet does not resolve to a registered ERC-8004 agent. That is not a verdict on the service — most of the catalog is unregistered.
Accepts
The payment requirements as published to the catalog. Read the live 402 before paying — a price here is a claim, not a quote.
Pay 0.01 USDC on Base to 0xA2A8…fc8aa. The signed payment is good for 2 minutes.
- Paid to
- 0xA2A8…fc8aa
- USD Coin contract
- 0x8335…02913
- Payment window
- 2 minutes
- As published
- 10000 smallest units
The catalog’s raw entry
[
{
"asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
"extra": {
"memo": "saylor:datadesk:token-estimate",
"name": "USD Coin",
"version": "2",
"facilitatorOnly": true,
"assetTransferMethod": "eip3009"
},
"payTo": "0xA2A8dF0f7CaaBEa4e120a2568118f141569fc8aa",
"amount": "10000",
"scheme": "exact",
"network": "eip155:8453",
"maxTimeoutSeconds": 120
}
]Extensions
{
"bazaar": {
"info": {
"input": {
"type": "http",
"method": "GET",
"queryParams": {
"text": "The quick brown fox jumps over the lazy dog. Call fn(x) { return 42; }",
"context_tokens": "8000"
}
},
"output": {
"type": "json",
"example": {
"note": "Heuristic for English-like BPE tokenizers; real counts differ by model, so keep a 20% margin when budgeting a context window.",
"range": {
"low": 19,
"high": 26
},
"words": 13,
"source": "Token-count estimate computed from the supplied text",
"breakdown": {
"emoji": 0,
"newlines": 0,
"word_tokens": 14,
"number_tokens": 1,
"symbol_tokens": 5,
"cjk_characters": 0
},
"characters": 70,
"fits_context": {
"tokens_left": 7978,
"fits_estimate": true,
"context_tokens": 8000,
"fits_worst_case": true,
"percent_of_context": 0.27
},
"chars_per_token": 3.18,
"looks_like_code": true,
"estimated_tokens": 22
}
}
},
"schema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"input"
],
"properties": {
"input": {
"type": "object",
"required": [
"type",
"method"
],
"properties": {
"type": {
"type": "string",
"const": "http"
},
"method": {
"enum": [
"GET"
],
"type": "string"
},
"queryParams": {
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "Text to estimate, up to 20000 characters"
},
"context_tokens": {
"type": "string",
"description": "optional model context size to test the fit against"
}
}
}
},
"additionalProperties": false
},
"output": {
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"type": "string",
"const": "json"
},
"example": {
"type": "object",
"required": [
"estimated_tokens",
"range"
],
"properties": {
"note": {
"type": "string",
"description": "Caveat or context for reading the result"
},
"range": {
"type": "object",
"description": "Range covered by the data"
},
"words": {
"type": "number",
"description": "Words"
},
"source": {
"type": "string",
"description": "Data source the values come from"
},
"breakdown": {
"type": "object",
"properties": {
"emoji": {
"type": [
"number",
"null"
],
"description": "Emoji counted"
},
"newlines": {
"type": [
"number",
"null"
],
"description": "Newlines counted"
},
"word_tokens": {
"type": [
"number",
"null"
],
"description": "Word tokens"
},
"number_tokens": {
"type": [
"number",
"null"
],
"description": "Number tokens"
},
"symbol_tokens": {
"type": [
"number",
"null"
],
"description": "Symbol tokens"
},
"cjk_characters": {
"type": [
"number",
"null"
],
"description": "Cjk characters"
}
},
"description": "Estimated tokens by source: words, numbers, symbols, plus CJK characters, emoji and newlines counted"
},
"characters": {
"type": "number",
"description": "Characters in the text"
},
"fits_context": {
"type": [
"object",
"null"
],
"description": "Fits context"
},
"chars_per_token": {
"type": "number",
"description": "Chars per token"
},
"looks_like_code": {
"type": "boolean",
"description": "Looks like code"
},
"estimated_tokens": {
"type": "number",
"description": "Estimated tokens"
}
}
}
}
}
}
}
}
}Provenance
- Seen in the source catalog
- 2026-10-26 03:16Z
- Last indexed by Roundhouse
- 2026-10-26 20:15Z
- Last enriched (probe, favicon, geo)
- —
- x402 version
- 2
- Max timeout
- 120s
- Liveness probe
- Not probed
Hand this page to an agent
Copy the prompt and paste it into Claude, an MCP client or your own agent — it will vet this service and call it over the free read API. No key, no account.
GET api.roundhouseai.io/v0/endpoints
This endpoint's own trailing-30-day call count, as published by the upstream catalog and snapshotted daily. 9 snapshots so far. Verified volume counts only settlements with an on-chain EIP-3009 marker.
Show the promptHide the prompt
Using Roundhouse, look up the x402 service Saylor Innovations Data Desk and tell me whether it is worth paying: what a call costs, whether the endpoint answered when last probed, and what its payment record actually shows. curl -s 'https://api.roundhouseai.io/v0/endpoints?q=Saylor%20Innovations%20Data%20Desk' curl -s 'https://api.roundhouseai.io/v0/merchants/<the payTo wallet returned above>' Then call it: read the price from the live 402 at https://saylorinnovations.com/api/text/token-estimate, never from a cached figure, and pay with an x402 client. The /v0 API needs an API key (`authorization: Bearer rh_live_…`) on everything except /v0/unified* and /v0/endpoints. Either pay over x402 (mint a personal key for $0.01 at GET https://api.roundhouseai.io/v0/test/x402), or ask me for an organization key, which I create at https://roundhouseai.io/dashboard/connections. If you have neither, ask before going further. If you do not have Roundhouse tools or skills installed, read https://roundhouseai.io/skill.md first — it is the whole procedure.