Cheapest-model router
Cheapest-model router: send your token workload and get every current LLM ranked by estimated USD cost, with per-MTok prices, cached-input rates, and context windows. Merges the weekly hand-verified llm-pricing table (every figure carrying its official source URL and verification date) with the daily OpenRouter marketplace catalog — 400+ models — and marks each row `operator-verified` or `marketplace-listed`; `verified_only=1` keeps just the first kind.…
Paid test badge: not yet. The checks above are free: we call the tool without paying and read the payment request it sends back. The Verified badge needs paid calls whose answers match the promised output, and nobody can buy a badge.
Endpoint
GET https://datastand.dev/api/llm/route
| Category | Market data |
|---|---|
| Provider host | datastand.dev |
| Networks | eip155:8453 |
| Payment schemes | exact |
| Self-reported calls, 30 days | 3 from 3 payers (the provider's figure, not ours) |
Our checks, last 30 days
We never call tools that send, buy, move money or file anything, not even without paying.
Example input (from the provider)
{
"method": "GET",
"queryParams": {
"input_tokens": "20000",
"limit": "100",
"min_context": "200000",
"offset": "0",
"output_tokens": "1500"
},
"type": "http"
}
Promised output schema (from the provider)
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"additionalProperties": false,
"properties": {
"method": {
"enum": [
"GET",
"HEAD"
],
"type": "string"
},
"queryParams": {
"properties": {
"include_unknown_context": {
"description": "1/true to also rank models whose context window is unverified when min_context is set",
"type": "string"
},
"input_tokens": {
"description": "Input tokens per request (default 1000)",
"type": "string"
},
"limit": {
"description": "Rows per page, 1-100 (default 100)",
"type": "string"
},
"min_context": {
"description": "Only models with at least this context window. Models whose window is null (not verified) are excluded and counted in filters.unknown_context_excluded.",
"type": "string"
},
"offset": {
"description": "Skip this many ranked models (default 0). Use page.next_offset from the previous response. A page past the end costs nothing.",
"type": "string"
},
"output_tokens": {
"description": "Output tokens per request (default 1000)",
"type": "string"
},
"provider": {
"description": "Filter to one vendor token, e.g. anthropic, openai, x-ai, mistralai, qwen. Matched exactly against the vendor (punctuation and case ignored, so x-ai and xai are the same token) \u2014 never as a prefix, because meta and meta-llama are different vendors. Every response carries providers_available; a token that matches nothing is refused for free and names the near misses.",
"type": "string"
},
"verified_only": {
"description": "1/true to rank only operator-verified rows, dropping the marketplace catalog",
"type": "string"
}
},
"type": "object"
},
"type": {
"const": "http",
"type": "string"
}
},
"required": [
"type",
"method"
],
"type": "object"
},
"output": {
"properties": {
"example": {
"type": "object"
},
"type": {
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
}
},
"required": [
"input"
],
"type": "object"
}