Free tool · #10
LLM Pricing API & Widget
A free, keyless REST API over the model-pricing registry, plus a self-hosted embeddable widget that shows any model’s live price on your own page.
Prices verified 15 Jul 2026 · 131 models
The pricing API
A free, public, keyless REST API over the same verified model-pricing registry every tool on this site reads — list every model, fetch one by id or alias, compute a cost, or read the machine-readable OpenAPI 3.1 document.
GET/api/pricing/modelsList every model in the registry (verified, pending, and stale alike); filter by ?provider= and ?status=.GET/api/pricing/models/{id}One model by id or alias.POST/api/pricing/cost{ model, usage } → cost, via the same computeCost the web tools use.GET/api/pricing/openapi.jsonThe OpenAPI 3.1 document for the endpoints above.
Every GET endpoint above sends Access-Control-Allow-Origin: *— call it directly from browser JS on any origin, no server-side proxy required. It’s what makes the widget below possible: the script runs on YOUR page and fetches the price live, cross-origin.
Live preview
This is the actual widget script, embedded on this very page — exactly what a visitor to your site would see:
Embed generator
<div data-telemeter-pricing="gpt-4o"></div>
<script src="https://telemeter.ai/widget/pricing.js" async></script>No integrity (SRI) hash on this snippet — deliberately. The script is served first-party from telemeter.aiitself, not a third-party CDN, and it’s designed to auto-update; a pinned SRI hash would break every time the widget ships a fix. SRI defends against a compromised third-party host — that isn’t the threat model for a same-origin script you already trust to serve the rest of this page.
Use this tool from code — or hand it to your agentagent prompt · REST · MCP
Hand this tool to your coding agent
Paste into Claude Code, Cursor, Codex, or any agent. It learns to call this tool over REST or MCP, reaches for it when you ask, and keeps our sourced/pending labels honest.
You can use telemeter.ai's free "LLM Pricing API & Widget" — a keyless, read-only tool (no signup), available as an HTTP API and an MCP tool. What it does: A free, keyless REST API over the model-pricing registry, plus a self-hosted embeddable widget that shows any model’s live price on your own page.
Whenever I ask you something this tool answers, call it and use its result instead of estimating yourself.
REST:
curl -sX POST https://telemeter.ai/api/tools/pricing-api -H 'content-type: application/json' -d '{"model":"gpt-4o"}'
MCP: the telemeter MCP server at https://telemeter.ai/mcp exposes this as the tool "pricing-api" — call it with tools/call.
The response is JSON: { status, data, summary, provenance }. "provenance" carries the source and the date the figure was verified. If status is "pending" or "stale", tell me the value isn't currently verified rather than presenting it as fact.Or call it directly. This tool runs behind one handler with three front doors — this page, a REST endpoint, and an MCP tool. Same result, read-only, no key. The example below is a request that works.
curl -sX POST https://telemeter.ai/api/tools/pricing-api \
-H 'content-type: application/json' \
-d '{"model":"gpt-4o"}'curl -sX POST https://telemeter.ai/mcp \
-H 'content-type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"pricing-api","arguments":{"model":"gpt-4o"}}}'{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"model": {
"default": "gpt-4o",
"type": "string",
"minLength": 1
}
},
"required": [
"model"
],
"additionalProperties": false
}Want this across your whole stack?
Telemeter tracks real cost, latency, and quality on every production agent run — on the same verified pricing behind this tool.
https://telemeter.ai/tools/pricing-apiNo account, no cookies, nothing stored — the embed snippet is generated entirely in your browser; the live preview and the widget itself only call our own public, keyless pricing API, and never send or store anything about you. Data notice →