LLM Pricing Tracker: Model Prices per Token, All Providers avatar

LLM Pricing Tracker: Model Prices per Token, All Providers

Pricing

from $0.58 / 1,000 price row returneds

Go to Apify Store
LLM Pricing Tracker: Model Prices per Token, All Providers

LLM Pricing Tracker: Model Prices per Token, All Providers

LLM pricing for 400+ models: input and output price per million tokens, cached price, context window, provider endpoints and price-change tracking since your last run. No key.

Pricing

from $0.58 / 1,000 price row returneds

Rating

0.0

(0)

Developer

Detroit Web Agent - Open Data

Detroit Web Agent - Open Data

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

8 hours ago

Last modified

Features

Limited permissions

Share

LLM pricing for more than 400 AI models in one table: input price and output price per million tokens, cached-input price, context window, tool and reasoning support, the hosts that serve each model, and what changed since your last run. No API key, no login, no proxy.

If you build with language models you already know the problem: prices move every week, the same model is sold by several hosts at different rates, and a pricing page only shows you today. This Actor reads a live public model catalog, converts every rate to US dollars per million tokens, and, if you schedule it, tells you which models got cheaper or more expensive since the previous run.

Run in 30 seconds

  1. Open the Input tab. The prefilled keywords (claude, gpt, gemini, llama) return the 25 newest matching models.
  2. Click Start. A default run finishes in a few seconds.
  3. Open the Prices table in the Output tab, or export as JSON, CSV or Excel.
  4. Change the keywords, add a price ceiling, or switch on One row per provider endpoint and run again.

What does this Actor do?

It downloads the current price list of the catalog, keeps the models that match your keywords and filters, sorts them, and returns one flat row per model. Prices in the source are quoted per single token; the Actor multiplies them so every number you see is US dollars per 1,000,000 tokens, the unit used on every vendor's pricing page.

Optionally it also fetches every hosting provider behind a model, so you can see that the same open-weight model costs one amount at one host and a different amount at another, along with quantization and recent uptime.

On top of that it keeps a small price snapshot in a named storage in your own Apify account. On the next run each row is marked new, up, down or unchanged, with the date the price changed and the previous input and output price. That turns a one-off lookup into a price-drop alert you can send to Slack, a sheet or an email.

GroupFields
Identitymodel, name, provider, modelUrl
Token prices (USD per 1M tokens)inputPricePerM, outputPricePerM, cachedInputPricePerM, cacheWritePricePerM, reasoningPricePerM
Other prices (USD per unit)imagePriceUsd, webSearchPriceUsd, requestPriceUsd
CapacitycontextWindow, maxCompletionTokens
Capabilitiesmodality, inputModalities, outputModalities, supportsTools, supportsReasoning
FlagsisFree, isVariablePrice, releasedAt, expiresAt
Provider endpoint (optional)endpointProvider, endpointTag, quantization, uptime30m, discount
Change trackingpriceChange, changedAt, previousInputPricePerM, previousOutputPricePerM
RunscrapedAt

Fields that a model does not have are returned as null, never as zero, so a missing cache price is not confused with a free one. Models with variable or router pricing are flagged with isVariablePrice and have null token prices.

Who uses it

  • Developers choosing a model. Sort by input price, filter to models with a 200,000-token context window and tool support, and pick the cheapest that fits.
  • Teams watching their AI bill. Schedule a daily run with Only models whose price changed and get a message only when something you depend on moves.
  • Analysts and newsletter writers. Track how fast prices fall for each model family, using the changedAt and previous price fields collected run after run.
  • Procurement and finance. Export a dated price table for every model your company uses, with the host-level prices behind it.
  • Product builders. Feed live prices into a calculator, a comparison page or an internal cost dashboard through the API.

Limits

  • Prices are the catalog's published rates, the same ones the gateway charges its own users. A vendor can charge a different amount on its own direct price page, for volume deals, or for a batch tier.
  • The catalog lists what is currently available. A model that was removed is not returned and cannot be priced after the fact.
  • Change tracking compares your run with your previous run, so the first run only saves a baseline (every row says new). Changes show from the second run on. History is kept per Apify account, not per task.
  • Image, audio and web-search prices are quoted by the source in US dollars per unit, not per token, and are returned in that unit as imagePriceUsd, webSearchPriceUsd and requestPriceUsd.
  • Free models can disappear or be rate limited; isFree only tells you the listed price is zero.

Input

FieldWhat it does
modelsKeywords matched against model id and name, one per line. Empty means every model.
providersOnly models from these makers, for example openai, anthropic, google.
maxItemsMaximum rows returned. Default 25, up to 5000.
sortBynewest, inputPrice, outputPrice, context or name. Applied before the limit.
maxInputPricePerMKeep models at or below this input price in dollars per million tokens.
maxOutputPricePerMKeep models at or below this output price.
minContextWindowKeep models with at least this many tokens of context.
outputModalitytext, image, audio or embeddings.
includeFreeUntick to hide zero-priced models.
perProviderEndpointsOne row per hosting provider with that host's own price.
trackChangesSave a snapshot and mark each row new, up, down or unchanged. Default on.
onlyChangedReturn only models whose price differs from your previous run.

Example input

Find the cheapest models with a long context window:

{
"sortBy": "inputPrice",
"minContextWindow": 200000,
"outputModality": "text",
"maxItems": 20
}

Compare hosts for one open-weight family:

{
"models": ["llama"],
"perProviderEndpoints": true,
"sortBy": "outputPrice",
"maxItems": 40
}

Daily price-change alert (schedule it, then connect the dataset to Slack or email):

{
"models": ["claude", "gpt", "gemini"],
"onlyChanged": true,
"maxItems": 200
}

Output sample

{
"model": "openai/example-model",
"name": "OpenAI: Example Model",
"provider": "openai",
"inputPricePerM": 2.5,
"outputPricePerM": 10,
"cachedInputPricePerM": 0.25,
"cacheWritePricePerM": null,
"reasoningPricePerM": null,
"imagePriceUsd": null,
"webSearchPriceUsd": 0.01,
"requestPriceUsd": null,
"contextWindow": 1050000,
"maxCompletionTokens": 128000,
"modality": "text+image->text",
"inputModalities": ["text", "image"],
"outputModalities": ["text"],
"supportsTools": true,
"supportsReasoning": true,
"isFree": false,
"isVariablePrice": false,
"releasedAt": "2026-11-17T18:00:32.000Z",
"expiresAt": null,
"modelUrl": "https://openrouter.ai/openai/example-model",
"endpointProvider": null,
"endpointTag": null,
"quantization": null,
"uptime30m": null,
"discount": null,
"priceChange": "down",
"changedAt": "2026-11-20T06:00:03.000Z",
"previousInputPricePerM": 3,
"previousOutputPricePerM": 12,
"scrapedAt": "2026-11-20T06:00:03.000Z"
}

The values above are an illustration. Your own run returns the live prices.

Use cases

  • Pick the cheapest model that still has tools, vision or a very long context.
  • Get a message the day a model you rely on gets cheaper, or more expensive.
  • Compare the hosts of the same open-weight model before you commit to one.
  • Build a public or internal LLM price comparison page that updates itself.
  • Audit which of the models in your codebase are about to expire or have been replaced.
  • Estimate monthly cost: multiply the per-million prices by your token volume in a sheet.

Pricing

Pay per event, no subscription. Current prices:

EventFreeBronzeSilverGoldPlatinumDiamond
Actor Start$0.00005$0.00005$0.00005$0.00005$0.00005$0.00005
Price row returned$0.00095$0.000885$0.000755$0.000583$0.000583$0.000583

Tier follows your Apify subscription plan.

Apify's free plan includes monthly platform credit that covers test runs.

Examples at the current price (one model-price event per result; Free-plan tier):

You pullYou pay
100 results$0.095
1,000 results$0.95
10,000 results$9.50

Scheduled runs stay cheap when each run only returns new records.

Integrations and scheduling

For monitoring, create a Task with your keywords and Only models whose price changed switched on, then add a schedule (daily is plenty, prices rarely move more often). Send the dataset to Google Sheets, Slack, email, Make, Zapier or n8n with the Apify integrations, or read it through the REST API.

Use with the API, n8n, Make, Zapier or AI agents

API (one call, returns the rows as JSON):

$curl -X POST "https://api.apify.com/v2/acts/transparent_meteorite~llm-pricing-tracker/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" -H "Content-Type: application/json" -d '{"models":["claude","gpt"],"sortBy":"inputPrice","maxItems":25}'

Python

from apify_client import ApifyClient
client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("transparent_meteorite/llm-pricing-tracker").call(run_input={"models": ["claude", "gpt", "gemini"], "maxItems": 25})
for row in client.dataset(run["defaultDatasetId"]).iterate_items():
print(row["model"], row["inputPricePerM"], row["outputPricePerM"], row["priceChange"])
  • n8n, Make, Zapier: use the Apify app's "Run Actor" step with actor transparent_meteorite/llm-pricing-tracker, paste the input JSON, then map the dataset items to your sheet or message.
  • AI agents (MCP): connect the Apify MCP server at https://mcp.apify.com?tools=transparent_meteorite/llm-pricing-tracker to Claude, Cursor or any MCP client, and your agent can look up live model prices as a tool.

The Actor reads a public, key-free price catalog and does not log in or bypass anything. The prices are factual public information. This is an independent tool and is not affiliated with any model maker or hosting provider. Always confirm the price on the provider's own page before signing a contract.

FAQ

Do I need an API key? No. Neither the source nor the Actor needs one.

Which providers are covered? Every maker and host listed in the catalog, which is more than 400 models from the large labs and open-weight hosts. Use providers to narrow it down.

Why is a price null? The model does not have that price, or its price is variable (router and auto models). Zero always means free.

How do I get price changes? Keep Track price changes on and run at least twice. The first run saves the baseline. From then on priceChange is up, down or unchanged, and changedAt is the time the Actor first saw the new price.

Can I get the price of one model at every host? Yes. Set models to its name and turn on One row per provider endpoint.

Are batch or discounted tiers shown? Batch variants that the catalog lists as separate models appear as their own rows, usually with a :batch suffix in the id. The discount field shows a host's listed discount when there is one.

Why do I get fewer rows than maxItems? Fewer models matched your filters. The run status says which filters were active.

Are the prices real-time? They are read live at the start of every run.

Support

Found a model that reads wrongly, or need another field? Open an issue on the Issues tab with the run URL and the model id.

Changelog

  • 0.1: First private build. Prices per million tokens, filters, provider endpoints, price-change tracking.