# LLM Price Tracker — OpenRouter Markup vs Provider List Prices (`kaz_kakyo/llm-price-alerts`) Actor See OpenRouter's estimated markup vs each provider's direct list price — full comparison table every run. Optional scheduled alerts when prices, context windows, or markups move. Clean JSON, keyless sources, watchlist filters. - **URL**: https://apify.com/kaz\_kakyo/llm-price-alerts.md - **Developed by:** [Heim AI](https://apify.com/kaz_kakyo) (community) - **Categories:** AI, Developer tools, Automation - **Stats:** 2 total users, 0 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing from $1.00 / 1,000 markup table rows This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## LLM Price Tracker — OpenRouter Markup vs Provider List Prices **See what OpenRouter's markup is right now, and get a structured feed of LLM API price changes on a schedule.** Free keyless JSON sources, no scraping, no personal data. Detection is per-run: changes surface on your next scheduled run, not in real time. ### What you get **1. The current markup table — every run, including the first.** OpenRouter resells other providers' models, often at a markup, sometimes at a discount. One `markup_snapshot` row per OpenRouter model with a confidently matched direct list price (from the LiteLLM price map), worst markup first: ```json { "eventType": "markup_snapshot", "modelId": "google/gemini-flash-latest", "openrouterPromptPrice": 1.5, "openrouterCompletionPrice": 9, "listPromptPrice": 0.3, "listCompletionPrice": 2.5, "markupPromptPct": 400, "markupCompletionPct": 260, "matchedLitellmKey": "gemini/gemini-flash-latest", "detectedAt": "2026-07-12T06:00:00.000Z" } ```` Matching is high-confidence only: provider family + exact normalized name. Ambiguous names are refused, not guessed — models without a confident match don't get a row. The markup is an **estimate** (LiteLLM's list price is community-maintained); `matchedLitellmKey` lets you audit every pairing. Toggle with `includeMarkupSnapshot` (needs both sources). **2. A change feed for scheduled alerting.** Each run diffs current prices against your previous run and emits one event per change: ```json { "eventType": "price_change", "modelId": "openai/gpt-5", "source": "openrouter", "field": "completionPrice", "oldValue": 10, "newValue": 8, "pctChange": -20, "direction": "decrease", "detectedAt": "2026-07-10T09:00:00.000Z", "prevRunAt": "2026-07-09T09:00:00.000Z" } ``` `eventType` is one of `price_change`, `context_change`, `new_model`, `removed_model`, `markup_change` (markup changes also carry the four underlying prices so you can check the arithmetic). All prices are **$ per 1,000,000 tokens** — the unit providers quote. `0` = free; when a percent genuinely can't be computed (e.g. free → paid), the event still fires with `pctChange: null`, never a fabricated number. ### How to use it (zero setup, no API key) 1. Optionally set a **watchlist** — model-id substrings or globs (`gpt-5`, `claude-opus`, `anthropic/*`). Empty = watch everything. 2. Pick **sources** (default both): `openrouter` (~350 models) and `litellm` (broad multi-provider map). 3. Run it on a **schedule** (hourly/daily). Give each independent schedule its own `monitorId` — two schedules sharing one starve each other, because each run consumes the diff. 4. **First run is a baseline**: it emits zero change-events (nothing to compare yet) but still delivers the full markup table. A later run with 0 items just means nothing changed — normal, not an error. ### Cost controls - `changeThresholdPct` — suppress price/context moves smaller than this **relative %** (e.g. `5` hides a +4% move). - `markupThresholdPts` — suppress markup moves smaller than this many absolute **percentage points**. - `maxItems` caps delivered rows per event class. The cap is **lossy**: excess changes are dropped permanently (the snapshot still advances), not queued for next run. - Change events are delivered before the markup table, so alerts keep budget priority if your Max total charge runs out. ### When a source breaks If a source returns zero priced models, or its model count drops more than `maxSourceDropPct` (default 40%) since the last run, the run **skips the diff**: nothing charged, snapshot untouched, so an upstream outage can't bill you a flood of false `removed_model` events. The run still succeeds and emits one uncharged `source_degraded` item you can alert on. ### Pricing Pay per delivered row: `price-change-detected` per change-event, `markup-snapshot-row` per markup-table row (set `includeMarkupSnapshot: false` for a pure change feed), plus the standard per-run `apify-actor-start` charge. Rows filtered out by your watchlist or thresholds are never charged. One real-world price cut can produce more than one row — e.g. a completion-price drop is 1 `price_change` and, since it moves OpenRouter's markup, 1 `markup_change`. ### Limitations - **Coverage follows the aggregators.** A model shipped only through a lab's own API (e.g. Meta's Muse Spark, July 2026) is invisible here until OpenRouter or LiteLLM lists it — then a `new_model` event fires automatically. - **Markup is an estimate**, dependent on LiteLLM's community-maintained prices; unmatched models carry `null`, not a guess. - **Detection is per-run.** Run more frequently for tighter latency. ### Data sources [OpenRouter models API](https://openrouter.ai/api/v1/models) and the [LiteLLM price map](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json) — both public JSON, queried with an identifying User-Agent. Not affiliated with or endorsed by OpenRouter, BerriAI/LiteLLM, or any provider; verify prices against the provider's official page before commercial decisions. *** *Found this useful? A [review](https://apify.com/kaz_kakyo/llm-price-alerts) helps others find it. Hit a problem? [Open an issue](https://apify.com/kaz_kakyo/llm-price-alerts/issues) and I'll fix it fast.* ### Telemetry Each run records one anonymous event to the developer's own storage: a salted hash of the caller account ID (never the raw ID), the run origin, and a timestamp. No inputs, results, or personal data — this only measures adoption. # Actor input Schema ## `watchlist` (type: `array`): Only emit changes for models whose id matches one of these. Plain text is a case-insensitive substring (e.g. `gpt-5`, `claude-opus`, `glm`); `*`/`?` globs are supported (e.g. `anthropic/*`). **Leave empty to watch ALL models — that is the runtime default.** The `gpt-5`/`claude-opus`/`gemini` values shown prefilled in the Console are only a starter example, not a default; clear them to watch everything. Matching affects only which events are emitted — the price snapshot always covers every model, so changing this list never fabricates new/removed events. ## `monitorId` (type: `string`): Names the snapshot this schedule diffs against. Run **one schedule per monitorId**. The diff is consumed as it is reported: two schedules that share a monitorId (and the same sources) will starve each other — each run consumes the change the other would have reported. Give each independent schedule its own value (e.g. `hourly-all`, `daily-watchlist`). Leave empty to use the shared `default` scope. ## `sources` (type: `array`): Where to pull current model pricing. OpenRouter = ~350 models with per-token prompt/completion prices; LiteLLM = a broad multi-provider map (OpenAI, Anthropic, Google, Bedrock, Mistral, Meta…). Both are free, keyless JSON APIs. ## `changeThresholdPct` (type: `integer`): Relative-percent gate for `price_change` and `context_change` events: emit only if the absolute % move is at least this large. 0 = report every change. Example: at `5`, a price moving 100→104 ($/1M, a 4% move) is suppressed; 100→106 (6%) passes. Does NOT gate new/removed models or markup (see `markupThresholdPts`). Transitions where a % can't be computed — free↔paid, and a price appearing or disappearing (number↔null) — always pass. ## `markupThresholdPts` (type: `integer`): Absolute percentage-POINT gate for `markup_change` events (OpenRouter's estimated markup over the LiteLLM list price). 0 = report every markup move. This is points, not relative percent: at `2`, a markup moving from +10 to +11 points (a 1-point move) is suppressed; +10 to +13 (3 points) passes. Kept separate from `changeThresholdPct` because a markup figure is already a percentage. ## `includeNewModels` (type: `boolean`): Emit an event when a model appears that was not in the previous snapshot. ## `includeRemovedModels` (type: `boolean`): Emit an event when a model that was in the previous snapshot has disappeared. ## `includeMarkupSnapshot` (type: `boolean`): On every run (including the first), output one `markup_snapshot` row per OpenRouter model matched to a direct provider list price: OpenRouter price vs list price vs markup % per 1M tokens, worst markup first. This is the current-state comparison — change events only fire when something moves between runs. Needs both sources selected. Rows bill as `markup-snapshot-row`. Turn off for a pure change feed. ## `maxItems` (type: `integer`): Maximum change-events delivered per run. Keeps cost predictable — you are charged once per delivered event. **Lossy cap:** when the number of changes exceeds this (or your run's Max total charge), the excess is dropped permanently — it is NOT queued for the next run, and the snapshot still advances to today's prices, so those dropped changes are never re-reported. Raise this if completeness matters more than a cost ceiling. A volatile pricing day can legitimately produce many events, so this defaults high. ## `maxSourceDropPct` (type: `integer`): Outage safety valve. If a source's priced-model count falls more than this percent versus the previous snapshot, the run skips the diff WITHOUT charging or advancing the snapshot — an upstream outage that made half a source's models vanish would otherwise bill you for a flood of false `removed_model` events. The run still succeeds and emits an uncharged `source_degraded` item you can alert on. Default 40. Lower it to be stricter; set 100 to disable. If a large drop is genuine (a provider really delisted models), raise this to let it through. ## Actor input object example ```json { "watchlist": [ "gpt-5", "claude-opus", "gemini" ], "monitorId": "", "sources": [ "openrouter", "litellm" ], "changeThresholdPct": 0, "markupThresholdPts": 0, "includeNewModels": true, "includeRemovedModels": true, "includeMarkupSnapshot": true, "maxItems": 1000, "maxSourceDropPct": 40 } ``` # Actor output Schema ## `changes` (type: `string`): No description # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "watchlist": [ "gpt-5", "claude-opus", "gemini" ] }; // Run the Actor and wait for it to finish const run = await client.actor("kaz_kakyo/llm-price-alerts").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "watchlist": [ "gpt-5", "claude-opus", "gemini", ] } # Run the Actor and wait for it to finish run = client.actor("kaz_kakyo/llm-price-alerts").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "watchlist": [ "gpt-5", "claude-opus", "gemini" ] }' | apify call kaz_kakyo/llm-price-alerts --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=kaz_kakyo/llm-price-alerts", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "LLM Price Tracker — OpenRouter Markup vs Provider List Prices", "description": "See OpenRouter's estimated markup vs each provider's direct list price — full comparison table every run. Optional scheduled alerts when prices, context windows, or markups move. Clean JSON, keyless sources, watchlist filters.", "version": "0.0", "x-build-id": "F7wlgZmBK1XmPoFHe" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kaz_kakyo~llm-price-alerts/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kaz_kakyo-llm-price-alerts", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/kaz_kakyo~llm-price-alerts/runs": { "post": { "operationId": "runs-sync-kaz_kakyo-llm-price-alerts", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/kaz_kakyo~llm-price-alerts/run-sync": { "post": { "operationId": "run-sync-kaz_kakyo-llm-price-alerts", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "watchlist": { "title": "Model watchlist (substrings or globs)", "type": "array", "description": "Only emit changes for models whose id matches one of these. Plain text is a case-insensitive substring (e.g. `gpt-5`, `claude-opus`, `glm`); `*`/`?` globs are supported (e.g. `anthropic/*`). **Leave empty to watch ALL models — that is the runtime default.** The `gpt-5`/`claude-opus`/`gemini` values shown prefilled in the Console are only a starter example, not a default; clear them to watch everything. Matching affects only which events are emitted — the price snapshot always covers every model, so changing this list never fabricates new/removed events.", "items": { "type": "string" } }, "monitorId": { "title": "Monitor ID (snapshot scope)", "type": "string", "description": "Names the snapshot this schedule diffs against. Run **one schedule per monitorId**. The diff is consumed as it is reported: two schedules that share a monitorId (and the same sources) will starve each other — each run consumes the change the other would have reported. Give each independent schedule its own value (e.g. `hourly-all`, `daily-watchlist`). Leave empty to use the shared `default` scope.", "default": "" }, "sources": { "title": "Pricing sources", "type": "array", "description": "Where to pull current model pricing. OpenRouter = ~350 models with per-token prompt/completion prices; LiteLLM = a broad multi-provider map (OpenAI, Anthropic, Google, Bedrock, Mistral, Meta…). Both are free, keyless JSON APIs.", "items": { "type": "string", "enum": [ "openrouter", "litellm" ], "enumTitles": [ "OpenRouter — openrouter.ai/api/v1/models", "LiteLLM — community multi-provider price map" ] }, "default": [ "openrouter", "litellm" ] }, "changeThresholdPct": { "title": "Minimum price / context change (%)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Relative-percent gate for `price_change` and `context_change` events: emit only if the absolute % move is at least this large. 0 = report every change. Example: at `5`, a price moving 100→104 ($/1M, a 4% move) is suppressed; 100→106 (6%) passes. Does NOT gate new/removed models or markup (see `markupThresholdPts`). Transitions where a % can't be computed — free↔paid, and a price appearing or disappearing (number↔null) — always pass.", "default": 0 }, "markupThresholdPts": { "title": "Minimum markup change (percentage points)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Absolute percentage-POINT gate for `markup_change` events (OpenRouter's estimated markup over the LiteLLM list price). 0 = report every markup move. This is points, not relative percent: at `2`, a markup moving from +10 to +11 points (a 1-point move) is suppressed; +10 to +13 (3 points) passes. Kept separate from `changeThresholdPct` because a markup figure is already a percentage.", "default": 0 }, "includeNewModels": { "title": "Emit new-model events", "type": "boolean", "description": "Emit an event when a model appears that was not in the previous snapshot.", "default": true }, "includeRemovedModels": { "title": "Emit removed-model events", "type": "boolean", "description": "Emit an event when a model that was in the previous snapshot has disappeared.", "default": true }, "includeMarkupSnapshot": { "title": "Include current markup table", "type": "boolean", "description": "On every run (including the first), output one `markup_snapshot` row per OpenRouter model matched to a direct provider list price: OpenRouter price vs list price vs markup % per 1M tokens, worst markup first. This is the current-state comparison — change events only fire when something moves between runs. Needs both sources selected. Rows bill as `markup-snapshot-row`. Turn off for a pure change feed.", "default": true }, "maxItems": { "title": "Max change-events per run", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum change-events delivered per run. Keeps cost predictable — you are charged once per delivered event. **Lossy cap:** when the number of changes exceeds this (or your run's Max total charge), the excess is dropped permanently — it is NOT queued for the next run, and the snapshot still advances to today's prices, so those dropped changes are never re-reported. Raise this if completeness matters more than a cost ceiling. A volatile pricing day can legitimately produce many events, so this defaults high.", "default": 1000 }, "maxSourceDropPct": { "title": "Source drop guard (%)", "minimum": 0, "maximum": 100, "type": "integer", "description": "Outage safety valve. If a source's priced-model count falls more than this percent versus the previous snapshot, the run skips the diff WITHOUT charging or advancing the snapshot — an upstream outage that made half a source's models vanish would otherwise bill you for a flood of false `removed_model` events. The run still succeeds and emits an uncharged `source_degraded` item you can alert on. Default 40. Lower it to be stricter; set 100 to disable. If a large drop is genuine (a provider really delisted models), raise this to let it through.", "default": 40 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```