# OpenRouter (`apify/openrouter`) Actor You can use any AI LLM model without accounts in AI providers. Use this Actor as a proxy for all requests. Use pay-per-event pricing to pay only for the real credit used. - **URL**: https://apify.com/apify/openrouter.md - **Developed by:** [Apify](https://apify.com/apify) (Apify) - **Categories:** AI, Agents - **Stats:** 12,990 total users, 361 monthly users, 96.2% runs succeeded, 42 bookmarks - **User rating**: 4.92 out of 5 stars ## Pricing from $0.01 / 1,000 ai model tokens This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage. Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have. Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event ## What's an Apify Actor? An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes. 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. Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md. ## 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. Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run. For examples already wired to this Actor's own input schema, see the [API](#api) section below. Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`). # README ## OpenRouter Proxy This Apify Actor proxies the [OpenRouter](https://openrouter.ai) API over an OpenAI-compatible interface, billed to your Apify account on a pay-per-event basis. ### What this Actor does - **Proxy access**: Forwards API requests to OpenRouter's models - **OpenRouter SDK compatible**: Works with the official [`@openrouter/sdk`](https://www.npmjs.com/package/@openrouter/sdk) (TypeScript) and any OpenAI-compatible HTTP client - **Billing**: Charges your Apify account at OpenRouter's rates (see [Pricing](#pricing)) - **Supports**: chat completions, embeddings, streaming, and image generation via `modalities` - **Multiple API formats**: OpenAI (`/chat/completions`), Anthropic (`/messages`), and OpenAI Responses (`/responses`) - **Standby mode**: Runs in Standby mode with a static URL, like a standard web server ### Supported endpoints | Method | Endpoint | Description | | ------ | ------------------------------------------ | -------------------------------- | | POST | `/api/v1/chat/completions` | Chat completions (OpenAI format) | | POST | `/api/v1/systemone` | System One (Jev, TypeSafe SDKs) | | POST | `/api/v1/messages` | Messages (Anthropic format) | | POST | `/api/v1/responses` | Responses (OpenAI Responses API) | | POST | `/api/v1/embeddings` | Text embeddings | | GET | `/api/v1/models` | List available models | | GET | `/api/v1/models/count` | Model count | | GET | `/api/v1/models/user` | User model preferences | | GET | `/api/v1/models/{author}/{slug}/endpoints` | Model endpoints | | GET | `/api/v1/embeddings/models` | Embedding models | | GET | `/api/v1/providers` | Available providers | | GET | `/api/v1/endpoints/zdr` | Zero-data-retention endpoints | | GET | `/api/v1/generation` | Generation details | For full API documentation, see the [OpenRouter API docs](https://openrouter.ai/docs/api-reference). #### System One (Jev) TypeSafe's Jev is a System One model: it returns typed decisions, not generated text, and does not use `/api/v1/chat/completions`. OpenRouter serves it on `/api/v1/systemone`, the route the [TypeSafe SDKs](https://openrouter.ai/docs/guides/community/typesafe-sdk) append to their base URL, so `@typesafe-ai/sdk` / `typesafe_sdk` work by pointing `baseURL` at this Actor. Send `model`, `questions`, and `state`; the response contains typed `answers` and `usage.cost`. The proxy uses that cost for the same pay-per-event billing as other inference endpoints. See the [TypeSafe SDK guide](https://openrouter.ai/docs/guides/community/typesafe-sdk) for question types and request examples. System One returns usage without an opt-in and has no `max_tokens` parameter. The proxy leaves these requests unchanged, including for FREE users; its existing billing and spending-limit handling still applies. ### Pricing This Actor uses a pay-per-event pricing model on the Apify platform. You pay for the tokens used by the OpenRouter API. Free tier users pay 10x more than paying users. Chat and Responses requests have a 2,048-output-token cap; System One has no output-token limit parameter. #### Pricing structure - **Event**: `openrouter-api-usage` - **Paying users**: Pay the exact OpenRouter cost (rounded up to nearest $0.00001) #### Pricing examples | OpenRouter cost | Calculation | Charged events | You pay | Markup factor | | --------------- | ---------------------- | -------------- | -------- | ------------- | | $0.00001212 | `0.00001212 / 0.00001` | 2 | $0.00002 | 1.65x | | $0.0001 | `0.0001 / 0.00001` | 10 | $0.0001 | 1x (exact) | | $0.001 | `0.001 / 0.00001` | 100 | $0.001 | 1x (exact) | | $0.01 | `0.01 / 0.00001` | 1,000 | $0.01 | 1x (exact) | ### Quick start The proxy only accepts calls from inside the Apify platform (caller type `APIFY_ACTOR`). The examples below use the official [OpenRouter TypeScript SDK](https://openrouter.ai/docs/client-sdks/typescript/overview); any OpenAI-compatible HTTP client also works — point it at the same base URL and pass your Apify token as the bearer. #### 1. Install [`@openrouter/sdk`](https://www.npmjs.com/package/@openrouter/sdk) ```bash npm install @openrouter/sdk ``` #### 2. Basic usage Point the SDK at the proxy with `serverURL`, and pass your Apify token as `apiKey` — the SDK sends it as `Authorization: Bearer `, which is what the proxy expects. ```typescript import { OpenRouter } from '@openrouter/sdk'; const client = new OpenRouter({ serverURL: 'https://openrouter.apify.actor/api/v1', apiKey: process.env.APIFY_TOKEN, // Apify token is loaded automatically in runtime }); const result = await client.chat.send({ chatRequest: { model: 'openrouter/auto', messages: [ { role: 'user', content: 'What is the meaning of life?', }, ], }, }); console.log(result.choices[0].message.content); ``` #### 3. Streaming responses Set `stream: true` inside `chatRequest`. The SDK returns an async iterable of SSE chunks; the final chunk carries the `usage` object the proxy uses for billing. ```typescript const stream = await client.chat.send({ chatRequest: { model: 'openrouter/auto', messages: [ { role: 'user', content: 'Write a short story about a robot.', }, ], stream: true, }, }); for await (const chunk of stream) { process.stdout.write(chunk.choices[0]?.delta?.content ?? ''); } ``` #### 4. Image generation OpenRouter generates images through chat completions on image-capable models, using the `modalities` parameter: ```typescript const result = await client.chat.send({ chatRequest: { model: 'google/gemini-2.5-flash-image', // Image-capable model messages: [ { role: 'user', content: 'Generate an image of a cute baby sea otter', }, ], modalities: ['text', 'image'], // Enable image generation }, }); // Generated image data lives on the assistant message console.log(result.choices[0].message); ``` **Note:** OpenRouter does not expose an OpenAI-style `/images/generations` endpoint. Image generation goes through compatible chat-completion models. Check available image-capable models on [OpenRouter's models page](https://openrouter.ai/models). #### Using a different client The proxy is OpenAI-compatible, so any client that lets you set the base URL and the `Authorization` header works — point it at `https://openrouter.apify.actor/api/v1` and pass `Authorization: Bearer `. The [OpenAI SDK](https://www.npmjs.com/package/openai) can be wired up this way, but it currently rejects some of the SSE events OpenRouter emits on streamed responses; prefer `@openrouter/sdk` above. Raw `fetch` works too: ```typescript const res = await fetch('https://openrouter.apify.actor/api/v1/chat/completions', { method: 'POST', headers: { 'content-type': 'application/json', Authorization: `Bearer ${process.env.APIFY_TOKEN}`, }, body: JSON.stringify({ model: 'openrouter/auto', messages: [{ role: 'user', content: 'Hello' }], }), }); ``` ### Available models Every model OpenRouter serves is reachable through this proxy. For the full list, see [OpenRouter's models page](https://openrouter.ai/models) or call `GET /api/v1/models`. ### Authentication The Actor uses your Apify token for authentication. In Actor environments on the Apify platform, `APIFY_TOKEN` is automatically available. ### Support For issues related to this Actor, please [open an issue](https://github.com/apify/actor-openrouter-proxy/issues) or contact the Actor developer on [Apify Store](https://apify.com/apify/openrouter). # Actor input Schema ## Actor input object example ```json {} ``` # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = {}; // Run the Actor and wait for it to finish const run = await client.actor("apify/openrouter").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${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 = {} # Run the Actor and wait for it to finish run = client.actor("apify/openrouter").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}") for item in client.dataset(run.default_dataset_id).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{}' | apify call apify/openrouter --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "type": "http", "url": "https://mcp.apify.com/?tools=fetch-actor-details,apify/openrouter" } } } ``` The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer ` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations). ## OpenAPI specification Download the OpenAPI definition: https://api.apify.com/v2/actors/sxck9mShRCfmMOZ8S/builds/wHKMEBRF6hRcCH5cq/openapi.json