Free Models Router
Get started with free AI inference using the OpenRouter Chat Playground
OpenRouter offers free models that let you experiment with AI without any cost. The easiest way to try these models is through the Chat Playground, where you can start chatting immediately.
The simplest way to get free inference is to use openrouter/free, our Free Models Router that automatically selects a free model at random from the available free models on OpenRouter. The router intelligently filters for models that support the features your request needs, such as image understanding, tool calling, and structured outputs.
Navigate to openrouter.ai/chat to access the Chat Playground.
Click the Add Model button (or press Cmd+K / Ctrl+K) to open the model selector. Type “free” in the search box to filter for free models.
You’ll see a list of available free models, including the Free Models Router option.
Click on Free Models Router to select it. This router will automatically choose a free model for each request based on your needs.
Once selected, you can start sending messages. The Free Models Router will route your request to an appropriate free model, and you’ll see which model responded in the chat.
In this example, the Free Models Router selected Solar Pro 3 (free) to respond to the message.
If you prefer to use a specific free model rather than the Free Models Router, you can select any model with “(free)” in its name from the model selector. Some popular free models include:
You can also use the Free Models Router programmatically. Simply set the model to openrouter/free in your API requests:
For more details on the Free Models Router API, see the API Quickstart.
Free models may have different rate limits and availability compared to paid models. They are ideal for experimentation, learning, and low-volume use cases. For production workloads with higher reliability requirements, consider using paid models.
:free variant suffix