Use routing.run credits in LLM Playground for smarter AI chats

Connect your routing.run account to LLM Playground and use your credits inside a full-featured AI chat app with characters, search, and file creation.

If you have routing.run credits, you don’t have to choose between smart model routing and a rich chat experience. LLM Playground lets you connect your routing.run account and use those credits inside a full AI workspace—complete with AI characters, web search, document analysis, and file generation. No email or credit card is required to start, and the built-in free model keeps chatting unlimited even if your credits run low. Here’s how to bring routing.run into LLM Playground and make the most of both tools in one place.

Why combine routing.run with LLM Playground?

routing.run is an OpenAI-compatible router that lets you access dozens of models through a single API endpoint. It learns which model performs best for each type of prompt, saving you the trial-and-error of picking providers manually. But routing.run is an API—it doesn’t include a chat interface, characters, or the extras that turn raw model responses into a productive workspace.

LLM Playground fills that gap. It’s a free AI app that gives you a full chat environment, AI characters (Character Card v2), web search, deep research, document analysis, and group rooms. You can even generate downloadable files—PDFs, spreadsheets, images—directly in chat. Every account includes a built-in free model with unlimited messages, so you can keep chatting even when your routing.run credits are low. By connecting routing.run to LLM Playground, you get the best of both: smart model routing and a feature-rich app.

• Access routing.run’s 30+ models without leaving a chat interface
• Use AI characters, web search, and document analysis alongside routed responses
• Generate and download files (PDFs, spreadsheets, images) from routed model outputs
• Switch between routing.run and the built-in free model anytime

How to connect routing.run to LLM Playground

Connecting your routing.run account takes less than a minute. In LLM Playground, go to the provider settings and select routing.run from the list. Enter your routing.run API key (found in your routing.run dashboard) and save. Your credentials are encrypted and never shared with LLM Playground or any third party.

Once connected, routing.run appears as a model option in every chat. Select it just like you would any other provider, and your prompts will be routed to the best available model based on routing.run’s scoring system. You’ll see the model name and cost in the chat metadata, so you always know what’s running and how much it’s using your credits.

• No email or credit card required to sign up for LLM Playground
• Your routing.run API key stays encrypted and private
• routing.run models appear alongside other providers in the model picker
• Chat metadata shows which model was used and the cost

What you can do with routing.run inside LLM Playground

With routing.run connected, you’re not limited to basic chat. LLM Playground’s features work seamlessly with routed responses. For example:

Use AI characters to role-play scenarios or get creative writing help, with routing.run picking the best model for the task. Need a spreadsheet? Generate one from a routed response and download it as an Excel file. Upload a document and ask routing.run to analyze, summarize, or rewrite it—then save the output as a PDF.

Web search and deep research also work with routing.run. Ask a question, and LLM Playground will fetch live results, then route your query to the best model for synthesis. The built-in free model is always there as a fallback, so you’re never locked out of chatting.

• AI characters (Character Card v2) with routed model responses
• Generate and download files (PDFs, Word docs, spreadsheets, images) from routed outputs
• Web search and deep research with routed synthesis
• Group rooms for collaborative chats using routing.run models

Free built-in model vs. routing.run: what’s the difference?

LLM Playground gives you two ways to chat: the built-in free model and any connected provider, including routing.run. Here’s how they compare:

The built-in model is unlimited and requires no API key or credits. It’s ideal for casual chats, quick questions, or when you want to save your routing.run credits for more demanding tasks. routing.run, on the other hand, gives you access to a wider range of models and smart routing, but it uses your routing.run credits. If you run out of credits, you can switch back to the free model anytime without losing your chat history.

Tips for getting the most from routing.run in LLM Playground

To make the most of your routing.run credits inside LLM Playground, try these approaches:

Start with the built-in free model for simple chats, then switch to routing.run when you need higher-quality responses or specific models. Use the model comparison arena to test how routing.run’s choices stack up against other providers for your use case. If you’re generating files, routing.run’s smarter routing can often produce better-structured outputs for spreadsheets or formatted documents.

Keep an eye on your routing.run dashboard to monitor credit usage and see which models are being selected. The dashboard also lets you manually rate responses, which helps routing.run improve its routing decisions over time. If you’re working in a group room, routing.run can handle multiple users’ prompts efficiently, so you don’t have to worry about rate limits or model availability.

• Use the built-in free model for casual chats to save routing.run credits
• Test routing.run’s model choices in the model comparison arena
• Generate files from routed responses for better-structured outputs
• Rate responses in the routing.run dashboard to improve future routing

Providers you can use alongside routing.run

LLM Playground supports multiple OpenAI-compatible providers, so you can mix and match based on your needs. routing.run is just one option—others include Airforce, Pollinations, g4f, NavyAI, VoidAI, InferencePort, and Tomdacat. Each provider has its own pricing, models, and strengths, and you can switch between them in the same chat.

For example, you might use Airforce for image generation (since the built-in free model doesn’t support images) and routing.run for chat. Or, you could compare routing.run’s responses with those from another provider in the model comparison arena. Your credentials for each provider are encrypted, and LLM Playground never marks up or resells access—you’re billed directly by the provider at their own rates.

• Connect multiple providers (Airforce, Pollinations, g4f, etc.) alongside routing.run
• Switch between providers in the same chat
• Use Airforce or Pollinations for image generation, routing.run for chat
• Compare routing.run’s responses with other providers in the model arena